Improvise a Jazz Solo with an LSTM Network
2018-02-05 12:36
651 查看
Improvise a Jazz Solo with an LSTM Network
Welcome to your final programming assignment of this week! In this notebook, you will implement a model that uses an LSTM to generate music. You will even be able to listen to your own music at the end of the assignment.You will learn to:
- Apply an LSTM to music generation.
- Generate your own jazz music with deep learning.
Please run the following cell to load all the packages required in this assignment. This may take a few minutes.
from __future__ import print_function import IPython import sys from music21 import * import numpy as np from grammar import * from qa import * from preprocess import * from music_utils import * from data_utils import * from keras.models import load_model, Model from keras.layers import Dense, Activation, Dropout, Input, LSTM, Reshape, Lambda, RepeatVector from keras.initializers import glorot_uniform from keras.utils import to_categorical from keras.optimizers import Adam from keras import backend as K
Using TensorFlow backend.
1 - Problem statement
You would like to create a jazz music piece specially for a friend’s birthday. However, you don’t know any instruments or music composition. Fortunately, you know deep learning and will solve this problem using an LSTM netwok.You will train a network to generate novel jazz solos in a style representative of a body of performed work.
1.1 - Dataset
You will train your algorithm on a corpus of Jazz music. Run the cell below to listen to a snippet of the audio from the training set:We have taken care of the preprocessing of the musical data to render it in terms of musical “values.” You can informally think of each “value” as a note, which comprises a pitch and a duration. For example, if you press down a specific piano key for 0.5 seconds, then you have just played a note. In music theory, a “value” is actually more complicated than this–specifically, it also captures the information needed to play multiple notes at the same time. For example, when playing a music piece, you might press down two piano keys at the same time (playng multiple notes at the same time generates what’s called a “chord”). But we don’t need to worry about the details of music theory for this assignment. For the purpose of this assignment, all you need to know is that we will obtain a dataset of values, and will learn an RNN model to generate sequences of values.
Our music generation system will use 78 unique values. Run the following code to load the raw music data and preprocess it into values. This might take a few minutes.
X, Y, n_values, indices_values = load_music_utils()
print('shape of X:', X.shape)
print('number of training examples:', X.shape[0])
print('Tx (length of sequence):', X.shape[1])
print('total # of unique values:', n_values)
print('Shape of Y:', Y.shape)shape of X: (60, 30, 78) number of training examples: 60 Tx (length of sequence): 30 total # of unique values: 78 Shape of Y: (30, 60, 78)
You have just loaded the following:
X: This is an (m, TxTx, 78) dimensional array. We have m training examples, each of which is a snippet of Tx=30Tx=30 musical values. At each time step, the input is one of 78 different possible values, represented as a one-hot vector. Thus for example, X[i,t,:] is a one-hot vector representating the value of the i-th example at time t.
Y: This is essentially the same as
X, but shifted one step to the left (to the past). Similar to the dinosaurus assignment, we’re interested in the network using the previous values to predict the next value, so our sequence model will try to predict y⟨t⟩y⟨t⟩ given x⟨1⟩,…,x⟨t⟩x⟨1⟩,…,x⟨t⟩. However, the data in
Yis reordered to be dimension (Ty,m,78)(Ty,m,78), where Ty=TxTy=Tx. This format makes it more convenient to feed to the LSTM later.
n_values: The number of unique values in this dataset. This should be 78.
indices_values: python dictionary mapping from 0-77 to musical values.
1.2 - Overview of our model
Here is the architecture of the model we will use. This is similar to the Dinosaurus model you had used in the previous notebook, except that in you will be implementing it in Keras. The architecture is as follows:
We will be training the model on random snippets of 30 values taken from a much longer piece of music. Thus, we won’t bother to set the first input x⟨1⟩=0⃗ x⟨1⟩=0→, which we had done previously to denote the start of a dinosaur name, since now most of these snippets of audio start somewhere in the middle of a piece of music. We are setting each of the snippts to have the same length Tx=30Tx=30 to make vectorization easier.
2 - Building the model
In this part you will build and train a model that will learn musical patterns. To do so, you will need to build a model that takes in X of shape (m,Tx,78)(m,Tx,78) and Y of shape (Ty,m,78)(Ty,m,78). We will use an LSTM with 64 dimensional hidden states. Lets setn_a = 64.
n_a = 64
Here’s how you can create a Keras model with multiple inputs and outputs. If you’re building an RNN where even at test time entire input sequence x⟨1⟩,x⟨2⟩,…,x⟨Tx⟩x⟨1⟩,x⟨2⟩,…,x⟨Tx⟩ were given in advance, for example if the inputs were words and the output was a label, then Keras has simple built-in functions to build the model. However, for sequence generation, at test time we don’t know all the values of x⟨t⟩x⟨t⟩ in advance; instead we generate them one at a time using x⟨t⟩=y⟨t−1⟩x⟨t⟩=y⟨t−1⟩. So the code will be a bit more complicated, and you’ll need to implement your own for-loop to iterate over the different time steps.
The function
djmodel()will call the LSTM layer TxTx times using a for-loop, and it is important that all TxTx copies have the same weights. I.e., it should not re-initiaiize the weights every time—the TxTx steps should have shared weights. The key steps for implementing layers with shareable weights in Keras are:
1. Define the layer objects (we will use global variables for this).
2. Call these objects when propagating the input.
We have defined the layers objects you need as global variables. Please run the next cell to create them. Please check the Keras documentation to make sure you understand what these layers are: Reshape(), LSTM(), Dense().
reshapor = Reshape((1, 78)) # Used in Step 2.B of djmodel(), below LSTM_cell = LSTM(n_a, return_state = True) # Used in Step 2.C densor = Dense(n_values, activation='softmax') # Used in Step 2.D
Each of
reshapor,
LSTM_celland
densorare now layer objects, and you can use them to implement
djmodel(). In order to propagate a Keras tensor object X through one of these layers, use
layer_object(X)(or
layer_object([X,Y])if it requires multiple inputs.). For example,
reshapor(X)will propagate X through the
Reshape((1,78))layer defined above.
Exercise: Implement
djmodel(). You will need to carry out 2 steps:
Create an empty list “outputs” to save the outputs of the LSTM Cell at every time step.
Loop for t∈1,…,Txt∈1,…,Tx:
A. Select the “t”th time-step vector from X. The shape of this selection should be (78,). To do so, create a custom Lambda layer in Keras by using this line of code:
x = Lambda(lambda x: X[:,t,:])(X)
Look over the Keras documentation to figure out what this does. It is creating a “temporary” or “unnamed” function (that’s what Lambda functions are) that extracts out the appropriate one-hot vector, and making this function a Keras
Layerobject to apply to
X.
B. Reshape x to be (1,78). You may find the `reshapor()` layer (defined below) helpful. C. Run x through one step of LSTM_cell. Remember to initialize the LSTM_cell with the previous step's hidden state $a$ and cell state $c$. Use the following formatting:
a, _, c = LSTM_cell(input_x, initial_state=[previous hidden state, previous cell state])
D. Propagate the LSTM's output activation value through a dense+softmax layer using `densor`. E. Append the predicted value to the list of "outputs"
# GRADED FUNCTION: djmodel def djmodel(Tx, n_a, n_values): """ Implement the model Arguments: Tx -- length of the sequence in a corpus n_a -- the number of activations used in our model n_values -- number of unique values in the music data Returns: model -- a keras model with the """ # Define the input of your model with a shape X = Input(shape=(Tx, n_values)) # Define s0, initial hidden state for the decoder LSTM a0 = Input(shape=(n_a,), name='a0') c0 = Input(shape=(n_a,), name='c0') a = a0 c = c0 ### START CODE HERE ### # Step 1: Create empty list to append the outputs while you iterate (≈1 line) outputs = [] # Step 2: Loop for t in range(Tx): # Step 2.A: select the "t"th time step vector from X. x = Lambda(lambda x: X[:,t,:])(X) # Step 2.B: Use reshapor to reshape x to be (1, n_values) (≈1 line) x = reshapor(x) # Step 2.C: Perform one step of the LSTM_cell a, _, c = LSTM_cell(x, initial_state=[a, c]) # Step 2.D: Apply densor to the hidden state output of LSTM_Cell out = densor(a) # Step 2.E: add the output to "outputs" outputs.append(out) # Step 3: Create model instance model = Model(inputs=[X,a0,c0],outputs=outputs) ### END CODE HERE ### return model
Run the following cell to define your model. We will use
Tx=30,
n_a=64(the dimension of the LSTM activations), and
n_values=78. This cell may take a few seconds to run.
model = djmodel(Tx = 30 , n_a = 64, n_values = 78)
You now need to compile your model to be trained. We will Adam and a categorical cross-entropy loss.
opt = Adam(lr=0.01, beta_1=0.9, beta_2=0.999, decay=0.01) model.compile(optimizer=opt, loss='categorical_crossentropy', metrics=['accuracy'])
Finally, lets initialize
a0and
c0for the LSTM’s initial state to be zero.
m = 60 a0 = np.zeros((m, n_a)) c0 = np.zeros((m, n_a))
Lets now fit the model! We will turn
Yto a list before doing so, since the cost function expects
Yto be provided in this format (one list item per time-step). So
list(Y)is a list with 30 items, where each of the list items is of shape (60,78). Lets train for 100 epochs. This will take a few minutes.
model.fit([X, a0, c0], list(Y), epochs=100)
Epoch 1/100 60/60 [==============================] - 9s - loss: 125.7792 - dense_2_loss_1: 4.3548 - dense_2_loss_2: 4.3475 - dense_2_loss_3: 4.3443 - dense_2_loss_4: 4.3460 - dense_2_loss_5: 4.3489 - dense_2_loss_6: 4.3364 - dense_2_loss_7: 4.3416 - dense_2_loss_8: 4.3402 - dense_2_loss_9: 4.3319 - dense_2_loss_10: 4.3354 - dense_2_loss_11: 4.3280 - dense_2_loss_12: 4.3408 - dense_2_loss_13: 4.3343 - dense_2_loss_14: 4.3360 - dense_2_loss_15: 4.3369 - dense_2_loss_16: 4.3339 - dense_2_loss_17: 4.3277 - dense_2_loss_18: 4.3391 - dense_2_loss_19: 4.3400 - dense_2_loss_20: 4.3307 - dense_2_loss_21: 4.3319 - dense_2_loss_22: 4.3402 - dense_2_loss_23: 4.3350 - dense_2_loss_24: 4.3276 - dense_2_loss_25: 4.3302 - dense_2_loss_26: 4.3372 - dense_2_loss_27: 4.3276 - dense_2_loss_28: 4.3383 - dense_2_loss_29: 4.3369 - dense_2_loss_30: 0.0000e+00 - dense_2_acc_1: 0.0000e+00 - dense_2_acc_2: 0.0333 - dense_2_acc_3: 0.0167 - dense_2_acc_4: 0.0167 - dense_2_acc_5: 0.0000e+00 - dense_2_acc_6: 0.0833 - dense_2_acc_7: 0.1000 - dense_2_acc_8: 0.1000 - dense_2_acc_9: 0.0667 - dense_2_acc_10: 0.0833 - dense_2_acc_11: 0.0500 - dense_2_acc_12: 0.0333 - dense_2_acc_13: 0.0667 - dense_2_acc_14: 0.1000 - dense_2_acc_15: 0.0000e+00 - dense_2_acc_16: 0.0333 - dense_2_acc_17: 0.0500 - dense_2_acc_18: 0.0000e+00 - dense_2_acc_19: 0.0500 - dense_2_acc_20: 0.0667 - dense_2_acc_21: 0.0500 - dense_2_acc_22: 0.0833 - dense_2_acc_23: 0.1000 - dense_2_acc_24: 0.1000 - dense_2_acc_25: 0.0667 - dense_2_acc_26: 0.0167 - dense_2_acc_27: 0.0833 - dense_2_acc_28: 0.0167 - dense_2_acc_29: 0.0500 - dense_2_acc_30: 0.0500 Epoch 2/100 60/60 [==============================] - 0s - loss: 121.9761 - dense_2_loss_1: 4.3351 - dense_2_loss_2: 4.3057 - dense_2_loss_3: 4.2844 - dense_2_loss_4: 4.2819 - dense_2_loss_5: 4.2615 - dense_2_loss_6: 4.2562 - dense_2_loss_7: 4.2480 - dense_2_loss_8: 4.2304 - dense_2_loss_9: 4.2327 - dense_2_loss_10: 4.2135 - dense_2_loss_11: 4.1874 - dense_2_loss_12: 4.2303 - dense_2_loss_13: 4.2027 - dense_2_loss_14: 4.1833 - dense_2_loss_15: 4.1759 - dense_2_loss_16: 4.1711 - dense_2_loss_17: 4.1588 - dense_2_loss_18: 4.1761 - dense_2_loss_19: 4.1671 - dense_2_loss_20: 4.1744 - dense_2_loss_21: 4.1716 - dense_2_loss_22: 4.1351 - dense_2_loss_23: 4.1786 - dense_2_loss_24: 4.1714 - dense_2_loss_25: 4.1975 - dense_2_loss_26: 4.1450 - dense_2_loss_27: 4.1421 - dense_2_loss_28: 4.1744 - dense_2_loss_29: 4.1839 - dense_2_loss_30: 0.0000e+00 - dense_2_acc_1: 0.0000e+00 - dense_2_acc_2: 0.0833 - dense_2_acc_3: 0.1667 - dense_2_acc_4: 0.1167 - dense_2_acc_5: 0.0667 - dense_2_acc_6: 0.0833 - dense_2_acc_7: 0.2000 - dense_2_acc_8: 0.1667 - dense_2_acc_9: 0.1500 - dense_2_acc_10: 0.1500 - dense_2_acc_11: 0.1667 - dense_2_acc_12: 0.1000 - dense_2_acc_13: 0.1167 - dense_2_acc_14: 0.1500 - dense_2_acc_15: 0.0833 - dense_2_acc_16: 0.1167 - dense_2_acc_17: 0.1500 - dense_2_acc_18: 0.1000 - dense_2_acc_19: 0.0500 - dense_2_acc_20: 0.0833 - dense_2_acc_21: 0.1167 - dense_2_acc_22: 0.0833 - dense_2_acc_23: 0.0833 - dense_2_acc_24: 0.1167 - dense_2_acc_25: 0.0500 - dense_2_acc_26: 0.0833 - dense_2_acc_27: 0.1000 - dense_2_acc_28: 0.0500 - dense_2_acc_29: 0.0333 - dense_2_acc_30: 0.0000e+00 Epoch 3/100 60/60 [==============================] - 0s - loss: 116.2892 - dense_2_loss_1: 4.3132 - dense_2_loss_2: 4.2546 - dense_2_loss_3: 4.2051 - dense_2_loss_4: 4.1843 - dense_2_loss_5: 4.1294 - dense_2_loss_6: 4.1303 - dense_2_loss_7: 4.0884 - dense_2_loss_8: 4.0161 - dense_2_loss_9: 3.9971 - dense_2_loss_10: 3.8736 - dense_2_loss_11: 3.8182 - dense_2_loss_12: 4.0622 - dense_2_loss_13: 3.9367 - dense_2_loss_14: 3.8504 - dense_2_loss_15: 3.9220 - dense_2_loss_16: 3.8923 - dense_2_loss_17: 3.8611 - dense_2_loss_18: 3.9659 - dense_2_loss_19: 3.8392 - dense_2_loss_20: 3.9865 - dense_2_loss_21: 4.0097 - dense_2_loss_22: 3.9552 - dense_2_loss_23: 4.0278 - dense_2_loss_24: 3.9465 - dense_2_loss_25: 4.0879 - dense_2_loss_26: 3.8277 - dense_2_loss_27: 3.9477 - dense_2_loss_28: 4.0622 - dense_2_loss_29: 4.0979 - dense_2_loss_30: 0.0000e+00 - dense_2_acc_1: 0.0667 - dense_2_acc_2: 0.1333 - dense_2_acc_3: 0.1500 - dense_2_acc_4: 0.1833 - dense_2_acc_5: 0.2167 - dense_2_acc_6: 0.0667 - dense_2_acc_7: 0.1500 - dense_2_acc_8: 0.1667 - dense_2_acc_9: 0.1333 - dense_2_acc_10: 0.0833 - dense_2_acc_11: 0.1167 - dense_2_acc_12: 0.0500 - dense_2_acc_13: 0.0833 - dense_2_acc_14: 0.1000 - dense_2_acc_15: 0.0667 - dense_2_acc_16: 0.0667 - dense_2_acc_17: 0.1167 - dense_2_acc_18: 0.0333 - dense_2_acc_19: 0.0500 - dense_2_acc_20: 0.1000 - dense_2_acc_21: 0.0667 - dense_2_acc_22: 0.0333 - dense_2_acc_23: 0.0167 - dense_2_acc_24: 0.0167 - dense_2_acc_25: 0.0833 - dense_2_acc_26: 0.1167 - dense_2_acc_27: 0.0667 - dense_2_acc_28: 0.0667 - dense_2_acc_29: 0.1167 - dense_2_acc_30: 0.0000e+00 Epoch 4/100 60/60 [==============================] - 0s - loss: 112.7256 - dense_2_loss_1: 4.2913 - dense_2_loss_2: 4.2062 - dense_2_loss_3: 4.1151 - dense_2_loss_4: 4.0847 - dense_2_loss_5: 3.9837 - dense_2_loss_6: 3.9846 - dense_2_loss_7: 3.9455 - dense_2_loss_8: 3.7549 - dense_2_loss_9: 3.8230 - dense_2_loss_10: 3.7020 - dense_2_loss_11: 3.7024 - dense_2_loss_12: 4.0321 - dense_2_loss_13: 3.8002 - dense_2_loss_14: 3.7469 - dense_2_loss_15: 3.8185 - dense_2_loss_16: 3.7950 - dense_2_loss_17: 3.8077 - dense_2_loss_18: 3.9049 - dense_2_loss_19: 3.7543 - dense_2_loss_20: 3.9428 - dense_2_loss_21: 3.9318 - dense_2_loss_22: 3.8437 - dense_2_loss_23: 3.8210 - dense_2_loss_24: 3.7525 - dense_2_loss_25: 3.9735 - dense_2_loss_26: 3.6095 - dense_2_loss_27: 3.7449 - dense_2_loss_28: 3.8639 - dense_2_loss_29: 3.9889 - dense_2_loss_30: 0.0000e+00 - dense_2_acc_1: 0.0667 - dense_2_acc_2: 0.1333 - dense_2_acc_3: 0.2000 - dense_2_acc_4: 0.2167 - dense_2_acc_5: 0.2833 - dense_2_acc_6: 0.1167 - dense_2_acc_7: 0.1167 - dense_2_acc_8: 0.1833 - dense_2_acc_9: 0.1333 - dense_2_acc_10: 0.1167 - dense_2_acc_11: 0.1167 - dense_2_acc_12: 0.0333 - dense_2_acc_13: 0.1167 - dense_2_acc_14: 0.1000 - dense_2_acc_15: 0.0833 - dense_2_acc_16: 0.0833 - dense_2_acc_17: 0.1167 - dense_2_acc_18: 0.0167 - dense_2_acc_19: 0.1000 - dense_2_acc_20: 0.0833 - dense_2_acc_21: 0.0833 - dense_2_acc_22: 0.0500 - dense_2_acc_23: 0.0833 - dense_2_acc_24: 0.0833 - dense_2_acc_25: 0.0167 - dense_2_acc_26: 0.1167 - dense_2_acc_27: 0.0500 - dense_2_acc_28: 0.0667 - dense_2_acc_29: 0.0333 - dense_2_acc_30: 0.0000e+00 Epoch 5/100 60/60 [==============================] - 0s - loss: 110.2826 - dense_2_loss_1: 4.2720 - dense_2_loss_2: 4.1601 - dense_2_loss_3: 4.0361 - dense_2_loss_4: 4.0073 - dense_2_loss_5: 3.8723 - dense_2_loss_6: 3.9082 - dense_2_loss_7: 3.8729 - dense_2_loss_8: 3.6282 - dense_2_loss_9: 3.7436 - dense_2_loss_10: 3.6412 - dense_2_loss_11: 3.6633 - dense_2_loss_12: 3.9788 - dense_2_loss_13: 3.6886 - dense_2_loss_14: 3.6392 - dense_2_loss_15: 3.7202 - dense_2_loss_16: 3.7415 - dense_2_loss_17: 3.8014 - dense_2_loss_18: 3.7987 - dense_2_loss_19: 3.6876 - dense_2_loss_20: 3.8570 - dense_2_loss_21: 3.8421 - dense_2_loss_22: 3.7734 - dense_2_loss_23: 3.6554 - dense_2_loss_24: 3.6554 - dense_2_loss_25: 3.8323 - dense_2_loss_26: 3.5735 - dense_2_loss_27: 3.6165 - dense_2_loss_28: 3.7142 - dense_2_loss_29: 3.9013 - dense_2_loss_30: 0.0000e+00 - dense_2_acc_1: 0.0667 - dense_2_acc_2: 0.1500 - dense_2_acc_3: 0.1833 - dense_2_acc_4: 0.2167 - dense_2_acc_5: 0.1667 - dense_2_acc_6: 0.0333 - dense_2_acc_7: 0.1000 - dense_2_acc_8: 0.1667 - dense_2_acc_9: 0.1000 - dense_2_acc_10: 0.1333 - dense_2_acc_11: 0.1500 - dense_2_acc_12: 0.0667 - dense_2_acc_13: 0.1333 - dense_2_acc_14: 0.1667 - dense_2_acc_15: 0.1167 - dense_2_acc_16: 0.0833 - dense_2_acc_17: 0.1000 - dense_2_acc_18: 0.1333 - dense_2_acc_19: 0.1500 - dense_2_acc_20: 0.0167 - dense_2_acc_21: 0.0500 - dense_2_acc_22: 0.1167 - dense_2_acc_23: 0.1000 - dense_2_acc_24: 0.0500 - dense_2_acc_25: 0.0500 - dense_2_acc_26: 0.0833 - dense_2_acc_27: 0.0833 - dense_2_acc_28: 0.0833 - dense_2_acc_29: 0.0167 - dense_2_acc_30: 0.0000e+00 Epoch 6/100 60/60 [==============================] - 0s - loss: 107.5390 - dense_2_loss_1: 4.2535 - dense_2_loss_2: 4.1196 - dense_2_loss_3: 3.9524 - dense_2_loss_4: 3.9281 - dense_2_loss_5: 3.7875 - dense_2_loss_6: 3.8378 - dense_2_loss_7: 3.8091 - dense_2_loss_8: 3.5173 - dense_2_loss_9: 3.6480 - dense_2_loss_10: 3.5392 - dense_2_loss_11: 3.5981 - dense_2_loss_12: 3.8611 - dense_2_loss_13: 3.5490 - dense_2_loss_14: 3.5406 - dense_2_loss_15: 3.5990 - dense_2_loss_16: 3.6150 - dense_2_loss_17: 3.6905 - dense_2_loss_18: 3.6707 - dense_2_loss_19: 3.5927 - dense_2_loss_20: 3.7148 - dense_2_loss_21: 3.7626 - dense_2_loss_22: 3.6596 - dense_2_loss_23: 3.5492 - dense_2_loss_24: 3.5669 - dense_2_loss_25: 3.7592 - dense_2_loss_26: 3.4604 - dense_2_loss_27: 3.5949 - dense_2_loss_28: 3.5830 - dense_2_loss_29: 3.7790 - dense_2_loss_30: 0.0000e+00 - dense_2_acc_1: 0.0667 - dense_2_acc_2: 0.1667 - dense_2_acc_3: 0.1833 - dense_2_acc_4: 0.2167 - dense_2_acc_5: 0.2667 - dense_2_acc_6: 0.0833 - dense_2_acc_7: 0.1000 - dense_2_acc_8: 0.2000 - dense_2_acc_9: 0.1333 - dense_2_acc_10: 0.1333 - dense_2_acc_11: 0.1500 - dense_2_acc_12: 0.1000 - dense_2_acc_13: 0.2167 - dense_2_acc_14: 0.2000 - dense_2_acc_15: 0.1667 - dense_2_acc_16: 0.1500 - dense_2_acc_17: 0.2167 - dense_2_acc_18: 0.1500 - dense_2_acc_19: 0.1333 - dense_2_acc_20: 0.1333 - dense_2_acc_21: 0.1333 - dense_2_acc_22: 0.1333 - dense_2_acc_23: 0.1167 - dense_2_acc_24: 0.1167 - dense_2_acc_25: 0.1000 - dense_2_acc_26: 0.1833 - dense_2_acc_27: 0.0667 - dense_2_acc_28: 0.1500 - dense_2_acc_29: 0.1333 - dense_2_acc_30: 0.0000e+00 Epoch 7/100 60/60 [==============================] - 0s - loss: 104.7688 - dense_2_loss_1: 4.2371 - dense_2_loss_2: 4.0772 - dense_2_loss_3: 3.8692 - dense_2_loss_4: 3.8502 - dense_2_loss_5: 3.6817 - dense_2_loss_6: 3.7520 - dense_2_loss_7: 3.7229 - dense_2_loss_8: 3.4010 - dense_2_loss_9: 3.5419 - dense_2_loss_10: 3.4189 - dense_2_loss_11: 3.5064 - dense_2_loss_12: 3.7660 - dense_2_loss_13: 3.4417 - dense_2_loss_14: 3.4312 - dense_2_loss_15: 3.5073 - dense_2_loss_16: 3.5092 - dense_2_loss_17: 3.5457 - dense_2_loss_18: 3.5527 - dense_2_loss_19: 3.4855 - dense_2_loss_20: 3.5847 - dense_2_loss_21: 3.7095 - dense_2_loss_22: 3.5714 - dense_2_loss_23: 3.4780 - dense_2_loss_24: 3.4768 - dense_2_loss_25: 3.6710 - dense_2_loss_26: 3.3121 - dense_2_loss_27: 3.4743 - dense_2_loss_28: 3.5398 - dense_2_loss_29: 3.6532 - dense_2_loss_30: 0.0000e+00 - dense_2_acc_1: 0.0667 - dense_2_acc_2: 0.1667 - dense_2_acc_3: 0.2167 - dense_2_acc_4: 0.1833 - dense_2_acc_5: 0.2833 - dense_2_acc_6: 0.1500 - dense_2_acc_7: 0.1000 - dense_2_acc_8: 0.2000 - dense_2_acc_9: 0.1333 - dense_2_acc_10: 0.1500 - dense_2_acc_11: 0.1500 - dense_2_acc_12: 0.0833 - dense_2_acc_13: 0.1500 - dense_2_acc_14: 0.1667 - dense_2_acc_15: 0.1500 - dense_2_acc_16: 0.1167 - dense_2_acc_17: 0.2000 - dense_2_acc_18: 0.1000 - dense_2_acc_19: 0.1500 - dense_2_acc_20: 0.1500 - dense_2_acc_21: 0.1000 - dense_2_acc_22: 0.1000 - dense_2_acc_23: 0.0667 - dense_2_acc_24: 0.0833 - dense_2_acc_25: 0.1333 - dense_2_acc_26: 0.2000 - dense_2_acc_27: 0.0667 - dense_2_acc_28: 0.1000 - dense_2_acc_29: 0.1333 - dense_2_acc_30: 0.0000e+00 Epoch 8/100 60/60 [==============================] - 0s - loss: 101.2518 - dense_2_loss_1: 4.2235 - dense_2_loss_2: 4.0337 - dense_2_loss_3: 3.7961 - dense_2_loss_4: 3.7751 - dense_2_loss_5: 3.5905 - dense_2_loss_6: 3.6569 - dense_2_loss_7: 3.5977 - dense_2_loss_8: 3.2810 - dense_2_loss_9: 3.3955 - dense_2_loss_10: 3.2214 - dense_2_loss_11: 3.3640 - dense_2_loss_12: 3.5695 - dense_2_loss_13: 3.2600 - dense_2_loss_14: 3.2535 - dense_2_loss_15: 3.3329 - dense_2_loss_16: 3.3941 - dense_2_loss_17: 3.3560 - dense_2_loss_18: 3.3962 - dense_2_loss_19: 3.2745 - dense_2_loss_20: 3.4063 - dense_2_loss_21: 3.5805 - dense_2_loss_22: 3.4329 - dense_2_loss_23: 3.3442 - dense_2_loss_24: 3.4470 - dense_2_loss_25: 3.5717 - dense_2_loss_26: 3.2627 - dense_2_loss_27: 3.4841 - dense_2_loss_28: 3.4040 - dense_2_loss_29: 3.5466 - dense_2_loss_30: 0.0000e+00 - dense_2_acc_1: 0.0667 - dense_2_acc_2: 0.1667 - dense_2_acc_3: 0.2167 - dense_2_acc_4: 0.1833 - dense_2_acc_5: 0.2500 - dense_2_acc_6: 0.1167 - dense_2_acc_7: 0.1000 - dense_2_acc_8: 0.2167 - dense_2_acc_9: 0.1667 - dense_2_acc_10: 0.1500 - dense_2_acc_11: 0.1500 - dense_2_acc_12: 0.0833 - dense_2_acc_13: 0.1500 - dense_2_acc_14: 0.2000 - dense_2_acc_15: 0.1667 - dense_2_acc_16: 0.1833 - dense_2_acc_17: 0.2333 - dense_2_acc_18: 0.1500 - dense_2_acc_19: 0.1667 - dense_2_acc_20: 0.1500 - dense_2_acc_21: 0.1333 - dense_2_acc_22: 0.1000 - dense_2_acc_23: 0.1667 - dense_2_acc_24: 0.1000 - dense_2_acc_25: 0.0667 - dense_2_acc_26: 0.2000 - dense_2_acc_27: 0.1167 - dense_2_acc_28: 0.2000 - dense_2_acc_29: 0.1167 - dense_2_acc_30: 0.0000e+00 Epoch 9/100 60/60 [==============================] - 0s - loss: 97.0864 - dense_2_loss_1: 4.2119 - dense_2_loss_2: 3.9925 - dense_2_loss_3: 3.7246 - dense_2_loss_4: 3.6920 - dense_2_loss_5: 3.4898 - dense_2_loss_6: 3.5503 - dense_2_loss_7: 3.4736 - dense_2_loss_8: 3.1662 - dense_2_loss_9: 3.2714 - dense_2_loss_10: 3.1088 - dense_2_loss_11: 3.2413 - dense_2_loss_12: 3.4017 - dense_2_loss_13: 3.1087 - dense_2_loss_14: 3.0971 - dense_2_loss_15: 3.1624 - dense_2_loss_16: 3.2210 - dense_2_loss_17: 3.2213 - dense_2_loss_18: 3.1996 - dense_2_loss_19: 3.1162 - dense_2_loss_20: 3.2784 - dense_2_loss_21: 3.4034 - dense_2_loss_22: 3.2158 - dense_2_loss_23: 3.2450 - dense_2_loss_24: 3.2186 - dense_2_loss_25: 3.3665 - dense_2_loss_26: 3.1103 - dense_2_loss_27: 3.2713 - dense_2_loss_28: 3.2000 - dense_2_loss_29: 3.3267 - dense_2_loss_30: 0.0000e+00 - dense_2_acc_1: 0.0667 - dense_2_acc_2: 0.1667 - dense_2_acc_3: 0.2000 - dense_2_acc_4: 0.1833 - dense_2_acc_5: 0.2667 - dense_2_acc_6: 0.1000 - dense_2_acc_7: 0.1500 - dense_2_acc_8: 0.2833 - dense_2_acc_9: 0.1667 - dense_2_acc_10: 0.1667 - dense_2_acc_11: 0.1833 - dense_2_acc_12: 0.1167 - dense_2_acc_13: 0.2833 - dense_2_acc_14: 0.3000 - dense_2_acc_15: 0.2000 - dense_2_acc_16: 0.1500 - dense_2_acc_17: 0.2500 - dense_2_acc_18: 0.1333 - dense_2_acc_19: 0.1667 - dense_2_acc_20: 0.1333 - dense_2_acc_21: 0.1000 - dense_2_acc_22: 0.1667 - dense_2_acc_23: 0.1167 - dense_2_acc_24: 0.1167 - dense_2_acc_25: 0.1000 - dense_2_acc_26: 0.2167 - dense_2_acc_27: 0.1500 - dense_2_acc_28: 0.2333 - dense_2_acc_29: 0.1167 - dense_2_acc_30: 0.0000e+00 Epoch 10/100 60/60 [==============================] - 0s - loss: 93.0385 - dense_2_loss_1: 4.2021 - dense_2_loss_2: 3.9495 - dense_2_loss_3: 3.6564 - dense_2_loss_4: 3.6109 - dense_2_loss_5: 3.3883 - dense_2_loss_6: 3.4423 - dense_2_loss_7: 3.3249 - dense_2_loss_8: 3.0344 - dense_2_loss_9: 3.1470 - dense_2_loss_10: 2.9995 - dense_2_loss_11: 3.1160 - dense_2_loss_12: 3.2157 - dense_2_loss_13: 2.9746 - dense_2_loss_14: 2.9573 - dense_2_loss_15: 3.0156 - dense_2_loss_16: 3.0931 - dense_2_loss_17: 3.0513 - dense_2_loss_18: 3.0207 - dense_2_loss_19: 2.9611 - dense_2_loss_20: 3.1338 - dense_2_loss_21: 3.1995 - dense_2_loss_22: 3.0237 - dense_2_loss_23: 3.1240 - dense_2_loss_24: 3.0850 - dense_2_loss_25: 3.1864 - dense_2_loss_26: 2.9007 - dense_2_loss_27: 3.0661 - dense_2_loss_28: 3.0191 - dense_2_loss_29: 3.1395 - dense_2_loss_30: 0.0000e+00 - dense_2_acc_1: 0.0667 - dense_2_acc_2: 0.1667 - dense_2_acc_3: 0.1833 - dense_2_acc_4: 0.1833 - dense_2_acc_5: 0.2667 - dense_2_acc_6: 0.1333 - dense_2_acc_7: 0.1667 - dense_2_acc_8: 0.2333 - dense_2_acc_9: 0.2000 - dense_2_acc_10: 0.1833 - dense_2_acc_11: 0.2000 - dense_2_acc_12: 0.1500 - dense_2_acc_13: 0.2500 - dense_2_acc_14: 0.3167 - dense_2_acc_15: 0.2000 - dense_2_acc_16: 0.1667 - dense_2_acc_17: 0.2500 - dense_2_acc_18: 0.1333 - dense_2_acc_19: 0.2000 - dense_2_acc_20: 0.1833 - dense_2_acc_21: 0.1833 - dense_2_acc_22: 0.1667 - dense_2_acc_23: 0.2667 - dense_2_acc_24: 0.2000 - dense_2_acc_25: 0.1333 - dense_2_acc_26: 0.2333 - dense_2_acc_27: 0.2167 - dense_2_acc_28: 0.2333 - dense_2_acc_29: 0.1333 - dense_2_acc_30: 0.0000e+00 Epoch 11/100 60/60 [==============================] - 0s - loss: 88.7889 - dense_2_loss_1: 4.1926 - dense_2_loss_2: 3.9057 - dense_2_loss_3: 3.5820 - dense_2_loss_4: 3.5174 - dense_2_loss_5: 3.2731 - dense_2_loss_6: 3.3021 - dense_2_loss_7: 3.1694 - dense_2_loss_8: 2.9084 - dense_2_loss_9: 3.0211 - dense_2_loss_10: 2.8260 - dense_2_loss_11: 2.9560 - dense_2_loss_12: 3.0153 - dense_2_loss_13: 2.7691 - dense_2_loss_14: 2.7892 - dense_2_loss_15: 2.8313 - dense_2_loss_16: 2.9217 - dense_2_loss_17: 2.8477 - dense_2_loss_18: 2.8419 - dense_2_loss_19: 2.8033 - dense_2_loss_20: 2.9163 - dense_2_loss_21: 2.9768 - dense_2_loss_22: 2.7760 - dense_2_loss_23: 2.9905 - dense_2_loss_24: 2.9831 - dense_2_loss_25: 3.0568 - dense_2_loss_26: 2.7734 - dense_2_loss_27: 2.9223 - dense_2_loss_28: 2.9149 - dense_2_loss_29: 3.0053 - dense_2_loss_30: 0.0000e+00 - dense_2_acc_1: 0.0667 - dense_2_acc_2: 0.1833 - dense_2_acc_3: 0.2000 - dense_2_acc_4: 0.1833 - dense_2_acc_5: 0.3167 - dense_2_acc_6: 0.1500 - dense_2_acc_7: 0.2333 - dense_2_acc_8: 0.1833 - dense_2_acc_9: 0.1667 - dense_2_acc_10: 0.2333 - dense_2_acc_11: 0.1667 - dense_2_acc_12: 0.1333 - dense_2_acc_13: 0.2667 - dense_2_acc_14: 0.3333 - dense_2_acc_15: 0.2000 - dense_2_acc_16: 0.1833 - dense_2_acc_17: 0.2167 - dense_2_acc_18: 0.1500 - dense_2_acc_19: 0.2000 - dense_2_acc_20: 0.1500 - dense_2_acc_21: 0.1667 - dense_2_acc_22: 0.2167 - dense_2_acc_23: 0.2000 - dense_2_acc_24: 0.1667 - dense_2_acc_25: 0.1000 - dense_2_acc_26: 0.2333 - dense_2_acc_27: 0.2167 - dense_2_acc_28: 0.1833 - dense_2_acc_29: 0.1500 - dense_2_acc_30: 0.0000e+00 Epoch 12/100 60/60 [==============================] - 0s - loss: 84.8223 - dense_2_loss_1: 4.1843 - dense_2_loss_2: 3.8594 - dense_2_loss_3: 3.5042 - dense_2_loss_4: 3.4183 - dense_2_loss_5: 3.1307 - dense_2_loss_6: 3.1267 - dense_2_loss_7: 3.0318 - dense_2_loss_8: 2.7495 - dense_2_loss_9: 2.8952 - dense_2_loss_10: 2.7065 - dense_2_loss_11: 2.8783 - dense_2_loss_12: 2.8363 - dense_2_loss_13: 2.5947 - dense_2_loss_14: 2.6618 - dense_2_loss_15: 2.7866 - dense_2_loss_16: 2.7477 - dense_2_loss_17: 2.6821 - dense_2_loss_18: 2.7164 - dense_2_loss_19: 2.7004 - dense_2_loss_20: 2.7126 - dense_2_loss_21: 2.7943 - dense_2_loss_22: 2.7397 - dense_2_loss_23: 2.7720 - dense_2_loss_24: 2.7477 - dense_2_loss_25: 2.9134 - dense_2_loss_26: 2.6101 - dense_2_loss_27: 2.7938 - dense_2_loss_28: 2.6949 - dense_2_loss_29: 2.8328 - dense_2_loss_30: 0.0000e+00 - dense_2_acc_1: 0.0667 - dense_2_acc_2: 0.1833 - dense_2_acc_3: 0.2167 - dense_2_acc_4: 0.1833 - dense_2_acc_5: 0.3167 - dense_2_acc_6: 0.1667 - dense_2_acc_7: 0.2000 - dense_2_acc_8: 0.2500 - dense_2_acc_9: 0.1500 - dense_2_acc_10: 0.2333 - dense_2_acc_11: 0.2000 - dense_2_acc_12: 0.1667 - dense_2_acc_13: 0.3333 - dense_2_acc_14: 0.3333 - dense_2_acc_15: 0.1833 - dense_2_acc_16: 0.1833 - dense_2_acc_17: 0.3167 - dense_2_acc_18: 0.2000 - dense_2_acc_19: 0.2167 - dense_2_acc_20: 0.2667 - dense_2_acc_21: 0.1667 - dense_2_acc_22: 0.1833 - dense_2_acc_23: 0.3000 - dense_2_acc_24: 0.2000 - dense_2_acc_25: 0.1500 - dense_2_acc_26: 0.3333 - dense_2_acc_27: 0.2333 - dense_2_acc_28: 0.3333 - dense_2_acc_29: 0.1500 - dense_2_acc_30: 0.0000e+00 Epoch 13/100 60/60 [==============================] - 0s - loss: 81.2648 - dense_2_loss_1: 4.1740 - dense_2_loss_2: 3.8155 - dense_2_loss_3: 3.4283 - dense_2_loss_4: 3.3116 - dense_2_loss_5: 2.9987 - dense_2_loss_6: 2.9750 - dense_2_loss_7: 2.9080 - dense_2_loss_8: 2.6323 - dense_2_loss_9: 2.7431 - dense_2_loss_10: 2.5689 - dense_2_loss_11: 2.6830 - dense_2_loss_12: 2.6844 - dense_2_loss_13: 2.5239 - dense_2_loss_14: 2.6228 - dense_2_loss_15: 2.6851 - dense_2_loss_16: 2.7069 - dense_2_loss_17: 2.5376 - dense_2_loss_18: 2.5787 - dense_2_loss_19: 2.5886 - dense_2_loss_20: 2.5689 - dense_2_loss_21: 2.6427 - dense_2_loss_22: 2.5381 - dense_2_loss_23: 2.6369 - dense_2_loss_24: 2.5563 - dense_2_loss_25: 2.7916 - dense_2_loss_26: 2.5273 - dense_2_loss_27: 2.6117 - dense_2_loss_28: 2.5700 - dense_2_loss_29: 2.6548 - dense_2_loss_30: 0.0000e+00 - dense_2_acc_1: 0.0667 - dense_2_acc_2: 0.1833 - dense_2_acc_3: 0.2167 - dense_2_acc_4: 0.2333 - dense_2_acc_5: 0.3167 - dense_2_acc_6: 0.2333 - dense_2_acc_7: 0.2333 - dense_2_acc_8: 0.2167 - dense_2_acc_9: 0.1667 - dense_2_acc_10: 0.2333 - dense_2_acc_11: 0.2000 - dense_2_acc_12: 0.2000 - dense_2_acc_13: 0.3000 - dense_2_acc_14: 0.2667 - dense_2_acc_15: 0.2000 - dense_2_acc_16: 0.2167 - dense_2_acc_17: 0.2667 - dense_2_acc_18: 0.1667 - dense_2_acc_19: 0.2167 - dense_2_acc_20: 0.2667 - dense_2_acc_21: 0.2167 - dense_2_acc_22: 0.2833 - dense_2_acc_23: 0.2500 - dense_2_acc_24: 0.2667 - dense_2_acc_25: 0.2000 - dense_2_acc_26: 0.2500 - dense_2_acc_27: 0.2833 - dense_2_acc_28: 0.3167 - dense_2_acc_29: 0.1667 - dense_2_acc_30: 0.0000e+00 Epoch 14/100 60/60 [==============================] - 0s - loss: 77.8998 - dense_2_loss_1: 4.1673 - dense_2_loss_2: 3.7752 - dense_2_loss_3: 3.3541 - dense_2_loss_4: 3.1938 - dense_2_loss_5: 2.8718 - dense_2_loss_6: 2.8345 - dense_2_loss_7: 2.7802 - dense_2_loss_8: 2.4742 - dense_2_loss_9: 2.6493 - dense_2_loss_10: 2.4751 - dense_2_loss_11: 2.5782 - dense_2_loss_12: 2.4911 - dense_2_loss_13: 2.2828 - dense_2_loss_14: 2.4225 - dense_2_loss_15: 2.5654 - dense_2_loss_16: 2.5029 - dense_2_loss_17: 2.4676 - dense_2_loss_18: 2.4687 - dense_2_loss_19: 2.4223 - dense_2_loss_20: 2.4669 - dense_2_loss_21: 2.4727 - dense_2_loss_22: 2.4781 - dense_2_loss_23: 2.6451 - dense_2_loss_24: 2.5759 - dense_2_loss_25: 2.6453 - dense_2_loss_26: 2.2628 - dense_2_loss_27: 2.5914 - dense_2_loss_28: 2.3811 - dense_2_loss_29: 2.6036 - dense_2_loss_30: 0.0000e+00 - dense_2_acc_1: 0.0667 - dense_2_acc_2: 0.2000 - dense_2_acc_3: 0.2167 - dense_2_acc_4: 0.2500 - dense_2_acc_5: 0.3333 - dense_2_acc_6: 0.2333 - dense_2_acc_7: 0.3000 - dense_2_acc_8: 0.3500 - dense_2_acc_9: 0.2833 - dense_2_acc_10: 0.4000 - dense_2_acc_11: 0.2333 - dense_2_acc_12: 0.2667 - dense_2_acc_13: 0.4167 - dense_2_acc_14: 0.3667 - dense_2_acc_15: 0.2667 - dense_2_acc_16: 0.3500 - dense_2_acc_17: 0.3000 - dense_2_acc_18: 0.2333 - dense_2_acc_19: 0.3500 - dense_2_acc_20: 0.4000 - dense_2_acc_21: 0.2500 - dense_2_acc_22: 0.2167 - dense_2_acc_23: 0.2500 - dense_2_acc_24: 0.2000 - dense_2_acc_25: 0.2000 - dense_2_acc_26: 0.4167 - dense_2_acc_27: 0.3000 - dense_2_acc_28: 0.3333 - dense_2_acc_29: 0.2000 - dense_2_acc_30: 0.0000e+00 Epoch 15/100 60/60 [==============================] - 0s - loss: 74.0802 - dense_2_loss_1: 4.1591 - dense_2_loss_2: 3.7329 - dense_2_loss_3: 3.2768 - dense_2_loss_4: 3.0877 - dense_2_loss_5: 2.7500 - dense_2_loss_6: 2.6844 - dense_2_loss_7: 2.6471 - dense_2_loss_8: 2.3814 - dense_2_loss_9: 2.5099 - dense_2_loss_10: 2.3372 - dense_2_loss_11: 2.4330 - dense_2_loss_12: 2.3274 - dense_2_loss_13: 2.1572 - dense_2_loss_14: 2.3292 - dense_2_loss_15: 2.4040 - dense_2_loss_16: 2.3267 - dense_2_loss_17: 2.2723 - dense_2_loss_18: 2.2979 - dense_2_loss_19: 2.3326 - dense_2_loss_20: 2.3118 - dense_2_loss_21: 2.3821 - dense_2_loss_22: 2.3523 - dense_2_loss_23: 2.4190 - dense_2_loss_24: 2.3942 - dense_2_loss_25: 2.5389 - dense_2_loss_26: 2.1275 - dense_2_loss_27: 2.4127 - dense_2_loss_28: 2.2690 - dense_2_loss_29: 2.4256 - dense_2_loss_30: 0.0000e+00 - dense_2_acc_1: 0.0667 - dense_2_acc_2: 0.2500 - dense_2_acc_3: 0.2167 - dense_2_acc_4: 0.2500 - dense_2_acc_5: 0.3167 - dense_2_acc_6: 0.3500 - dense_2_acc_7: 0.3500 - dense_2_acc_8: 0.3500 - dense_2_acc_9: 0.3167 - dense_2_acc_10: 0.4333 - dense_2_acc_11: 0.2500 - dense_2_acc_12: 0.2833 - dense_2_acc_13: 0.5167 - dense_2_acc_14: 0.3333 - dense_2_acc_15: 0.3500 - dense_2_acc_16: 0.3500 - dense_2_acc_17: 0.4333 - dense_2_acc_18: 0.3000 - dense_2_acc_19: 0.2500 - dense_2_acc_20: 0.4167 - dense_2_acc_21: 0.3333 - dense_2_acc_22: 0.1833 - dense_2_acc_23: 0.3000 - dense_2_acc_24: 0.2667 - dense_2_acc_25: 0.2667 - dense_2_acc_26: 0.4667 - dense_2_acc_27: 0.3167 - dense_2_acc_28: 0.3167 - dense_2_acc_29: 0.2833 - dense_2_acc_30: 0.0000e+00 Epoch 16/100 60/60 [==============================] - 0s - loss: 70.0849 - dense_2_loss_1: 4.1512 - dense_2_loss_2: 3.6938 - dense_2_loss_3: 3.1911 - dense_2_loss_4: 2.9830 - dense_2_loss_5: 2.6523 - dense_2_loss_6: 2.5543 - dense_2_loss_7: 2.5643 - dense_2_loss_8: 2.2405 - dense_2_loss_9: 2.3628 - dense_2_loss_10: 2.2100 - dense_2_loss_11: 2.2499 - dense_2_loss_12: 2.1909 - dense_2_loss_13: 2.0173 - dense_2_loss_14: 2.1850 - dense_2_loss_15: 2.2977 - dense_2_loss_16: 2.2450 - dense_2_loss_17: 2.1590 - dense_2_loss_18: 2.1723 - dense_2_loss_19: 2.1036 - dense_2_loss_20: 2.1056 - dense_2_loss_21: 2.1923 - dense_2_loss_22: 2.1585 - dense_2_loss_23: 2.2199 - dense_2_loss_24: 2.1946 - dense_2_loss_25: 2.3581 - dense_2_loss_26: 1.9951 - dense_2_loss_27: 2.2695 - dense_2_loss_28: 2.1423 - dense_2_loss_29: 2.2251 - dense_2_loss_30: 0.0000e+00 - dense_2_acc_1: 0.0667 - dense_2_acc_2: 0.2000 - dense_2_acc_3: 0.2333 - dense_2_acc_4: 0.2500 - dense_2_acc_5: 0.3167 - dense_2_acc_6: 0.3667 - dense_2_acc_7: 0.3500 - dense_2_acc_8: 0.4000 - dense_2_acc_9: 0.3500 - dense_2_acc_10: 0.3833 - dense_2_acc_11: 0.3333 - dense_2_acc_12: 0.3167 - dense_2_acc_13: 0.5167 - dense_2_acc_14: 0.4000 - dense_2_acc_15: 0.3333 - dense_2_acc_16: 0.3333 - dense_2_acc_17: 0.4333 - dense_2_acc_18: 0.3833 - dense_2_acc_19: 0.3333 - dense_2_acc_20: 0.5167 - dense_2_acc_21: 0.3333 - dense_2_acc_22: 0.2333 - dense_2_acc_23: 0.3667 - dense_2_acc_24: 0.2667 - dense_2_acc_25: 0.2500 - dense_2_acc_26: 0.4667 - dense_2_acc_27: 0.3500 - dense_2_acc_28: 0.3833 - dense_2_acc_29: 0.3167 - dense_2_acc_30: 0.0000e+00 Epoch 17/100 60/60 [==============================] - 0s - loss: 66.5506 - dense_2_loss_1: 4.1446 - dense_2_loss_2: 3.6488 - dense_2_loss_3: 3.1057 - dense_2_loss_4: 2.8825 - dense_2_loss_5: 2.5560 - dense_2_loss_6: 2.4104 - dense_2_loss_7: 2.4275 - dense_2_loss_8: 2.1187 - dense_2_loss_9: 2.1770 - dense_2_loss_10: 2.0883 - dense_2_loss_11: 2.0533 - dense_2_loss_12: 2.0708 - dense_2_loss_13: 1.8788 - dense_2_loss_14: 1.9316 - dense_2_loss_15: 2.1526 - dense_2_loss_16: 2.1100 - dense_2_loss_17: 2.0616 - dense_2_loss_18: 2.0400 - dense_2_loss_19: 1.9292 - dense_2_loss_20: 1.9791 - dense_2_loss_21: 2.0567 - dense_2_loss_22: 2.0098 - dense_2_loss_23: 2.1211 - dense_2_loss_24: 2.0941 - dense_2_loss_25: 2.2604 - dense_2_loss_26: 1.9556 - dense_2_loss_27: 2.1848 - dense_2_loss_28: 2.0462 - dense_2_loss_29: 2.0555 - dense_2_loss_30: 0.0000e+00 - dense_2_acc_1: 0.0667 - dense_2_acc_2: 0.2000 - dense_2_acc_3: 0.2500 - dense_2_acc_4: 0.2667 - dense_2_acc_5: 0.3333 - dense_2_acc_6: 0.3667 - dense_2_acc_7: 0.3167 - dense_2_acc_8: 0.4667 - dense_2_acc_9: 0.4000 - dense_2_acc_10: 0.3500 - dense_2_acc_11: 0.4500 - dense_2_acc_12: 0.4000 - dense_2_acc_13: 0.5000 - dense_2_acc_14: 0.4833 - dense_2_acc_15: 0.3500 - dense_2_acc_16: 0.3667 - dense_2_acc_17: 0.4167 - dense_2_acc_18: 0.4000 - dense_2_acc_19: 0.4000 - dense_2_acc_20: 0.5167 - dense_2_acc_21: 0.3667 - dense_2_acc_22: 0.4000 - dense_2_acc_23: 0.3500 - dense_2_acc_24: 0.2833 - dense_2_acc_25: 0.2833 - dense_2_acc_26: 0.4833 - dense_2_acc_27: 0.3667 - dense_2_acc_28: 0.3833 - dense_2_acc_29: 0.4667 - dense_2_acc_30: 0.0000e+00 Epoch 18/100 60/60 [==============================] - 0s - loss: 63.0833 - dense_2_loss_1: 4.1371 - dense_2_loss_2: 3.6017 - dense_2_loss_3: 3.0187 - dense_2_loss_4: 2.7758 - dense_2_loss_5: 2.4658 - dense_2_loss_6: 2.2867 - dense_2_loss_7: 2.3051 - dense_2_loss_8: 2.0152 - dense_2_loss_9: 2.0612 - dense_2_loss_10: 1.9617 - dense_2_loss_11: 1.9541 - dense_2_loss_12: 1.9504 - dense_2_loss_13: 1.7517 - dense_2_loss_14: 1.7914 - dense_2_loss_15: 2.0090 - dense_2_loss_16: 1.9740 - dense_2_loss_17: 1.9419 - dense_2_loss_18: 1.8954 - dense_2_loss_19: 1.8473 - dense_2_loss_20: 1.8524 - dense_2_loss_21: 1.9478 - dense_2_loss_22: 1.9185 - dense_2_loss_23: 1.9776 - dense_2_loss_24: 1.9430 - dense_2_loss_25: 2.0724 - dense_2_loss_26: 1.8161 - dense_2_loss_27: 2.0488 - dense_2_loss_28: 1.8395 - dense_2_loss_29: 1.9232 - dense_2_loss_30: 0.0000e+00 - dense_2_acc_1: 0.0667 - dense_2_acc_2: 0.2333 - dense_2_acc_3: 0.2833 - dense_2_acc_4: 0.2833 - dense_2_acc_5: 0.3500 - dense_2_acc_6: 0.3667 - dense_2_acc_7: 0.3333 - dense_2_acc_8: 0.4833 - dense_2_acc_9: 0.4167 - dense_2_acc_10: 0.4333 - dense_2_acc_11: 0.4667 - dense_2_acc_12: 0.4167 - dense_2_acc_13: 0.5667 - dense_2_acc_14: 0.5167 - dense_2_acc_15: 0.3333 - dense_2_acc_16: 0.4333 - dense_2_acc_17: 0.4500 - dense_2_acc_18: 0.4833 - dense_2_acc_19: 0.4333 - dense_2_acc_20: 0.5333 - dense_2_acc_21: 0.4000 - dense_2_acc_22: 0.4833 - dense_2_acc_23: 0.4333 - dense_2_acc_24: 0.3333 - dense_2_acc_25: 0.2333 - dense_2_acc_26: 0.5167 - dense_2_acc_27: 0.3667 - dense_2_acc_28: 0.4833 - dense_2_acc_29: 0.5167 - dense_2_acc_30: 0.0333 Epoch 19/100 60/60 [==============================] - 0s - loss: 59.9905 - dense_2_loss_1: 4.1278 - dense_2_loss_2: 3.5532 - dense_2_loss_3: 2.9339 - dense_2_loss_4: 2.6708 - dense_2_loss_5: 2.3652 - dense_2_loss_6: 2.1588 - dense_2_loss_7: 2.1990 - dense_2_loss_8: 1.9128 - dense_2_loss_9: 1.9652 - dense_2_loss_10: 1.8749 - dense_2_loss_11: 1.8706 - dense_2_loss_12: 1.8057 - dense_2_loss_13: 1.6318 - dense_2_loss_14: 1.7295 - dense_2_loss_15: 1.8752 - dense_2_loss_16: 1.8406 - dense_2_loss_17: 1.7982 - dense_2_loss_18: 1.7910 - dense_2_loss_19: 1.7355 - dense_2_loss_20: 1.7477 - dense_2_loss_21: 1.8643 - dense_2_loss_22: 1.8496 - dense_2_loss_23: 1.8411 - dense_2_loss_24: 1.7794 - dense_2_loss_25: 1.9067 - dense_2_loss_26: 1.7578 - dense_2_loss_27: 1.9041 - dense_2_loss_28: 1.6616 - dense_2_loss_29: 1.8384 - dense_2_loss_30: 0.0000e+00 - dense_2_acc_1: 0.0667 - dense_2_acc_2: 0.2500 - dense_2_acc_3: 0.2833 - dense_2_acc_4: 0.3333 - dense_2_acc_5: 0.3667 - dense_2_acc_6: 0.4000 - dense_2_acc_7: 0.3667 - dense_2_acc_8: 0.4833 - dense_2_acc_9: 0.4333 - dense_2_acc_10: 0.4167 - dense_2_acc_11: 0.4500 - dense_2_acc_12: 0.4833 - dense_2_acc_13: 0.6333 - dense_2_acc_14: 0.5333 - dense_2_acc_15: 0.4500 - dense_2_acc_16: 0.4667 - dense_2_acc_17: 0.5333 - dense_2_acc_18: 0.5167 - dense_2_acc_19: 0.5167 - dense_2_acc_20: 0.5833 - dense_2_acc_21: 0.4667 - dense_2_acc_22: 0.4667 - dense_2_acc_23: 0.5667 - dense_2_acc_24: 0.4667 - dense_2_acc_25: 0.3000 - dense_2_acc_26: 0.5167 - dense_2_acc_27: 0.4167 - dense_2_acc_28: 0.6000 - dense_2_acc_29: 0.5167 - dense_2_acc_30: 0.0500 Epoch 20/100 60/60 [==============================] - 0s - loss: 56.7536 - dense_2_loss_1: 4.1190 - dense_2_loss_2: 3.5018 - dense_2_loss_3: 2.8475 - dense_2_loss_4: 2.5621 - dense_2_loss_5: 2.2646 - dense_2_loss_6: 2.0256 - dense_2_loss_7: 2.0572 - dense_2_loss_8: 1.8440 - dense_2_loss_9: 1.8299 - dense_2_loss_10: 1.7352 - dense_2_loss_11: 1.7695 - dense_2_loss_12: 1.6708 - dense_2_loss_13: 1.5204 - dense_2_loss_14: 1.6543 - dense_2_loss_15: 1.7390 - dense_2_loss_16: 1.7418 - dense_2_loss_17: 1.6337 - dense_2_loss_18: 1.6282 - dense_2_loss_19: 1.6295 - dense_2_loss_20: 1.6277 - dense_2_loss_21: 1.7504 - dense_2_loss_22: 1.7202 - dense_2_loss_23: 1.6992 - dense_2_loss_24: 1.6591 - dense_2_loss_25: 1.7965 - dense_2_loss_26: 1.6507 - dense_2_loss_27: 1.7918 - dense_2_loss_28: 1.5809 - dense_2_loss_29: 1.7031 - dense_2_loss_30: 0.0000e+00 - dense_2_acc_1: 0.0667 - dense_2_acc_2: 0.2333 - dense_2_acc_3: 0.3500 - dense_2_acc_4: 0.3500 - dense_2_acc_5: 0.3833 - dense_2_acc_6: 0.4167 - dense_2_acc_7: 0.4000 - dense_2_acc_8: 0.4667 - dense_2_acc_9: 0.4833 - dense_2_acc_10: 0.4333 - dense_2_acc_11: 0.4167 - dense_2_acc_12: 0.5000 - dense_2_acc_13: 0.6167 - dense_2_acc_14: 0.5667 - dense_2_acc_15: 0.4667 - dense_2_acc_16: 0.4500 - dense_2_acc_17: 0.6333 - dense_2_acc_18: 0.5667 - dense_2_acc_19: 0.5333 - dense_2_acc_20: 0.6000 - dense_2_acc_21: 0.4833 - dense_2_acc_22: 0.5333 - dense_2_acc_23: 0.6667 - dense_2_acc_24: 0.5167 - dense_2_acc_25: 0.4833 - dense_2_acc_26: 0.5667 - dense_2_acc_27: 0.5000 - dense_2_acc_28: 0.6167 - dense_2_acc_29: 0.6000 - dense_2_acc_30: 0.0500 Epoch 21/100 60/60 [==============================] - 0s - loss: 53.8405 - dense_2_loss_1: 4.1100 - dense_2_loss_2: 3.4526 - dense_2_loss_3: 2.7586 - dense_2_loss_4: 2.4498 - dense_2_loss_5: 2.1544 - dense_2_loss_6: 1.8879 - dense_2_loss_7: 1.9200 - dense_2_loss_8: 1.7538 - dense_2_loss_9: 1.7105 - dense_2_loss_10: 1.6109 - dense_2_loss_11: 1.6710 - dense_2_loss_12: 1.5625 - dense_2_loss_13: 1.4064 - dense_2_loss_14: 1.5163 - dense_2_loss_15: 1.5916 - dense_2_loss_16: 1.6440 - dense_2_loss_17: 1.5539 - dense_2_loss_18: 1.5435 - dense_2_loss_19: 1.5390 - dense_2_loss_20: 1.5367 - dense_2_loss_21: 1.6314 - dense_2_loss_22: 1.6151 - dense_2_loss_23: 1.6268 - dense_2_loss_24: 1.5498 - dense_2_loss_25: 1.7234 - dense_2_loss_26: 1.5481 - dense_2_loss_27: 1.6757 - dense_2_loss_28: 1.4969 - dense_2_loss_29: 1.5998 - dense_2_loss_30: 0.0000e+00 - dense_2_acc_1: 0.0667 - dense_2_acc_2: 0.2667 - dense_2_acc_3: 0.4000 - dense_2_acc_4: 0.3333 - dense_2_acc_5: 0.3833 - dense_2_acc_6: 0.4333 - dense_2_acc_7: 0.3833 - dense_2_acc_8: 0.4833 - dense_2_acc_9: 0.5167 - dense_2_acc_10: 0.5000 - dense_2_acc_11: 0.4833 - dense_2_acc_12: 0.5167 - dense_2_acc_13: 0.7000 - dense_2_acc_14: 0.6333 - dense_2_acc_15: 0.5333 - dense_2_acc_16: 0.5500 - dense_2_acc_17: 0.6500 - dense_2_acc_18: 0.5833 - dense_2_acc_19: 0.6333 - dense_2_acc_20: 0.7000 - dense_2_acc_21: 0.5667 - dense_2_acc_22: 0.5833 - dense_2_acc_23: 0.6333 - dense_2_acc_24: 0.5833 - dense_2_acc_25: 0.5333 - dense_2_acc_26: 0.5833 - dense_2_acc_27: 0.5833 - dense_2_acc_28: 0.7500 - dense_2_acc_29: 0.6500 - dense_2_acc_30: 0.0167 Epoch 22/100 60/60 [==============================] - 0s - loss: 50.9009 - dense_2_loss_1: 4.1013 - dense_2_loss_2: 3.4012 - dense_2_loss_3: 2.6757 - dense_2_loss_4: 2.3339 - dense_2_loss_5: 2.0323 - dense_2_loss_6: 1.7570 - dense_2_loss_7: 1.8055 - dense_2_loss_8: 1.6532 - dense_2_loss_9: 1.5814 - dense_2_loss_10: 1.5141 - dense_2_loss_11: 1.5609 - dense_2_loss_12: 1.4198 - dense_2_loss_13: 1.2841 - dense_2_loss_14: 1.4008 - dense_2_loss_15: 1.5162 - dense_2_loss_16: 1.5208 - dense_2_loss_17: 1.4518 - dense_2_loss_18: 1.4362 - dense_2_loss_19: 1.4045 - dense_2_loss_20: 1.4384 - dense_2_loss_21: 1.5344 - dense_2_loss_22: 1.5278 - dense_2_loss_23: 1.5486 - dense_2_loss_24: 1.4551 - dense_2_loss_25: 1.5853 - dense_2_loss_26: 1.4550 - dense_2_loss_27: 1.6046 - dense_2_loss_28: 1.4184 - dense_2_loss_29: 1.4825 - dense_2_loss_30: 0.0000e+00 - dense_2_acc_1: 0.0667 - dense_2_acc_2: 0.2833 - dense_2_acc_3: 0.4000 - dense_2_acc_4: 0.3500 - dense_2_acc_5: 0.4333 - dense_2_acc_6: 0.4667 - dense_2_acc_7: 0.4500 - dense_2_acc_8: 0.4833 - dense_2_acc_9: 0.5833 - dense_2_acc_10: 0.5333 - dense_2_acc_11: 0.5667 - dense_2_acc_12: 0.6333 - dense_2_acc_13: 0.7333 - dense_2_acc_14: 0.6667 - dense_2_acc_15: 0.5000 - dense_2_acc_16: 0.6000 - dense_2_acc_17: 0.6500 - dense_2_acc_18: 0.6000 - dense_2_acc_19: 0.6667 - dense_2_acc_20: 0.7167 - dense_2_acc_21: 0.5667 - dense_2_acc_22: 0.5333 - dense_2_acc_23: 0.6333 - dense_2_acc_24: 0.6833 - dense_2_acc_25: 0.6000 - dense_2_acc_26: 0.7000 - dense_2_acc_27: 0.6000 - dense_2_acc_28: 0.7000 - dense_2_acc_29: 0.6667 - dense_2_acc_30: 0.0167 Epoch 23/100 60/60 [==============================] - 0s - loss: 48.1340 - dense_2_loss_1: 4.0922 - dense_2_loss_2: 3.3493 - dense_2_loss_3: 2.5876 - dense_2_loss_4: 2.2255 - dense_2_loss_5: 1.9222 - dense_2_loss_6: 1.6494 - dense_2_loss_7: 1.6742 - dense_2_loss_8: 1.5312 - dense_2_loss_9: 1.5053 - dense_2_loss_10: 1.4061 - dense_2_loss_11: 1.4517 - dense_2_loss_12: 1.3298 - dense_2_loss_13: 1.2185 - dense_2_loss_14: 1.3157 - dense_2_loss_15: 1.4104 - dense_2_loss_16: 1.3889 - dense_2_loss_17: 1.3679 - dense_2_loss_18: 1.3272 - dense_2_loss_19: 1.3266 - dense_2_loss_20: 1.3563 - dense_2_loss_21: 1.4671 - dense_2_loss_22: 1.4252 - dense_2_loss_23: 1.4254 - dense_2_loss_24: 1.3626 - dense_2_loss_25: 1.4939 - dense_2_loss_26: 1.3350 - dense_2_loss_27: 1.4899 - dense_2_loss_28: 1.3045 - dense_2_loss_29: 1.3944 - dense_2_loss_30: 0.0000e+00 - dense_2_acc_1: 0.0667 - dense_2_acc_2: 0.2833 - dense_2_acc_3: 0.4000 - dense_2_acc_4: 0.3833 - dense_2_acc_5: 0.4667 - dense_2_acc_6: 0.4833 - dense_2_acc_7: 0.5167 - dense_2_acc_8: 0.5500 - dense_2_acc_9: 0.6333 - dense_2_acc_10: 0.6167 - dense_2_acc_11: 0.6000 - dense_2_acc_12: 0.6667 - dense_2_acc_13: 0.7500 - dense_2_acc_14: 0.7167 - dense_2_acc_15: 0.5667 - dense_2_acc_16: 0.7000 - dense_2_acc_17: 0.7167 - dense_2_acc_18: 0.7000 - dense_2_acc_19: 0.7333 - dense_2_acc_20: 0.7500 - dense_2_acc_21: 0.6667 - dense_2_acc_22: 0.6667 - dense_2_acc_23: 0.6667 - dense_2_acc_24: 0.7000 - dense_2_acc_25: 0.6000 - dense_2_acc_26: 0.7167 - dense_2_acc_27: 0.6000 - dense_2_acc_28: 0.7500 - dense_2_acc_29: 0.7333 - dense_2_acc_30: 0.0500 Epoch 24/100 60/60 [==============================] - 0s - loss: 45.6231 - dense_2_loss_1: 4.0841 - dense_2_loss_2: 3.2969 - dense_2_loss_3: 2.4957 - dense_2_loss_4: 2.1340 - dense_2_loss_5: 1.8217 - dense_2_loss_6: 1.5500 - dense_2_loss_7: 1.5517 - dense_2_loss_8: 1.4395 - dense_2_loss_9: 1.4158 - dense_2_loss_10: 1.3194 - dense_2_loss_11: 1.3615 - dense_2_loss_12: 1.2634 - dense_2_loss_13: 1.1440 - dense_2_loss_14: 1.2233 - dense_2_loss_15: 1.3352 - dense_2_loss_16: 1.2891 - dense_2_loss_17: 1.2592 - dense_2_loss_18: 1.1959 - dense_2_loss_19: 1.2585 - dense_2_loss_20: 1.2466 - dense_2_loss_21: 1.3667 - dense_2_loss_22: 1.3307 - dense_2_loss_23: 1.3217 - dense_2_loss_24: 1.3249 - dense_2_loss_25: 1.4109 - dense_2_loss_26: 1.2392 - dense_2_loss_27: 1.3931 - dense_2_loss_28: 1.2170 - dense_2_loss_29: 1.3336 - dense_2_loss_30: 0.0000e+00 - dense_2_acc_1: 0.0667 - dense_2_acc_2: 0.2833 - dense_2_acc_3: 0.4000 - dense_2_acc_4: 0.3833 - dense_2_acc_5: 0.4667 - dense_2_acc_6: 0.5500 - dense_2_acc_7: 0.6167 - dense_2_acc_8: 0.6500 - dense_2_acc_9: 0.7167 - dense_2_acc_10: 0.6833 - dense_2_acc_11: 0.6333 - dense_2_acc_12: 0.7167 - dense_2_acc_13: 0.8000 - dense_2_acc_14: 0.7500 - dense_2_acc_15: 0.5500 - dense_2_acc_16: 0.7667 - dense_2_acc_17: 0.7333 - dense_2_acc_18: 0.8000 - dense_2_acc_19: 0.7333 - dense_2_acc_20: 0.7167 - dense_2_acc_21: 0.6667 - dense_2_acc_22: 0.6667 - dense_2_acc_23: 0.6833 - dense_2_acc_24: 0.6500 - dense_2_acc_25: 0.5833 - dense_2_acc_26: 0.7167 - dense_2_acc_27: 0.6167 - dense_2_acc_28: 0.7833 - dense_2_acc_29: 0.7333 - dense_2_acc_30: 0.0500 Epoch 25/100 60/60 [==============================] - 0s - loss: 43.2446 - dense_2_loss_1: 4.0757 - dense_2_loss_2: 3.2408 - dense_2_loss_3: 2.4051 - dense_2_loss_4: 2.0389 - dense_2_loss_5: 1.7156 - dense_2_loss_6: 1.4456 - dense_2_loss_7: 1.4309 - dense_2_loss_8: 1.3669 - dense_2_loss_9: 1.3151 - dense_2_loss_10: 1.2384 - dense_2_loss_11: 1.2650 - dense_2_loss_12: 1.2138 - dense_2_loss_13: 1.0597 - dense_2_loss_14: 1.1339 - dense_2_loss_15: 1.2574 - dense_2_loss_16: 1.2077 - dense_2_loss_17: 1.1778 - dense_2_loss_18: 1.1120 - dense_2_loss_19: 1.2103 - dense_2_loss_20: 1.1547 - dense_2_loss_21: 1.2762 - dense_2_loss_22: 1.2238 - dense_2_loss_23: 1.2297 - dense_2_loss_24: 1.2540 - dense_2_loss_25: 1.2808 - dense_2_loss_26: 1.1823 - dense_2_loss_27: 1.2905 - dense_2_loss_28: 1.1698 - dense_2_loss_29: 1.2720 - dense_2_loss_30: 0.0000e+00 - dense_2_acc_1: 0.0667 - dense_2_acc_2: 0.3000 - dense_2_acc_3: 0.4333 - dense_2_acc_4: 0.4000 - dense_2_acc_5: 0.4667 - dense_2_acc_6: 0.5667 - dense_2_acc_7: 0.7167 - dense_2_acc_8: 0.6667 - dense_2_acc_9: 0.7333 - dense_2_acc_10: 0.7000 - dense_2_acc_11: 0.6500 - dense_2_acc_12: 0.7333 - dense_2_acc_13: 0.8000 - dense_2_acc_14: 0.7667 - dense_2_acc_15: 0.6833 - dense_2_acc_16: 0.8167 - dense_2_acc_17: 0.8167 - dense_2_acc_18: 0.8833 - dense_2_acc_19: 0.7000 - dense_2_acc_20: 0.8500 - dense_2_acc_21: 0.7500 - dense_2_acc_22: 0.7167 - dense_2_acc_23: 0.7167 - dense_2_acc_24: 0.7167 - dense_2_acc_25: 0.6667 - dense_2_acc_26: 0.6833 - dense_2_acc_27: 0.6500 - dense_2_acc_28: 0.8333 - dense_2_acc_29: 0.7667 - dense_2_acc_30: 0.0333 Epoch 26/100 60/60 [==============================] - 0s - loss: 40.7680 - dense_2_loss_1: 4.0675 - dense_2_loss_2: 3.1856 - dense_2_loss_3: 2.3109 - dense_2_loss_4: 1.9401 - dense_2_loss_5: 1.6162 - dense_2_loss_6: 1.3281 - dense_2_loss_7: 1.3240 - dense_2_loss_8: 1.2932 - dense_2_loss_9: 1.1992 - dense_2_loss_10: 1.1090 - dense_2_loss_11: 1.1875 - dense_2_loss_12: 1.0811 - dense_2_loss_13: 0.9583 - dense_2_loss_14: 1.0629 - dense_2_loss_15: 1.1770 - dense_2_loss_16: 1.1217 - dense_2_loss_17: 1.0635 - dense_2_loss_18: 1.0572 - dense_2_loss_19: 1.0991 - dense_2_loss_20: 1.0996 - dense_2_loss_21: 1.1858 - dense_2_loss_22: 1.1559 - dense_2_loss_23: 1.1674 - dense_2_loss_24: 1.1485 - dense_2_loss_25: 1.2422 - dense_2_loss_26: 1.0686 - dense_2_loss_27: 1.2024 - dense_2_loss_28: 1.1319 - dense_2_loss_29: 1.1839 - dense_2_loss_30: 0.0000e+00 - dense_2_acc_1: 0.0667 - dense_2_acc_2: 0.3000 - dense_2_acc_3: 0.4333 - dense_2_acc_4: 0.4167 - dense_2_acc_5: 0.5167 - dense_2_acc_6: 0.7000 - dense_2_acc_7: 0.7167 - dense_2_acc_8: 0.6833 - dense_2_acc_9: 0.8000 - dense_2_acc_10: 0.8000 - dense_2_acc_11: 0.7000 - dense_2_acc_12: 0.8000 - dense_2_acc_13: 0.9000 - dense_2_acc_14: 0.7833 - dense_2_acc_15: 0.7000 - dense_2_acc_16: 0.8667 - dense_2_acc_17: 0.8667 - dense_2_acc_18: 0.8333 - dense_2_acc_19: 0.7833 - dense_2_acc_20: 0.9000 - dense_2_acc_21: 0.7833 - dense_2_acc_22: 0.7167 - dense_2_acc_23: 0.7333 - dense_2_acc_24: 0.7833 - dense_2_acc_25: 0.7500 - dense_2_acc_26: 0.8667 - dense_2_acc_27: 0.7500 - dense_2_acc_28: 0.8000 - dense_2_acc_29: 0.8000 - dense_2_acc_30: 0.0167 Epoch 27/100 60/60 [==============================] - 0s - loss: 38.4513 - dense_2_loss_1: 4.0587 - dense_2_loss_2: 3.1326 - dense_2_loss_3: 2.2285 - dense_2_loss_4: 1.8413 - dense_2_loss_5: 1.5275 - dense_2_loss_6: 1.2343 - dense_2_loss_7: 1.2407 - dense_2_loss_8: 1.2035 - dense_2_loss_9: 1.1151 - dense_2_loss_10: 1.0399 - dense_2_loss_11: 1.0831 - dense_2_loss_12: 0.9922 - dense_2_loss_13: 0.8951 - dense_2_loss_14: 0.9752 - dense_2_loss_15: 1.1226 - dense_2_loss_16: 1.0326 - dense_2_loss_17: 1.0168 - dense_2_loss_18: 0.9734 - dense_2_loss_19: 1.0082 - dense_2_loss_20: 1.0467 - dense_2_loss_21: 1.1056 - dense_2_loss_22: 1.0749 - dense_2_loss_23: 1.0931 - dense_2_loss_24: 1.0166 - dense_2_loss_25: 1.1399 - dense_2_loss_26: 1.0100 - dense_2_loss_27: 1.1099 - dense_2_loss_28: 1.0475 - dense_2_loss_29: 1.0858 - dense_2_loss_30: 0.0000e+00 - dense_2_acc_1: 0.0667 - dense_2_acc_2: 0.3333 - dense_2_acc_3: 0.4333 - dense_2_acc_4: 0.4167 - dense_2_acc_5: 0.6333 - dense_2_acc_6: 0.7333 - dense_2_acc_7: 0.8500 - dense_2_acc_8: 0.7333 - dense_2_acc_9: 0.8500 - dense_2_acc_10: 0.8167 - dense_2_acc_11: 0.7667 - dense_2_acc_12: 0.8000 - dense_2_acc_13: 0.9000 - dense_2_acc_14: 0.8167 - dense_2_acc_15: 0.7333 - dense_2_acc_16: 0.8833 - dense_2_acc_17: 0.8500 - dense_2_acc_18: 0.9000 - dense_2_acc_19: 0.7833 - dense_2_acc_20: 0.8667 - dense_2_acc_21: 0.8333 - dense_2_acc_22: 0.7833 - dense_2_acc_23: 0.7833 - dense_2_acc_24: 0.8000 - dense_2_acc_25: 0.7333 - dense_2_acc_26: 0.8333 - dense_2_acc_27: 0.8000 - dense_2_acc_28: 0.8667 - dense_2_acc_29: 0.8167 - dense_2_acc_30: 0.0167 Epoch 28/100 60/60 [==============================] - 0s - loss: 36.3655 - dense_2_loss_1: 4.0507 - dense_2_loss_2: 3.0763 - dense_2_loss_3: 2.1389 - dense_2_loss_4: 1.7585 - dense_2_loss_5: 1.4309 - dense_2_loss_6: 1.1496 - dense_2_loss_7: 1.1511 - dense_2_loss_8: 1.1266 - dense_2_loss_9: 1.0588 - dense_2_loss_10: 0.9485 - dense_2_loss_11: 0.9919 - dense_2_loss_12: 0.9114 - dense_2_loss_13: 0.8310 - dense_2_loss_14: 0.9111 - dense_2_loss_15: 1.0232 - dense_2_loss_16: 0.9519 - dense_2_loss_17: 0.9562 - dense_2_loss_18: 0.9032 - dense_2_loss_19: 0.9314 - dense_2_loss_20: 0.9787 - dense_2_loss_21: 1.0266 - dense_2_loss_22: 0.9850 - dense_2_loss_23: 1.0417 - dense_2_loss_24: 0.9526 - dense_2_loss_25: 1.0319 - dense_2_loss_26: 0.9666 - dense_2_loss_27: 1.0715 - dense_2_loss_28: 0.9867 - dense_2_loss_29: 1.0228 - dense_2_loss_30: 0.0000e+00 - dense_2_acc_1: 0.0667 - dense_2_acc_2: 0.3667 - dense_2_acc_3: 0.5000 - dense_2_acc_4: 0.4500 - dense_2_acc_5: 0.6500 - dense_2_acc_6: 0.7833 - dense_2_acc_7: 0.8667 - dense_2_acc_8: 0.7667 - dense_2_acc_9: 0.8500 - dense_2_acc_10: 0.8500 - dense_2_acc_11: 0.8167 - dense_2_acc_12: 0.8833 - dense_2_acc_13: 0.9000 - dense_2_acc_14: 0.8667 - dense_2_acc_15: 0.8000 - dense_2_acc_16: 0.8667 - dense_2_acc_17: 0.8833 - dense_2_acc_18: 0.9833 - dense_2_acc_19: 0.8500 - dense_2_acc_20: 0.8833 - dense_2_acc_21: 0.8500 - dense_2_acc_22: 0.8667 - dense_2_acc_23: 0.8167 - dense_2_acc_24: 0.8833 - dense_2_acc_25: 0.8500 - dense_2_acc_26: 0.9000 - dense_2_acc_27: 0.8333 - dense_2_acc_28: 0.8833 - dense_2_acc_29: 0.8667 - dense_2_acc_30: 0.0167 Epoch 29/100 60/60 [==============================] - 0s - loss: 34.2840 - dense_2_loss_1: 4.0428 - dense_2_loss_2: 3.0222 - dense_2_loss_3: 2.0537 - dense_2_loss_4: 1.6801 - dense_2_loss_5: 1.3487 - dense_2_loss_6: 1.0652 - dense_2_loss_7: 1.0660 - dense_2_loss_8: 1.0547 - dense_2_loss_9: 0.9792 - dense_2_loss_10: 0.8976 - dense_2_loss_11: 0.9078 - dense_2_loss_12: 0.8575 - dense_2_loss_13: 0.7759 - dense_2_loss_14: 0.8321 - dense_2_loss_15: 0.9376 - dense_2_loss_16: 0.9153 - dense_2_loss_17: 0.8626 - dense_2_loss_18: 0.8331 - dense_2_loss_19: 0.8735 - dense_2_loss_20: 0.8949 - dense_2_loss_21: 0.9702 - dense_2_loss_22: 0.9194 - dense_2_loss_23: 0.9325 - dense_2_loss_24: 0.8913 - dense_2_loss_25: 0.9735 - dense_2_loss_26: 0.8857 - dense_2_loss_27: 0.9443 - dense_2_loss_28: 0.9020 - dense_2_loss_29: 0.9644 - dense_2_loss_30: 0.0000e+00 - dense_2_acc_1: 0.0667 - dense_2_acc_2: 0.3667 - dense_2_acc_3: 0.5333 - dense_2_acc_4: 0.5000 - dense_2_acc_5: 0.6500 - dense_2_acc_6: 0.8000 - dense_2_acc_7: 0.8833 - dense_2_acc_8: 0.8167 - dense_2_acc_9: 0.8500 - dense_2_acc_10: 0.8833 - dense_2_acc_11: 0.8833 - dense_2_acc_12: 0.9000 - dense_2_acc_13: 0.9167 - dense_2_acc_14: 0.8667 - dense_2_acc_15: 0.8500 - dense_2_acc_16: 0.8667 - dense_2_acc_17: 0.8833 - dense_2_acc_18: 0.9833 - dense_2_acc_19: 0.8833 - dense_2_acc_20: 0.9167 - dense_2_acc_21: 0.8833 - dense_2_acc_22: 0.9000 - dense_2_acc_23: 0.8167 - dense_2_acc_24: 0.9167 - dense_2_acc_25: 0.8333 - dense_2_acc_26: 0.8500 - dense_2_acc_27: 0.8333 - dense_2_acc_28: 0.9000 - dense_2_acc_29: 0.8333 - dense_2_acc_30: 0.0167 Epoch 30/100 60/60 [==============================] - 0s - loss: 32.3661 - dense_2_loss_1: 4.0355 - dense_2_loss_2: 2.9649 - dense_2_loss_3: 1.9755 - dense_2_loss_4: 1.5950 - dense_2_loss_5: 1.2655 - dense_2_loss_6: 0.9899 - dense_2_loss_7: 0.9856 - dense_2_loss_8: 0.9636 - dense_2_loss_9: 0.9340 - dense_2_loss_10: 0.8205 - dense_2_loss_11: 0.8274 - dense_2_loss_12: 0.7700 - dense_2_loss_13: 0.7295 - dense_2_loss_14: 0.7489 - dense_2_loss_15: 0.8826 - dense_2_loss_16: 0.8401 - dense_2_loss_17: 0.8101 - dense_2_loss_18: 0.7712 - dense_2_loss_19: 0.7988 - dense_2_loss_20: 0.8293 - dense_2_loss_21: 0.8982 - dense_2_loss_22: 0.8445 - dense_2_loss_23: 0.9009 - dense_2_loss_24: 0.8198 - dense_2_loss_25: 0.8882 - dense_2_loss_26: 0.8173 - dense_2_loss_27: 0.8917 - dense_2_loss_28: 0.8470 - dense_2_loss_29: 0.9205 - dense_2_loss_30: 0.0000e+00 - dense_2_acc_1: 0.0667 - dense_2_acc_2: 0.3500 - dense_2_acc_3: 0.5500 - dense_2_acc_4: 0.5167 - dense_2_acc_5: 0.7167 - dense_2_acc_6: 0.8500 - dense_2_acc_7: 0.9000 - dense_2_acc_8: 0.8500 - dense_2_acc_9: 0.8333 - dense_2_acc_10: 0.9167 - dense_2_acc_11: 0.9000 - dense_2_acc_12: 0.9333 - dense_2_acc_13: 0.9667 - dense_2_acc_14: 0.9333 - dense_2_acc_15: 0.8833 - dense_2_acc_16: 0.8833 - dense_2_acc_17: 0.9500 - dense_2_acc_18: 0.9833 - dense_2_acc_19: 0.9167 - dense_2_acc_20: 0.9500 - dense_2_acc_21: 0.9167 - dense_2_acc_22: 0.9667 - dense_2_acc_23: 0.8833 - dense_2_acc_24: 0.9167 - dense_2_acc_25: 0.8333 - dense_2_acc_26: 0.9500 - dense_2_acc_27: 0.9167 - dense_2_acc_28: 0.9167 - dense_2_acc_29: 0.8833 - dense_2_acc_30: 0.0167 Epoch 31/100 60/60 [==============================] - 0s - loss: 30.4266 - dense_2_loss_1: 4.0275 - dense_2_loss_2: 2.9127 - dense_2_loss_3: 1.8947 - dense_2_loss_4: 1.5150 - dense_2_loss_5: 1.1939 - dense_2_loss_6: 0.9186 - dense_2_loss_7: 0.9208 - dense_2_loss_8: 0.8736 - dense_2_loss_9: 0.8676 - dense_2_loss_10: 0.7536 - dense_2_loss_11: 0.7631 - dense_2_loss_12: 0.7050 - dense_2_loss_13: 0.6575 - dense_2_loss_14: 0.6818 - dense_2_loss_15: 0.8089 - dense_2_loss_16: 0.7497 - dense_2_loss_17: 0.7549 - dense_2_loss_18: 0.7016 - dense_2_loss_19: 0.7393 - dense_2_loss_20: 0.7641 - dense_2_loss_21: 0.8282 - dense_2_loss_22: 0.7861 - dense_2_loss_23: 0.8237 - dense_2_loss_24: 0.7597 - dense_2_loss_25: 0.8330 - dense_2_loss_26: 0.7530 - dense_2_loss_27: 0.8177 - dense_2_loss_28: 0.7708 - dense_2_loss_29: 0.8506 - dense_2_loss_30: 0.0000e+00 - dense_2_acc_1: 0.0667 - dense_2_acc_2: 0.3667 - dense_2_acc_3: 0.5833 - dense_2_acc_4: 0.5167 - dense_2_acc_5: 0.7333 - dense_2_acc_6: 0.8833 - dense_2_acc_7: 0.9333 - dense_2_acc_8: 0.8667 - dense_2_acc_9: 0.8667 - dense_2_acc_10: 0.9500 - dense_2_acc_11: 0.9000 - dense_2_acc_12: 0.9500 - dense_2_acc_13: 0.9667 - dense_2_acc_14: 0.9167 - dense_2_acc_15: 0.8500 - dense_2_acc_16: 0.8833 - dense_2_acc_17: 0.9500 - dense_2_acc_18: 0.9833 - dense_2_acc_19: 0.9333 - dense_2_acc_20: 0.9500 - dense_2_acc_21: 0.9500 - dense_2_acc_22: 0.9500 - dense_2_acc_23: 0.8500 - dense_2_acc_24: 0.9333 - dense_2_acc_25: 0.8333 - dense_2_acc_26: 0.9500 - dense_2_acc_27: 0.9333 - dense_2_acc_28: 0.9167 - dense_2_acc_29: 0.9000 - dense_2_acc_30: 0.0167 Epoch 32/100 60/60 [==============================] - 0s - loss: 28.6700 - dense_2_loss_1: 4.0204 - dense_2_loss_2: 2.8582 - dense_2_loss_3: 1.8153 - dense_2_loss_4: 1.4356 - dense_2_loss_5: 1.1268 - dense_2_loss_6: 0.8553 - dense_2_loss_7: 0.8384 - dense_2_loss_8: 0.8095 - dense_2_loss_9: 0.7959 - dense_2_loss_10: 0.6902 - dense_2_loss_11: 0.6896 - dense_2_loss_12: 0.6385 - dense_2_loss_13: 0.6066 - dense_2_loss_14: 0.6327 - dense_2_loss_15: 0.7222 - dense_2_loss_16: 0.7019 - dense_2_loss_17: 0.6870 - dense_2_loss_18: 0.6423 - dense_2_loss_19: 0.6980 - dense_2_loss_20: 0.7064 - dense_2_loss_21: 0.7812 - dense_2_loss_22: 0.7330 - dense_2_loss_23: 0.7250 - dense_2_loss_24: 0.7125 - dense_2_loss_25: 0.7797 - dense_2_loss_26: 0.7046 - dense_2_loss_27: 0.7619 - dense_2_loss_28: 0.7142 - dense_2_loss_29: 0.7871 - dense_2_loss_30: 0.0000e+00 - dense_2_acc_1: 0.0667 - dense_2_acc_2: 0.3667 - dense_2_acc_3: 0.6000 - dense_2_acc_4: 0.5167 - dense_2_acc_5: 0.7500 - dense_2_acc_6: 0.9000 - dense_2_acc_7: 0.9333 - dense_2_acc_8: 0.9167 - dense_2_acc_9: 0.8667 - dense_2_acc_10: 0.9667 - dense_2_acc_11: 0.9167 - dense_2_acc_12: 0.9667 - dense_2_acc_13: 0.9667 - dense_2_acc_14: 0.9167 - dense_2_acc_15: 0.9000 - dense_2_acc_16: 0.9167 - dense_2_acc_17: 0.9167 - dense_2_acc_18: 1.0000 - dense_2_acc_19: 0.9500 - dense_2_acc_20: 0.9333 - dense_2_acc_21: 0.9000 - dense_2_acc_22: 0.9333 - dense_2_acc_23: 0.9000 - dense_2_acc_24: 0.9333 - dense_2_acc_25: 0.8500 - dense_2_acc_26: 0.9333 - dense_2_acc_27: 0.9333 - dense_2_acc_28: 0.9000 - dense_2_acc_29: 0.8833 - dense_2_acc_30: 0.0167 Epoch 33/100 60/60 [==============================] - 0s - loss: 27.0051 - dense_2_loss_1: 4.0144 - dense_2_loss_2: 2.8021 - dense_2_loss_3: 1.7370 - dense_2_loss_4: 1.3560 - dense_2_loss_5: 1.0575 - dense_2_loss_6: 0.7977 - dense_2_loss_7: 0.7689 - dense_2_loss_8: 0.7443 - dense_2_loss_9: 0.7415 - dense_2_loss_10: 0.6369 - dense_2_loss_11: 0.6320 - dense_2_loss_12: 0.5862 - dense_2_loss_13: 0.5670 - dense_2_loss_14: 0.5884 - dense_2_loss_15: 0.6510 - dense_2_loss_16: 0.6448 - dense_2_loss_17: 0.6364 - dense_2_loss_18: 0.5799 - dense_2_loss_19: 0.6469 - dense_2_loss_20: 0.6632 - dense_2_loss_21: 0.7056 - dense_2_loss_22: 0.6652 - dense_2_loss_23: 0.6786 - dense_2_loss_24: 0.6567 - dense_2_loss_25: 0.6949 - dense_2_loss_26: 0.6521 - dense_2_loss_27: 0.6985 - dense_2_loss_28: 0.6733 - dense_2_loss_29: 0.7281 - dense_2_loss_30: 0.0000e+00 - dense_2_acc_1: 0.0667 - dense_2_acc_2: 0.4167 - dense_2_acc_3: 0.6333 - dense_2_acc_4: 0.5833 - dense_2_acc_5: 0.7833 - dense_2_acc_6: 0.9333 - dense_2_acc_7: 0.9500 - dense_2_acc_8: 0.9167 - dense_2_acc_9: 0.9167 - dense_2_acc_10: 0.9667 - dense_2_acc_11: 0.9167 - dense_2_acc_12: 0.9667 - dense_2_acc_13: 1.0000 - dense_2_acc_14: 1.0000 - dense_2_acc_15: 1.0000 - dense_2_acc_16: 0.9333 - dense_2_acc_17: 0.9167 - dense_2_acc_18: 1.0000 - dense_2_acc_19: 0.9833 - dense_2_acc_20: 0.9500 - dense_2_acc_21: 0.9667 - dense_2_acc_22: 0.9667 - dense_2_acc_23: 0.9167 - dense_2_acc_24: 0.9500 - dense_2_acc_25: 0.9167 - dense_2_acc_26: 0.9667 - dense_2_acc_27: 0.9500 - dense_2_acc_28: 0.9500 - dense_2_acc_29: 0.9167 - dense_2_acc_30: 0.0167 Epoch 34/100 60/60 [==============================] - 0s - loss: 25.4145 - dense_2_loss_1: 4.0072 - dense_2_loss_2: 2.7503 - dense_2_loss_3: 1.6643 - dense_2_loss_4: 1.2887 - dense_2_loss_5: 0.9918 - dense_2_loss_6: 0.7401 - dense_2_loss_7: 0.7119 - dense_2_loss_8: 0.6619 - dense_2_loss_9: 0.6852 - dense_2_loss_10: 0.5787 - dense_2_loss_11: 0.5865 - dense_2_loss_12: 0.5297 - dense_2_loss_13: 0.5190 - dense_2_loss_14: 0.5491 - dense_2_loss_15: 0.5925 - dense_2_loss_16: 0.5842 - dense_2_loss_17: 0.5802 - dense_2_loss_18: 0.5469 - dense_2_loss_19: 0.5807 - dense_2_loss_20: 0.6088 - dense_2_loss_21: 0.6451 - dense_2_loss_22: 0.6145 - dense_2_loss_23: 0.6388 - dense_2_loss_24: 0.5978 - dense_2_loss_25: 0.6578 - dense_2_loss_26: 0.5801 - dense_2_loss_27: 0.6339 - dense_2_loss_28: 0.6251 - dense_2_loss_29: 0.6636 - dense_2_loss_30: 0.0000e+00 - dense_2_acc_1: 0.0500 - dense_2_acc_2: 0.4333 - dense_2_acc_3: 0.6333 - dense_2_acc_4: 0.6167 - dense_2_acc_5: 0.8333 - dense_2_acc_6: 0.9500 - dense_2_acc_7: 0.9667 - dense_2_acc_8: 0.9500 - dense_2_acc_9: 0.9333 - dense_2_acc_10: 0.9667 - dense_2_acc_11: 0.9667 - dense_2_acc_12: 0.9667 - dense_2_acc_13: 1.0000 - dense_2_acc_14: 1.0000 - dense_2_acc_15: 1.0000 - dense_2_acc_16: 0.9333 - dense_2_acc_17: 0.9500 - dense_2_acc_18: 1.0000 - dense_2_acc_19: 1.0000 - dense_2_acc_20: 1.0000 - dense_2_acc_21: 0.9833 - dense_2_acc_22: 0.9667 - dense_2_acc_23: 0.9500 - dense_2_acc_24: 0.9500 - dense_2_acc_25: 0.9333 - dense_2_acc_26: 0.9667 - dense_2_acc_27: 0.9500 - dense_2_acc_28: 0.9667 - dense_2_acc_29: 0.9333 - dense_2_acc_30: 0.0167 Epoch 35/100 60/60 [==============================] - 0s - loss: 23.9578 - dense_2_loss_1: 4.0007 - dense_2_loss_2: 2.6951 - dense_2_loss_3: 1.5927 - dense_2_loss_4: 1.2205 - dense_2_loss_5: 0.9314 - dense_2_loss_6: 0.6889 - dense_2_loss_7: 0.6607 - dense_2_loss_8: 0.6081 - dense_2_loss_9: 0.6288 - dense_2_loss_10: 0.5245 - dense_2_loss_11: 0.5391 - dense_2_loss_12: 0.4877 - dense_2_loss_13: 0.4620 - dense_2_loss_14: 0.4949 - dense_2_loss_15: 0.5437 - dense_2_loss_16: 0.5328 - dense_2_loss_17: 0.5365 - dense_2_loss_18: 0.4995 - dense_2_loss_19: 0.5350 - dense_2_loss_20: 0.5500 - dense_2_loss_21: 0.6088 - dense_2_loss_22: 0.5768 - dense_2_loss_23: 0.5661 - dense_2_loss_24: 0.5497 - dense_2_loss_25: 0.6291 - dense_2_loss_26: 0.5225 - dense_2_loss_27: 0.5896 - dense_2_loss_28: 0.5703 - dense_2_loss_29: 0.6123 - dense_2_loss_30: 0.0000e+00 - dense_2_acc_1: 0.0667 - dense_2_acc_2: 0.4333 - dense_2_acc_3: 0.6333 - dense_2_acc_4: 0.7000 - dense_2_acc_5: 0.8167 - dense_2_acc_6: 0.9667 - dense_2_acc_7: 0.9667 - dense_2_acc_8: 0.9833 - dense_2_acc_9: 0.9500 - dense_2_acc_10: 0.9833 - dense_2_acc_11: 0.9833 - dense_2_acc_12: 0.9667 - dense_2_acc_13: 1.0000 - dense_2_acc_14: 1.0000 - dense_2_acc_15: 1.0000 - dense_2_acc_16: 1.0000 - dense_2_acc_17: 1.0000 - dense_2_acc_18: 1.0000 - dense_2_acc_19: 1.0000 - dense_2_acc_20: 1.0000 - dense_2_acc_21: 0.9833 - dense_2_acc_22: 0.9833 - dense_2_acc_23: 0.9667 - dense_2_acc_24: 0.9667 - dense_2_acc_25: 0.9500 - dense_2_acc_26: 0.9833 - dense_2_acc_27: 0.9833 - dense_2_acc_28: 0.9500 - dense_2_acc_29: 0.9167 - dense_2_acc_30: 0.0167 Epoch 36/100 60/60 [==============================] - 0s - loss: 22.5458 - dense_2_loss_1: 3.9946 - dense_2_loss_2: 2.6435 - dense_2_loss_3: 1.5260 - dense_2_loss_4: 1.1472 - dense_2_loss_5: 0.8651 - dense_2_loss_6: 0.6384 - dense_2_loss_7: 0.6115 - dense_2_loss_8: 0.5545 - dense_2_loss_9: 0.5786 - dense_2_loss_10: 0.4949 - dense_2_loss_11: 0.4790 - dense_2_loss_12: 0.4561 - dense_2_loss_13: 0.4315 - dense_2_loss_14: 0.4483 - dense_2_loss_15: 0.4990 - dense_2_loss_16: 0.4833 - dense_2_loss_17: 0.4852 - dense_2_loss_18: 0.4477 - dense_2_loss_19: 0.4972 - dense_2_loss_20: 0.5022 - dense_2_loss_21: 0.5569 - dense_2_loss_22: 0.5156 - dense_2_loss_23: 0.5092 - dense_2_loss_24: 0.5156 - dense_2_loss_25: 0.5553 - dense_2_loss_26: 0.4857 - dense_2_loss_27: 0.5334 - dense_2_loss_28: 0.5186 - dense_2_loss_29: 0.5713 - dense_2_loss_30: 0.0000e+00 - dense_2_acc_1: 0.0667 - dense_2_acc_2: 0.4333 - dense_2_acc_3: 0.6500 - dense_2_acc_4: 0.7500 - dense_2_acc_5: 0.8667 - dense_2_acc_6: 0.9667 - dense_2_acc_7: 0.9667 - dense_2_acc_8: 0.9667 - dense_2_acc_9: 0.9667 - dense_2_acc_10: 0.9833 - dense_2_acc_11: 0.9833 - dense_2_acc_12: 0.9667 - dense_2_acc_13: 1.0000 - dense_2_acc_14: 1.0000 - dense_2_acc_15: 1.0000 - dense_2_acc_16: 1.0000 - dense_2_acc_17: 1.0000 - dense_2_acc_18: 1.0000 - dense_2_acc_19: 1.0000 - dense_2_acc_20: 1.0000 - dense_2_acc_21: 0.9833 - dense_2_acc_22: 1.0000 - dense_2_acc_23: 1.0000 - dense_2_acc_24: 0.9833 - dense_2_acc_25: 0.9667 - dense_2_acc_26: 0.9833 - dense_2_acc_27: 1.0000 - dense_2_acc_28: 0.9667 - dense_2_acc_29: 0.9500 - dense_2_acc_30: 0.0167 Epoch 37/100 60/60 [==============================] - 0s - loss: 21.2876 - dense_2_loss_1: 3.9881 - dense_2_loss_2: 2.5901 - dense_2_loss_3: 1.4638 - dense_2_loss_4: 1.0787 - dense_2_loss_5: 0.8052 - dense_2_loss_6: 0.5963 - dense_2_loss_7: 0.5646 - dense_2_loss_8: 0.5062 - dense_2_loss_9: 0.5319 - dense_2_loss_10: 0.4548 - dense_2_loss_11: 0.4490 - dense_2_loss_12: 0.4174 - dense_2_loss_13: 0.3934 - dense_2_loss_14: 0.4220 - dense_2_loss_15: 0.4507 - dense_2_loss_16: 0.4450 - dense_2_loss_17: 0.4325 - dense_2_loss_18: 0.4112 - dense_2_loss_19: 0.4552 - dense_2_loss_20: 0.4623 - dense_2_loss_21: 0.5062 - dense_2_loss_22: 0.4700 - dense_2_loss_23: 0.4666 - dense_2_loss_24: 0.4732 - dense_2_loss_25: 0.4949 - dense_2_loss_26: 0.4526 - dense_2_loss_27: 0.4916 - dense_2_loss_28: 0.4837 - dense_2_loss_29: 0.5306 - dense_2_loss_30: 0.0000e+00 - dense_2_acc_1: 0.0667 - dense_2_acc_2: 0.4333 - dense_2_acc_3: 0.7000 - dense_2_acc_4: 0.7500 - dense_2_acc_5: 0.8833 - dense_2_acc_6: 0.9667 - dense_2_acc_7: 0.9667 - dense_2_acc_8: 0.9667 - dense_2_acc_9: 0.9667 - dense_2_acc_10: 0.9833 - dense_2_acc_11: 0.9833 - dense_2_acc_12: 0.9667 - dense_2_acc_13: 1.0000 - dense_2_acc_14: 1.0000 - dense_2_acc_15: 1.0000 - dense_2_acc_16: 0.9667 - dense_2_acc_17: 1.0000 - dense_2_acc_18: 1.0000 - dense_2_acc_19: 1.0000 - dense_2_acc_20: 1.0000 - dense_2_acc_21: 1.0000 - dense_2_acc_22: 1.0000 - dense_2_acc_23: 1.0000 - dense_2_acc_24: 1.0000 - dense_2_acc_25: 0.9667 - dense_2_acc_26: 0.9833 - dense_2_acc_27: 1.0000 - dense_2_acc_28: 0.9833 - dense_2_acc_29: 0.9667 - dense_2_acc_30: 0.0167 Epoch 38/100 60/60 [==============================] - 0s - loss: 20.0649 - dense_2_loss_1: 3.9819 - dense_2_loss_2: 2.5390 - dense_2_loss_3: 1.4049 - dense_2_loss_4: 1.0137 - dense_2_loss_5: 0.7467 - dense_2_loss_6: 0.5408 - dense_2_loss_7: 0.5223 - dense_2_loss_8: 0.4610 - dense_2_loss_9: 0.4808 - dense_2_loss_10: 0.4113 - dense_2_loss_11: 0.4126 - dense_2_loss_12: 0.3746 - dense_2_loss_13: 0.3512 - dense_2_loss_14: 0.3886 - dense_2_loss_15: 0.4073 - dense_2_loss_16: 0.4094 - dense_2_loss_17: 0.3977 - dense_2_loss_18: 0.3794 - dense_2_loss_19: 0.4098 - dense_2_loss_20: 0.4215 - dense_2_loss_21: 0.4698 - dense_2_loss_22: 0.4384 - dense_2_loss_23: 0.4255 - dense_2_loss_24: 0.4261 - dense_2_loss_25: 0.4692 - dense_2_loss_26: 0.4112 - dense_2_loss_27: 0.4468 - dense_2_loss_28: 0.4376 - dense_2_loss_29: 0.4857 - dense_2_loss_30: 0.0000e+00 - dense_2_acc_1: 0.0667 - dense_2_acc_2: 0.4333 - dense_2_acc_3: 0.7000 - dense_2_acc_4: 0.7667 - dense_2_acc_5: 0.8833 - dense_2_acc_6: 0.9667 - dense_2_acc_7: 0.9667 - dense_2_acc_8: 0.9833 - dense_2_acc_9: 0.9667 - dense_2_acc_10: 0.9833 - dense_2_acc_11: 0.9833 - dense_2_acc_12: 0.9833 - dense_2_acc_13: 1.0000 - dense_2_acc_14: 1.0000 - dense_2_acc_15: 1.0000 - dense_2_acc_16: 1.0000 - dense_2_acc_17: 1.0000 - dense_2_acc_18: 1.0000 - dense_2_acc_19: 1.0000 - dense_2_acc_20: 1.0000 - dense_2_acc_21: 0.9833 - dense_2_acc_22: 1.0000 - dense_2_acc_23: 1.0000 - dense_2_acc_24: 0.9833 - dense_2_acc_25: 0.9500 - dense_2_acc_26: 0.9833 - dense_2_acc_27: 1.0000 - dense_2_acc_28: 1.0000 - dense_2_acc_29: 0.9667 - dense_2_acc_30: 0.0167 Epoch 39/100 60/60 [==============================] - 0s - loss: 18.9737 - dense_2_loss_1: 3.9761 - dense_2_loss_2: 2.4883 - dense_2_loss_3: 1.3484 - dense_2_loss_4: 0.9541 - dense_2_loss_5: 0.6972 - dense_2_loss_6: 0.4982 - dense_2_loss_7: 0.4909 - dense_2_loss_8: 0.4210 - dense_2_loss_9: 0.4434 - dense_2_loss_10: 0.3770 - dense_2_loss_11: 0.3742 - dense_2_loss_12: 0.3458 - dense_2_loss_13: 0.3180 - dense_2_loss_14: 0.3561 - dense_2_loss_15: 0.3776 - dense_2_loss_16: 0.3656 - dense_2_loss_17: 0.3669 - dense_2_loss_18: 0.3497 - dense_2_loss_19: 0.3672 - dense_2_loss_20: 0.3893 - dense_2_loss_21: 0.4303 - dense_2_loss_22: 0.3967 - dense_2_loss_23: 0.3949 - dense_2_loss_24: 0.3819 - dense_2_loss_25: 0.4262 - dense_2_loss_26: 0.3741 - dense_2_loss_27: 0.4072 - dense_2_loss_28: 0.4078 - dense_2_loss_29: 0.4497 - dense_2_loss_30: 0.0000e+00 - dense_2_acc_1: 0.0667 - dense_2_acc_2: 0.4333 - dense_2_acc_3: 0.7167 - dense_2_acc_4: 0.7833 - dense_2_acc_5: 0.8833 - dense_2_acc_6: 0.9833 - dense_2_acc_7: 0.9667 - dense_2_acc_8: 1.0000 - dense_2_acc_9: 0.9667 - dense_2_acc_10: 1.0000 - dense_2_acc_11: 0.9833 - dense_2_acc_12: 0.9833 - dense_2_acc_13: 1.0000 - dense_2_acc_14: 1.0000 - dense_2_acc_15: 1.0000 - dense_2_acc_16: 1.0000 - dense_2_acc_17: 1.0000 - dense_2_acc_18: 1.0000 - dense_2_acc_19: 1.0000 - dense_2_acc_20: 1.0000 - dense_2_acc_21: 1.0000 - dense_2_acc_22: 1.0000 - dense_2_acc_23: 1.0000 - dense_2_acc_24: 1.0000 - dense_2_acc_25: 0.9833 - dense_2_acc_26: 0.9833 - dense_2_acc_27: 1.0000 - dense_2_acc_28: 0.9833 - dense_2_acc_29: 0.9667 - dense_2_acc_30: 0.0167 Epoch 40/100 60/60 [==============================] - 0s - loss: 17.9449 - dense_2_loss_1: 3.9703 - dense_2_loss_2: 2.4387 - dense_2_loss_3: 1.2971 - dense_2_loss_4: 0.8943 - dense_2_loss_5: 0.6444 - dense_2_loss_6: 0.4620 - dense_2_loss_7: 0.4508 - dense_2_loss_8: 0.3814 - dense_2_loss_9: 0.4048 - dense_2_loss_10: 0.3405 - dense_2_loss_11: 0.3459 - dense_2_loss_12: 0.3181 - dense_2_loss_13: 0.2883 - dense_2_loss_14: 0.3278 - dense_2_loss_15: 0.3377 - dense_2_loss_16: 0.3366 - dense_2_loss_17: 0.3320 - dense_2_loss_18: 0.3094 - dense_2_loss_19: 0.3409 - dense_2_loss_20: 0.3661 - dense_2_loss_21: 0.3864 - dense_2_loss_22: 0.3675 - dense_2_loss_23: 0.3618 - dense_2_loss_24: 0.3536 - dense_2_loss_25: 0.3826 - dense_2_loss_26: 0.3441 - dense_2_loss_27: 0.3788 - dense_2_loss_28: 0.3754 - dense_2_loss_29: 0.4074 - dense_2_loss_30: 0.0000e+00 - dense_2_acc_1: 0.0667 - dense_2_acc_2: 0.4333 - dense_2_acc_3: 0.7167 - dense_2_acc_4: 0.7833 - dense_2_acc_5: 0.8833 - dense_2_acc_6: 0.9833 - dense_2_acc_7: 0.9833 - dense_2_acc_8: 1.0000 - dense_2_acc_9: 0.9667 - dense_2_acc_10: 0.9833 - dense_2_acc_11: 0.9833 - dense_2_acc_12: 0.9833 - dense_2_acc_13: 1.0000 - dense_2_acc_14: 1.0000 - dense_2_acc_15: 1.0000 - dense_2_acc_16: 1.0000 - dense_2_acc_17: 1.0000 - dense_2_acc_18: 1.0000 - dense_2_acc_19: 1.0000 - dense_2_acc_20: 1.0000 - dense_2_acc_21: 1.0000 - dense_2_acc_22: 1.0000 - dense_2_acc_23: 1.0000 - dense_2_acc_24: 1.0000 - dense_2_acc_25: 1.0000 - dense_2_acc_26: 0.9833 - dense_2_acc_27: 1.0000 - dense_2_acc_28: 0.9833 - dense_2_acc_29: 0.9667 - dense_2_acc_30: 0.0167 Epoch 41/100 60/60 [==============================] - 0s - loss: 17.0235 - dense_2_loss_1: 3.9648 - dense_2_loss_2: 2.3905 - dense_2_loss_3: 1.2447 - dense_2_loss_4: 0.8384 - dense_2_loss_5: 0.5989 - dense_2_loss_6: 0.4330 - dense_2_loss_7: 0.4153 - dense_2_loss_8: 0.3460 - dense_2_loss_9: 0.3736 - dense_2_loss_10: 0.3085 - dense_2_loss_11: 0.3212 - dense_2_loss_12: 0.2880 - dense_2_loss_13: 0.2674 - dense_2_loss_14: 0.2887 - dense_2_loss_15: 0.3112 - dense_2_loss_16: 0.3161 - dense_2_loss_17: 0.3043 - dense_2_loss_18: 0.2797 - dense_2_loss_19: 0.3151 - dense_2_loss_20: 0.3367 - dense_2_loss_21: 0.3574 - dense_2_loss_22: 0.3346 - dense_2_loss_23: 0.3303 - dense_2_loss_24: 0.3216 - dense_2_loss_25: 0.3617 - dense_2_loss_26: 0.3126 - dense_2_loss_27: 0.3481 - dense_2_loss_28: 0.3443 - dense_2_loss_29: 0.3708 - dense_2_loss_30: 0.0000e+00 - dense_2_acc_1: 0.0667 - dense_2_acc_2: 0.4667 - dense_2_acc_3: 0.7167 - dense_2_acc_4: 0.8000 - dense_2_acc_5: 0.9167 - dense_2_acc_6: 0.9833 - dense_2_acc_7: 0.9833 - dense_2_acc_8: 1.0000 - dense_2_acc_9: 0.9667 - dense_2_acc_10: 1.0000 - dense_2_acc_11: 0.9833 - dense_2_acc_12: 0.9833 - dense_2_acc_13: 1.0000 - dense_2_acc_14: 1.0000 - dense_2_acc_15: 1.0000 - dense_2_acc_16: 1.0000 - dense_2_acc_17: 1.0000 - dense_2_acc_18: 1.0000 - dense_2_acc_19: 1.0000 - dense_2_acc_20: 1.0000 - dense_2_acc_21: 1.0000 - dense_2_acc_22: 1.0000 - dense_2_acc_23: 1.0000 - dense_2_acc_24: 1.0000 - dense_2_acc_25: 0.9833 - dense_2_acc_26: 0.9833 - dense_2_acc_27: 1.0000 - dense_2_acc_28: 1.0000 - dense_2_acc_29: 0.9667 - dense_2_acc_30: 0.0167 Epoch 42/100 60/60 [==============================] - 0s - loss: 16.1500 - dense_2_loss_1: 3.9589 - dense_2_loss_2: 2.3461 - dense_2_loss_3: 1.1953 - dense_2_loss_4: 0.7867 - dense_2_loss_5: 0.5594 - dense_2_loss_6: 0.4052 - dense_2_loss_7: 0.3881 - dense_2_loss_8: 0.3133 - dense_2_loss_9: 0.3493 - dense_2_loss_10: 0.2794 - dense_2_loss_11: 0.2918 - dense_2_loss_12: 0.2602 - dense_2_loss_13: 0.2438 - dense_2_loss_14: 0.2636 - dense_2_loss_15: 0.2823 - dense_2_loss_16: 0.2840 - dense_2_loss_17: 0.2806 - dense_2_loss_18: 0.2613 - dense_2_loss_19: 0.2812 - dense_2_loss_20: 0.3046 - dense_2_loss_21: 0.3257 - dense_2_loss_22: 0.3073 - dense_2_loss_23: 0.2976 - dense_2_loss_24: 0.2944 - dense_2_loss_25: 0.3216 - dense_2_loss_26: 0.2865 - dense_2_loss_27: 0.3175 - dense_2_loss_28: 0.3199 - dense_2_loss_29: 0.3442 - dense_2_loss_30: 0.0000e+00 - dense_2_acc_1: 0.0667 - dense_2_acc_2: 0.4667 - dense_2_acc_3: 0.7167 - dense_2_acc_4: 0.8333 - dense_2_acc_5: 0.9167 - dense_2_acc_6: 0.9833 - dense_2_acc_7: 0.9833 - dense_2_acc_8: 1.0000 - dense_2_acc_9: 0.9833 - dense_2_acc_10: 1.0000 - dense_2_acc_11: 0.9833 - dense_2_acc_12: 1.0000 - dense_2_acc_13: 1.0000 - dense_2_acc_14: 1.0000 - dense_2_acc_15: 1.0000 - dense_2_acc_16: 1.0000 - dense_2_acc_17: 1.0000 - dense_2_acc_18: 1.0000 - dense_2_acc_19: 1.0000 - dense_2_acc_20: 1.0000 - dense_2_acc_21: 1.0000 - dense_2_acc_22: 1.0000 - dense_2_acc_23: 1.0000 - dense_2_acc_24: 1.0000 - dense_2_acc_25: 1.0000 - dense_2_acc_26: 0.9833 - dense_2_acc_27: 1.0000 - dense_2_acc_28: 0.9833 - dense_2_acc_29: 0.9667 - dense_2_acc_30: 0.0167 Epoch 43/100 60/60 [==============================] - 0s - loss: 15.3817 - dense_2_loss_1: 3.9543 - dense_2_loss_2: 2.2983 - dense_2_loss_3: 1.1498 - dense_2_loss_4: 0.7350 - dense_2_loss_5: 0.5220 - dense_2_loss_6: 0.3758 - dense_2_loss_7: 0.3602 - dense_2_loss_8: 0.2887 - dense_2_loss_9: 0.3184 - dense_2_loss_10: 0.2591 - dense_2_loss_11: 0.2707 - dense_2_loss_12: 0.2393 - dense_2_loss_13: 0.2217 - dense_2_loss_14: 0.2473 - dense_2_loss_15: 0.2584 - dense_2_loss_16: 0.2581 - dense_2_loss_17: 0.2587 - dense_2_loss_18: 0.2396 - dense_2_loss_19: 0.2584 - dense_2_loss_20: 0.2811 - dense_2_loss_21: 0.2965 - dense_2_loss_22: 0.2824 - dense_2_loss_23: 0.2736 - dense_2_loss_24: 0.2716 - dense_2_loss_25: 0.2881 - dense_2_loss_26: 0.2616 - dense_2_loss_27: 0.2949 - dense_2_loss_28: 0.2951 - dense_2_loss_29: 0.3230 - dense_2_loss_30: 0.0000e+00 - dense_2_acc_1: 0.0667 - dense_2_acc_2: 0.4667 - dense_2_acc_3: 0.7167 - dense_2_acc_4: 0.8500 - dense_2_acc_5: 0.9167 - dense_2_acc_6: 0.9833 - dense_2_acc_7: 0.9833 - dense_2_acc_8: 1.0000 - dense_2_acc_9: 0.9833 - dense_2_acc_10: 1.0000 - dense_2_acc_11: 0.9833 - dense_2_acc_12: 1.0000 - dense_2_acc_13: 1.0000 - dense_2_acc_14: 1.0000 - dense_2_acc_15: 1.0000 - dense_2_acc_16: 1.0000 - dense_2_acc_17: 1.0000 - dense_2_acc_18: 1.0000 - dense_2_acc_19: 1.0000 - dense_2_acc_20: 1.0000 - dense_2_acc_21: 1.0000 - dense_2_acc_22: 1.0000 - dense_2_acc_23: 1.0000 - dense_2_acc_24: 1.0000 - dense_2_acc_25: 1.0000 - dense_2_acc_26: 0.9833 - dense_2_acc_27: 1.0000 - dense_2_acc_28: 1.0000 - dense_2_acc_29: 0.9667 - dense_2_acc_30: 0.0167 Epoch 44/100 60/60 [==============================] - 0s - loss: 14.6801 - dense_2_loss_1: 3.9489 - dense_2_loss_2: 2.2543 - dense_2_loss_3: 1.1080 - dense_2_loss_4: 0.6878 - dense_2_loss_5: 0.4884 - dense_2_loss_6: 0.3476 - dense_2_loss_7: 0.3347 - dense_2_loss_8: 0.2672 - dense_2_loss_9: 0.2851 - dense_2_loss_10: 0.2429 - dense_2_loss_11: 0.2497 - dense_2_loss_12: 0.2193 - dense_2_loss_13: 0.2005 - dense_2_loss_14: 0.2312 - dense_2_loss_15: 0.2413 - dense_2_loss_16: 0.2361 - dense_2_loss_17: 0.2369 - dense_2_loss_18: 0.2148 - dense_2_loss_19: 0.2404 - dense_2_loss_20: 0.2606 - dense_2_loss_21: 0.2674 - dense_2_loss_22: 0.2650 - dense_2_loss_23: 0.2529 - dense_2_loss_24: 0.2478 - dense_2_loss_25: 0.2653 - dense_2_loss_26: 0.2403 - dense_2_loss_27: 0.2762 - dense_2_loss_28: 0.2705 - dense_2_loss_29: 0.2991 - dense_2_loss_30: 0.0000e+00 - dense_2_acc_1: 0.0667 - dense_2_acc_2: 0.4833 - dense_2_acc_3: 0.7333 - dense_2_acc_4: 0.8833 - dense_2_acc_5: 0.9333 - dense_2_acc_6: 0.9833 - dense_2_acc_7: 0.9833 - dense_2_acc_8: 1.0000 - dense_2_acc_9: 0.9833 - dense_2_acc_10: 1.0000 - dense_2_acc_11: 0.9833 - dense_2_acc_12: 1.0000 - dense_2_acc_13: 1.0000 - dense_2_acc_14: 1.0000 - dense_2_acc_15: 1.0000 - dense_2_acc_16: 1.0000 - dense_2_acc_17: 1.0000 - dense_2_acc_18: 1.0000 - dense_2_acc_19: 1.0000 - dense_2_acc_20: 1.0000 - dense_2_acc_21: 1.0000 - dense_2_acc_22: 1.0000 - dense_2_acc_23: 1.0000 - dense_2_acc_24: 1.0000 - dense_2_acc_25: 1.0000 - dense_2_acc_26: 0.9833 - dense_2_acc_27: 1.0000 - dense_2_acc_28: 1.0000 - dense_2_acc_29: 0.9667 - dense_2_acc_30: 0.0167 Epoch 45/100 60/60 [==============================] - 0s - loss: 14.0022 - dense_2_loss_1: 3.9447 - dense_2_loss_2: 2.2113 - dense_2_loss_3: 1.0667 - dense_2_loss_4: 0.6471 - dense_2_loss_5: 0.4551 - dense_2_loss_6: 0.3232 - dense_2_loss_7: 0.3074 - dense_2_loss_8: 0.2424 - dense_2_loss_9: 0.2640 - dense_2_loss_10: 0.2207 - dense_2_loss_11: 0.2267 - dense_2_loss_12: 0.2005 - dense_2_loss_13: 0.1853 - dense_2_loss_14: 0.2092 - dense_2_loss_15: 0.2234 - dense_2_loss_16: 0.2167 - dense_2_loss_17: 0.2191 - dense_2_loss_18: 0.1978 - dense_2_loss_19: 0.2211 - dense_2_loss_20: 0.2369 - dense_2_loss_21: 0.2462 - dense_2_loss_22: 0.2406 - dense_2_loss_23: 0.2320 - dense_2_loss_24: 0.2293 - dense_2_loss_25: 0.2466 - dense_2_loss_26: 0.2158 - dense_2_loss_27: 0.2489 - dense_2_loss_28: 0.2454 - dense_2_loss_29: 0.2782 - dense_2_loss_30: 0.0000e+00 - dense_2_acc_1: 0.0667 - dense_2_acc_2: 0.4833 - dense_2_acc_3: 0.7667 - dense_2_acc_4: 0.9000 - dense_2_acc_5: 0.9333 - dense_2_acc_6: 0.9833 - dense_2_acc_7: 0.9833 - dense_2_acc_8: 1.0000 - dense_2_acc_9: 0.9833 - dense_2_acc_10: 1.0000 - dense_2_acc_11: 1.0000 - dense_2_acc_12: 1.0000 - dense_2_acc_13: 1.0000 - dense_2_acc_14: 1.0000 - dense_2_acc_15: 1.0000 - dense_2_acc_16: 1.0000 - dense_2_acc_17: 1.0000 - dense_2_acc_18: 1.0000 - dense_2_acc_19: 1.0000 - dense_2_acc_20: 1.0000 - dense_2_acc_21: 1.0000 - dense_2_acc_22: 1.0000 - dense_2_acc_23: 1.0000 - dense_2_acc_24: 1.0000 - dense_2_acc_25: 1.0000 - dense_2_acc_26: 0.9833 - dense_2_acc_27: 1.0000 - dense_2_acc_28: 1.0000 - dense_2_acc_29: 0.9667 - dense_2_acc_30: 0.0167 Epoch 46/100 60/60 [==============================] - 0s - loss: 13.4180 - dense_2_loss_1: 3.9389 - dense_2_loss_2: 2.1693 - dense_2_loss_3: 1.0310 - dense_2_loss_4: 0.6089 - dense_2_loss_5: 0.4247 - dense_2_loss_6: 0.3047 - dense_2_loss_7: 0.2867 - dense_2_loss_8: 0.2199 - dense_2_loss_9: 0.2498 - dense_2_loss_10: 0.2008 - dense_2_loss_11: 0.2115 - dense_2_loss_12: 0.1858 - dense_2_loss_13: 0.1710 - dense_2_loss_14: 0.1949 - dense_2_loss_15: 0.1986 - dense_2_loss_16: 0.2007 - dense_2_loss_17: 0.2009 - dense_2_loss_18: 0.1891 - dense_2_loss_19: 0.2027 - dense_2_loss_20: 0.2127 - dense_2_loss_21: 0.2288 - dense_2_loss_22: 0.2199 - dense_2_loss_23: 0.2142 - dense_2_loss_24: 0.2100 - dense_2_loss_25: 0.2240 - dense_2_loss_26: 0.1976 - dense_2_loss_27: 0.2329 - dense_2_loss_28: 0.2308 - dense_2_loss_29: 0.2571 - dense_2_loss_30: 0.0000e+00 - dense_2_acc_1: 0.0667 - dense_2_acc_2: 0.4833 - dense_2_acc_3: 0.7833 - dense_2_acc_4: 0.9000 - dense_2_acc_5: 0.9333 - dense_2_acc_6: 0.9833 - dense_2_acc_7: 0.9833 - dense_2_acc_8: 1.0000 - dense_2_acc_9: 0.9833 - dense_2_acc_10: 1.0000 - dense_2_acc_11: 1.0000 - dense_2_acc_12: 1.0000 - dense_2_acc_13: 1.0000 - dense_2_acc_14: 1.0000 - dense_2_acc_15: 1.0000 - dense_2_acc_16: 1.0000 - dense_2_acc_17: 1.0000 - dense_2_acc_18: 1.0000 - dense_2_acc_19: 1.0000 - dense_2_acc_20: 1.0000 - dense_2_acc_21: 1.0000 - dense_2_acc_22: 1.0000 - dense_2_acc_23: 1.0000 - dense_2_acc_24: 1.0000 - dense_2_acc_25: 1.0000 - dense_2_acc_26: 0.9833 - dense_2_acc_27: 1.0000 - dense_2_acc_28: 1.0000 - dense_2_acc_29: 0.9667 - dense_2_acc_30: 0.0167 Epoch 47/100 60/60 [==============================] - 0s - loss: 12.8731 - dense_2_loss_1: 3.9342 - dense_2_loss_2: 2.1287 - dense_2_loss_3: 0.9956 - dense_2_loss_4: 0.5721 - dense_2_loss_5: 0.3951 - dense_2_loss_6: 0.2846 - dense_2_loss_7: 0.2649 - dense_2_loss_8: 0.2035 - dense_2_loss_9: 0.2272 - dense_2_loss_10: 0.1869 - dense_2_loss_11: 0.1947 - dense_2_loss_12: 0.1698 - dense_2_loss_13: 0.1599 - dense_2_loss_14: 0.1756 - dense_2_loss_15: 0.1862 - dense_2_loss_16: 0.1875 - dense_2_loss_17: 0.1837 - dense_2_loss_18: 0.1728 - dense_2_loss_19: 0.1861 - dense_2_loss_20: 0.1983 - dense_2_loss_21: 0.2113 - dense_2_loss_22: 0.2050 - dense_2_loss_23: 0.1948 - dense_2_loss_24: 0.1951 - dense_2_loss_25: 0.2040 - dense_2_loss_26: 0.1847 - dense_2_loss_27: 0.2165 - dense_2_loss_28: 0.2186 - dense_2_loss_29: 0.2357 - dense_2_loss_30: 0.0000e+00 - dense_2_acc_1: 0.0667 - dense_2_acc_2: 0.4833 - dense_2_acc_3: 0.7833 - dense_2_acc_4: 0.9000 - dense_2_acc_5: 0.9667 - dense_2_acc_6: 0.9833 - dense_2_acc_7: 0.9833 - dense_2_acc_8: 1.0000 - dense_2_acc_9: 0.9833 - dense_2_acc_10: 1.0000 - dense_2_acc_11: 1.0000 - dense_2_acc_12: 1.0000 - dense_2_acc_13: 1.0000 - dense_2_acc_14: 1.0000 - dense_2_acc_15: 1.0000 - dense_2_acc_16: 1.0000 - dense_2_acc_17: 1.0000 - dense_2_acc_18: 1.0000 - dense_2_acc_19: 1.0000 - dense_2_acc_20: 1.0000 - dense_2_acc_21: 1.0000 - dense_2_acc_22: 1.0000 - dense_2_acc_23: 1.0000 - dense_2_acc_24: 1.0000 - dense_2_acc_25: 1.0000 - dense_2_acc_26: 0.9833 - dense_2_acc_27: 1.0000 - dense_2_acc_28: 1.0000 - dense_2_acc_29: 0.9833 - dense_2_acc_30: 0.0167 Epoch 48/100 60/60 [==============================] - 0s - loss: 12.3624 - dense_2_loss_1: 3.9295 - dense_2_loss_2: 2.0882 - dense_2_loss_3: 0.9631 - dense_2_loss_4: 0.5370 - dense_2_loss_5: 0.3710 - dense_2_loss_6: 0.2668 - dense_2_loss_7: 0.2436 - dense_2_loss_8: 0.1886 - dense_2_loss_9: 0.2080 - dense_2_loss_10: 0.1730 - dense_2_loss_11: 0.1791 - dense_2_loss_12: 0.1574 - dense_2_loss_13: 0.1470 - dense_2_loss_14: 0.1618 - dense_2_loss_15: 0.1723 - dense_2_loss_16: 0.1735 - dense_2_loss_17: 0.1679 - dense_2_loss_18: 0.1559 - dense_2_loss_19: 0.1690 - dense_2_loss_20: 0.1891 - dense_2_loss_21: 0.1937 - dense_2_loss_22: 0.1861 - dense_2_loss_23: 0.1769 - dense_2_loss_24: 0.1773 - dense_2_loss_25: 0.1939 - dense_2_loss_26: 0.1712 - dense_2_loss_27: 0.1971 - dense_2_loss_28: 0.2033 - dense_2_loss_29: 0.2213 - dense_2_loss_30: 0.0000e+00 - dense_2_acc_1: 0.0667 - dense_2_acc_2: 0.5333 - dense_2_acc_3: 0.7833 - dense_2_acc_4: 0.9167 - dense_2_acc_5: 0.9667 - dense_2_acc_6: 0.9833 - dense_2_acc_7: 0.9833 - dense_2_acc_8: 1.0000 - dense_2_acc_9: 1.0000 - dense_2_acc_10: 1.0000 - dense_2_acc_11: 1.0000 - dense_2_acc_12: 1.0000 - dense_2_acc_13: 1.0000 - dense_2_acc_14: 1.0000 - dense_2_acc_15: 1.0000 - dense_2_acc_16: 1.0000 - dense_2_acc_17: 1.0000 - dense_2_acc_18: 1.0000 - dense_2_acc_19: 1.0000 - dense_2_acc_20: 1.0000 - dense_2_acc_21: 1.0000 - dense_2_acc_22: 1.0000 - dense_2_acc_23: 1.0000 - dense_2_acc_24: 1.0000 - dense_2_acc_25: 1.0000 - dense_2_acc_26: 0.9833 - dense_2_acc_27: 1.0000 - dense_2_acc_28: 1.0000 - dense_2_acc_29: 0.9833 - dense_2_acc_30: 0.0167 Epoch 49/100 60/60 [==============================] - 0s - loss: 11.9034 - dense_2_loss_1: 3.9252 - dense_2_loss_2: 2.0494 - dense_2_loss_3: 0.9292 - dense_2_loss_4: 0.5073 - dense_2_loss_5: 0.3474 - dense_2_loss_6: 0.2518 - dense_2_loss_7: 0.2278 - dense_2_loss_8: 0.1765 - dense_2_loss_9: 0.1960 - dense_2_loss_10: 0.1608 - dense_2_loss_11: 0.1648 - dense_2_loss_12: 0.1466 - dense_2_loss_13: 0.1359 - dense_2_loss_14: 0.1520 - dense_2_loss_15: 0.1592 - dense_2_loss_16: 0.1599 - dense_2_loss_17: 0.1537 - dense_2_loss_18: 0.1462 - dense_2_loss_19: 0.1562 - dense_2_loss_20: 0.1725 - dense_2_loss_21: 0.1752 - dense_2_loss_22: 0.1734 - dense_2_loss_23: 0.1639 - dense_2_loss_24: 0.1662 - dense_2_loss_25: 0.1724 - dense_2_loss_26: 0.1563 - dense_2_loss_27: 0.1839 - dense_2_loss_28: 0.1894 - dense_2_loss_29: 0.2041 - dense_2_loss_30: 0.0000e+00 - dense_2_acc_1: 0.0667 - dense_2_acc_2: 0.5333 - dense_2_acc_3: 0.7833 - dense_2_acc_4: 0.9167 - dense_2_acc_5: 0.9667 - dense_2_acc_6: 0.9833 - dense_2_acc_7: 0.9833 - dense_2_acc_8: 1.0000 - dense_2_acc_9: 1.0000 - dense_2_acc_10: 1.0000 - dense_2_acc_11: 1.0000 - dense_2_acc_12: 1.0000 - dense_2_acc_13: 1.0000 - dense_2_acc_14: 1.0000 - dense_2_acc_15: 1.0000 - dense_2_acc_16: 1.0000 - dense_2_acc_17: 1.0000 - dense_2_acc_18: 1.0000 - dense_2_acc_19: 1.0000 - dense_2_acc_20: 1.0000 - dense_2_acc_21: 1.0000 - dense_2_acc_22: 1.0000 - dense_2_acc_23: 1.0000 - dense_2_acc_24: 1.0000 - dense_2_acc_25: 1.0000 - dense_2_acc_26: 1.0000 - dense_2_acc_27: 1.0000 - dense_2_acc_28: 1.0000 - dense_2_acc_29: 0.9833 - dense_2_acc_30: 0.0167 Epoch 50/100 60/60 [==============================] - 0s - loss: 11.4816 - dense_2_loss_1: 3.9207 - dense_2_loss_2: 2.0125 - dense_2_loss_3: 0.8972 - dense_2_loss_4: 0.4796 - dense_2_loss_5: 0.3251 - dense_2_loss_6: 0.2364 - dense_2_loss_7: 0.2116 - dense_2_loss_8: 0.1626 - dense_2_loss_9: 0.1820 - dense_2_loss_10: 0.1495 - dense_2_loss_11: 0.1506 - dense_2_loss_12: 0.1356 - dense_2_loss_13: 0.1258 - dense_2_loss_14: 0.1396 - dense_2_loss_15: 0.1492 - dense_2_loss_16: 0.1487 - dense_2_loss_17: 0.1434 - dense_2_loss_18: 0.1369 - dense_2_loss_19: 0.1443 - dense_2_loss_20: 0.1583 - dense_2_loss_21: 0.1642 - dense_2_loss_22: 0.1598 - dense_2_loss_23: 0.1536 - dense_2_loss_24: 0.1540 - dense_2_loss_25: 0.1576 - dense_2_loss_26: 0.1449 - dense_2_loss_27: 0.1716 - dense_2_loss_28: 0.1761 - dense_2_loss_29: 0.1901 - dense_2_loss_30: 0.0000e+00 - dense_2_acc_1: 0.0667 - dense_2_acc_2: 0.5333 - dense_2_acc_3: 0.7833 - dense_2_acc_4: 0.9167 - dense_2_acc_5: 0.9833 - dense_2_acc_6: 0.9833 - dense_2_acc_7: 0.9833 - dense_2_acc_8: 1.0000 - dense_2_acc_9: 1.0000 - dense_2_acc_10: 1.0000 - dense_2_acc_11: 1.0000 - dense_2_acc_12: 1.0000 - dense_2_acc_13: 1.0000 - dense_2_acc_14: 1.0000 - dense_2_acc_15: 1.0000 - dense_2_acc_16: 1.0000 - dense_2_acc_17: 1.0000 - dense_2_acc_18: 1.0000 - dense_2_acc_19: 1.0000 - dense_2_acc_20: 1.0000 - dense_2_acc_21: 1.0000 - dense_2_acc_22: 1.0000 - dense_2_acc_23: 1.0000 - dense_2_acc_24: 1.0000 - dense_2_acc_25: 1.0000 - dense_2_acc_26: 1.0000 - dense_2_acc_27: 1.0000 - dense_2_acc_28: 1.0000 - dense_2_acc_29: 0.9833 - dense_2_acc_30: 0.0167 Epoch 51/100 60/60 [==============================] - 0s - loss: 11.1003 - dense_2_loss_1: 3.9163 - dense_2_loss_2: 1.9757 - dense_2_loss_3: 0.8688 - dense_2_loss_4: 0.4565 - dense_2_loss_5: 0.3062 - dense_2_loss_6: 0.2226 - dense_2_loss_7: 0.1969 - dense_2_loss_8: 0.1503 - dense_2_loss_9: 0.1688 - dense_2_loss_10: 0.1373 - dense_2_loss_11: 0.1420 - dense_2_loss_12: 0.1268 - dense_2_loss_13: 0.1162 - dense_2_loss_14: 0.1314 - dense_2_loss_15: 0.1359 - dense_2_loss_16: 0.1390 - dense_2_loss_17: 0.1336 - dense_2_loss_18: 0.1265 - dense_2_loss_19: 0.1345 - dense_2_loss_20: 0.1461 - dense_2_loss_21: 0.1522 - dense_2_loss_22: 0.1507 - dense_2_loss_23: 0.1422 - dense_2_loss_24: 0.1415 - dense_2_loss_25: 0.1497 - dense_2_loss_26: 0.1351 - dense_2_loss_27: 0.1585 - dense_2_loss_28: 0.1606 - dense_2_loss_29: 0.1786 - dense_2_loss_30: 0.0000e+00 - dense_2_acc_1: 0.0667 - dense_2_acc_2: 0.5333 - dense_2_acc_3: 0.7833 - dense_2_acc_4: 0.9167 - dense_2_acc_5: 0.9833 - dense_2_acc_6: 0.9833 - dense_2_acc_7: 0.9833 - dense_2_acc_8: 1.0000 - dense_2_acc_9: 1.0000 - dense_2_acc_10: 1.0000 - dense_2_acc_11: 1.0000 - dense_2_acc_12: 1.0000 - dense_2_acc_13: 1.0000 - dense_2_acc_14: 1.0000 - dense_2_acc_15: 1.0000 - dense_2_acc_16: 1.0000 - dense_2_acc_17: 1.0000 - dense_2_acc_18: 1.0000 - dense_2_acc_19: 1.0000 - dense_2_acc_20: 1.0000 - dense_2_acc_21: 1.0000 - dense_2_acc_22: 1.0000 - dense_2_acc_23: 1.0000 - dense_2_acc_24: 1.0000 - dense_2_acc_25: 1.0000 - dense_2_acc_26: 1.0000 - dense_2_acc_27: 1.0000 - dense_2_acc_28: 1.0000 - dense_2_acc_29: 0.9833 - dense_2_acc_30: 0.0167 Epoch 52/100 60/60 [==============================] - 0s - loss: 10.7445 - dense_2_loss_1: 3.9122 - dense_2_loss_2: 1.9411 - dense_2_loss_3: 0.8412 - dense_2_loss_4: 0.4328 - dense_2_loss_5: 0.2888 - dense_2_loss_6: 0.2100 - dense_2_loss_7: 0.1839 - dense_2_loss_8: 0.1401 - dense_2_loss_9: 0.1565 - dense_2_loss_10: 0.1277 - dense_2_loss_11: 0.1316 - dense_2_loss_12: 0.1174 - dense_2_loss_13: 0.1092 - dense_2_loss_14: 0.1210 - dense_2_loss_15: 0.1268 - dense_2_loss_16: 0.1293 - dense_2_loss_17: 0.1251 - dense_2_loss_18: 0.1173 - dense_2_loss_19: 0.1257 - dense_2_loss_20: 0.1370 - dense_2_loss_21: 0.1425 - dense_2_loss_22: 0.1388 - dense_2_loss_23: 0.1306 - dense_2_loss_24: 0.1287 - dense_2_loss_25: 0.1422 - dense_2_loss_26: 0.1273 - dense_2_loss_27: 0.1453 - dense_2_loss_28: 0.1465 - dense_2_loss_29: 0.1676 - dense_2_loss_30: 0.0000e+00 - dense_2_acc_1: 0.0667 - dense_2_acc_2: 0.5333 - dense_2_acc_3: 0.7833 - dense_2_acc_4: 0.9167 - dense_2_acc_5: 0.9833 - dense_2_acc_6: 0.9833 - dense_2_acc_7: 0.9833 - dense_2_acc_8: 1.0000 - dense_2_acc_9: 1.0000 - dense_2_acc_10: 1.0000 - dense_2_acc_11: 1.0000 - dense_2_acc_12: 1.0000 - dense_2_acc_13: 1.0000 - dense_2_acc_14: 1.0000 - dense_2_acc_15: 1.0000 - dense_2_acc_16: 1.0000 - dense_2_acc_17: 1.0000 - dense_2_acc_18: 1.0000 - dense_2_acc_19: 1.0000 - dense_2_acc_20: 1.0000 - dense_2_acc_21: 1.0000 - dense_2_acc_22: 1.0000 - dense_2_acc_23: 1.0000 - dense_2_acc_24: 1.0000 - dense_2_acc_25: 1.0000 - dense_2_acc_26: 1.0000 - dense_2_acc_27: 1.0000 - dense_2_acc_28: 1.0000 - dense_2_acc_29: 0.9833 - dense_2_acc_30: 0.0167 Epoch 53/100 60/60 [==============================] - 0s - loss: 10.4301 - dense_2_loss_1: 3.9077 - dense_2_loss_2: 1.9073 - dense_2_loss_3: 0.8153 - dense_2_loss_4: 0.4112 - dense_2_loss_5: 0.2731 - dense_2_loss_6: 0.1998 - dense_2_loss_7: 0.1734 - dense_2_loss_8: 0.1321 - dense_2_loss_9: 0.1466 - dense_2_loss_10: 0.1211 - dense_2_loss_11: 0.1212 - dense_2_loss_12: 0.1105 - dense_2_loss_13: 0.1026 - dense_2_loss_14: 0.1121 - dense_2_loss_15: 0.1202 - dense_2_loss_16: 0.1197 - dense_2_loss_17: 0.1167 - dense_2_loss_18: 0.1101 - dense_2_loss_19: 0.1162 - dense_2_loss_20: 0.1281 - dense_2_loss_21: 0.1319 - dense_2_loss_22: 0.1292 - dense_2_loss_23: 0.1210 - dense_2_loss_24: 0.1206 - dense_2_loss_25: 0.1272 - dense_2_loss_26: 0.1198 - dense_2_loss_27: 0.1380 - dense_2_loss_28: 0.1398 - dense_2_loss_29: 0.1574 - dense_2_loss_30: 0.0000e+00 - dense_2_acc_1: 0.0667 - dense_2_acc_2: 0.5500 - dense_2_acc_3: 0.8167 - dense_2_acc_4: 0.9167 - dense_2_acc_5: 0.9833 - dense_2_acc_6: 0.9833 - dense_2_acc_7: 0.9833 - dense_2_acc_8: 1.0000 - dense_2_acc_9: 1.0000 - dense_2_acc_10: 1.0000 - dense_2_acc_11: 1.0000 - dense_2_acc_12: 1.0000 - dense_2_acc_13: 1.0000 - dense_2_acc_14: 1.0000 - dense_2_acc_15: 1.0000 - dense_2_acc_16: 1.0000 - dense_2_acc_17: 1.0000 - dense_2_acc_18: 1.0000 - dense_2_acc_19: 1.0000 - dense_2_acc_20: 1.0000 - dense_2_acc_21: 1.0000 - dense_2_acc_22: 1.0000 - dense_2_acc_23: 1.0000 - dense_2_acc_24: 1.0000 - dense_2_acc_25: 1.0000 - dense_2_acc_26: 1.0000 - dense_2_acc_27: 1.0000 - dense_2_acc_28: 1.0000 - dense_2_acc_29: 1.0000 - dense_2_acc_30: 0.0167 Epoch 54/100 60/60 [==============================] - 0s - loss: 10.1284 - dense_2_loss_1: 3.9037 - dense_2_loss_2: 1.8752 - dense_2_loss_3: 0.7905 - dense_2_loss_4: 0.3903 - dense_2_loss_5: 0.2561 - dense_2_loss_6: 0.1879 - dense_2_loss_7: 0.1612 - dense_2_loss_8: 0.1242 - dense_2_loss_9: 0.1362 - dense_2_loss_10: 0.1135 - dense_2_loss_11: 0.1137 - dense_2_loss_12: 0.1039 - dense_2_loss_13: 0.0953 - dense_2_loss_14: 0.1052 - dense_2_loss_15: 0.1124 - dense_2_loss_16: 0.1123 - dense_2_loss_17: 0.1091 - dense_2_loss_18: 0.1025 - dense_2_loss_19: 0.1076 - dense_2_loss_20: 0.1195 - dense_2_loss_21: 0.1240 - dense_2_loss_22: 0.1219 - dense_2_loss_23: 0.1127 - dense_2_loss_24: 0.1130 - dense_2_loss_25: 0.1181 - dense_2_loss_26: 0.1124 - dense_2_loss_27: 0.1267 - dense_2_loss_28: 0.1309 - dense_2_loss_29: 0.1487 - dense_2_loss_30: 0.0000e+00 - dense_2_acc_1: 0.0667 - dense_2_acc_2: 0.5500 - dense_2_acc_3: 0.8167 - dense_2_acc_4: 0.9333 - dense_2_acc_5: 0.9833 - dense_2_acc_6: 0.9833 - dense_2_acc_7: 0.9833 - dense_2_acc_8: 1.0000 - dense_2_acc_9: 1.0000 - dense_2_acc_10: 1.0000 - dense_2_acc_11: 1.0000 - dense_2_acc_12: 1.0000 - dense_2_acc_13: 1.0000 - dense_2_acc_14: 1.0000 - dense_2_acc_15: 1.0000 - dense_2_acc_16: 1.0000 - dense_2_acc_17: 1.0000 - dense_2_acc_18: 1.0000 - dense_2_acc_19: 1.0000 - dense_2_acc_20: 1.0000 - dense_2_acc_21: 1.0000 - dense_2_acc_22: 1.0000 - dense_2_acc_23: 1.0000 - dense_2_acc_24: 1.0000 - dense_2_acc_25: 1.0000 - dense_2_acc_26: 1.0000 - dense_2_acc_27: 1.0000 - dense_2_acc_28: 1.0000 - dense_2_acc_29: 1.0000 - dense_2_acc_30: 0.0167 Epoch 55/100 60/60 [==============================] - 0s - loss: 9.8628 - dense_2_loss_1: 3.8994 - dense_2_loss_2: 1.8424 - dense_2_loss_3: 0.7677 - dense_2_loss_4: 0.3730 - dense_2_loss_5: 0.2429 - dense_2_loss_6: 0.1788 - dense_2_loss_7: 0.1517 - dense_2_loss_8: 0.1166 - dense_2_loss_9: 0.1288 - dense_2_loss_10: 0.1050 - dense_2_loss_11: 0.1079 - dense_2_loss_12: 0.0976 - dense_2_loss_13: 0.0889 - dense_2_loss_14: 0.0993 - dense_2_loss_15: 0.1041 - dense_2_loss_16: 0.1071 - dense_2_loss_17: 0.1026 - dense_2_loss_18: 0.0961 - dense_2_loss_19: 0.1008 - dense_2_loss_20: 0.1123 - dense_2_loss_21: 0.1175 - dense_2_loss_22: 0.1136 - dense_2_loss_23: 0.1064 - dense_2_loss_24: 0.1065 - dense_2_loss_25: 0.1137 - dense_2_loss_26: 0.1039 - dense_2_loss_27: 0.1177 - dense_2_loss_28: 0.1218 - dense_2_loss_29: 0.1385 - dense_2_loss_30: 0.0000e+00 - dense_2_acc_1: 0.0667 - dense_2_acc_2: 0.5667 - dense_2_acc_3: 0.8167 - dense_2_acc_4: 0.9333 - dense_2_acc_5: 0.9833 - dense_2_acc_6: 0.9833 - dense_2_acc_7: 0.9833 - dense_2_acc_8: 1.0000 - dense_2_acc_9: 1.0000 - dense_2_acc_10: 1.0000 - dense_2_acc_11: 1.0000 - dense_2_acc_12: 1.0000 - dense_2_acc_13: 1.0000 - dense_2_acc_14: 1.0000 - dense_2_acc_15: 1.0000 - dense_2_acc_16: 1.0000 - dense_2_acc_17: 1.0000 - dense_2_acc_18: 1.0000 - dense_2_acc_19: 1.0000 - dense_2_acc_20: 1.0000 - dense_2_acc_21: 1.0000 - dense_2_acc_22: 1.0000 - dense_2_acc_23: 1.0000 - dense_2_acc_24: 1.0000 - dense_2_acc_25: 1.0000 - dense_2_acc_26: 1.0000 - dense_2_acc_27: 1.0000 - dense_2_acc_28: 1.0000 - dense_2_acc_29: 0.9833 - dense_2_acc_30: 0.0167 Epoch 56/100 60/60 [==============================] - 0s - loss: 9.6036 - dense_2_loss_1: 3.8957 - dense_2_loss_2: 1.8124 - dense_2_loss_3: 0.7442 - dense_2_loss_4: 0.3552 - dense_2_loss_5: 0.2278 - dense_2_loss_6: 0.1700 - dense_2_loss_7: 0.1411 - dense_2_loss_8: 0.1093 - dense_2_loss_9: 0.1202 - dense_2_loss_10: 0.0968 - dense_2_loss_11: 0.1007 - dense_2_loss_12: 0.0914 - dense_2_loss_13: 0.0835 - dense_2_loss_14: 0.0929 - dense_2_loss_15: 0.0975 - dense_2_loss_16: 0.1005 - dense_2_loss_17: 0.0972 - dense_2_loss_18: 0.0900 - dense_2_loss_19: 0.0953 - dense_2_loss_20: 0.1053 - dense_2_loss_21: 0.1105 - dense_2_loss_22: 0.1063 - dense_2_loss_23: 0.1013 - dense_2_loss_24: 0.0996 - dense_2_loss_25: 0.1058 - dense_2_loss_26: 0.0961 - dense_2_loss_27: 0.1128 - dense_2_loss_28: 0.1149 - dense_2_loss_29: 0.1295 - dense_2_loss_30: 0.0000e+00 - dense_2_acc_1: 0.0667 - dense_2_acc_2: 0.5667 - dense_2_acc_3: 0.8167 - dense_2_acc_4: 0.9500 - dense_2_acc_5: 0.9833 - dense_2_acc_6: 0.9833 - dense_2_acc_7: 1.0000 - dense_2_acc_8: 1.0000 - dense_2_acc_9: 1.0000 - dense_2_acc_10: 1.0000 - dense_2_acc_11: 1.0000 - dense_2_acc_12: 1.0000 - dense_2_acc_13: 1.0000 - dense_2_acc_14: 1.0000 - dense_2_acc_15: 1.0000 - dense_2_acc_16: 1.0000 - dense_2_acc_17: 1.0000 - dense_2_acc_18: 1.0000 - dense_2_acc_19: 1.0000 - dense_2_acc_20: 1.0000 - dense_2_acc_21: 1.0000 - dense_2_acc_22: 1.0000 - dense_2_acc_23: 1.0000 - dense_2_acc_24: 1.0000 - dense_2_acc_25: 1.0000 - dense_2_acc_26: 1.0000 - dense_2_acc_27: 1.0000 - dense_2_acc_28: 1.0000 - dense_2_acc_29: 0.9833 - dense_2_acc_30: 0.0167 Epoch 57/100 60/60 [==============================] - 0s - loss: 9.3751 - dense_2_loss_1: 3.8915 - dense_2_loss_2: 1.7825 - dense_2_loss_3: 0.7236 - dense_2_loss_4: 0.3395 - dense_2_loss_5: 0.2167 - dense_2_loss_6: 0.1621 - dense_2_loss_7: 0.1330 - dense_2_loss_8: 0.1036 - dense_2_loss_9: 0.1135 - dense_2_loss_10: 0.0917 - dense_2_loss_11: 0.0943 - dense_2_loss_12: 0.0864 - dense_2_loss_13: 0.0792 - dense_2_loss_14: 0.0871 - dense_2_loss_15: 0.0928 - dense_2_loss_16: 0.0941 - dense_2_loss_17: 0.0915 - dense_2_loss_18: 0.0844 - dense_2_loss_19: 0.0900 - dense_2_loss_20: 0.0985 - dense_2_loss_21: 0.1020 - dense_2_loss_22: 0.1000 - dense_2_loss_23: 0.0953 - dense_2_loss_24: 0.0932 - dense_2_loss_25: 0.0985 - dense_2_loss_26: 0.0904 - dense_2_loss_27: 0.1075 - dense_2_loss_28: 0.1085 - dense_2_loss_29: 0.1238 - dense_2_loss_30: 0.0000e+00 - dense_2_acc_1: 0.0667 - dense_2_acc_2: 0.5667 - dense_2_acc_3: 0.8333 - dense_2_acc_4: 0.9500 - dense_2_acc_5: 0.9833 - dense_2_acc_6: 0.9833 - dense_2_acc_7: 1.0000 - dense_2_acc_8: 1.0000 - dense_2_acc_9: 1.0000 - dense_2_acc_10: 1.0000 - dense_2_acc_11: 1.0000 - dense_2_acc_12: 1.0000 - dense_2_acc_13: 1.0000 - dense_2_acc_14: 1.0000 - dense_2_acc_15: 1.0000 - dense_2_acc_16: 1.0000 - dense_2_acc_17: 1.0000 - dense_2_acc_18: 1.0000 - dense_2_acc_19: 1.0000 - dense_2_acc_20: 1.0000 - dense_2_acc_21: 1.0000 - dense_2_acc_22: 1.0000 - dense_2_acc_23: 1.0000 - dense_2_acc_24: 1.0000 - dense_2_acc_25: 1.0000 - dense_2_acc_26: 1.0000 - dense_2_acc_27: 1.0000 - dense_2_acc_28: 1.0000 - dense_2_acc_29: 1. 4000 0000 - dense_2_acc_30: 0.0167 Epoch 58/100 60/60 [==============================] - 0s - loss: 9.1622 - dense_2_loss_1: 3.8875 - dense_2_loss_2: 1.7539 - dense_2_loss_3: 0.7045 - dense_2_loss_4: 0.3248 - dense_2_loss_5: 0.2060 - dense_2_loss_6: 0.1534 - dense_2_loss_7: 0.1254 - dense_2_loss_8: 0.0983 - dense_2_loss_9: 0.1061 - dense_2_loss_10: 0.0871 - dense_2_loss_11: 0.0881 - dense_2_loss_12: 0.0816 - dense_2_loss_13: 0.0752 - dense_2_loss_14: 0.0817 - dense_2_loss_15: 0.0885 - dense_2_loss_16: 0.0889 - dense_2_loss_17: 0.0864 - dense_2_loss_18: 0.0800 - dense_2_loss_19: 0.0849 - dense_2_loss_20: 0.0928 - dense_2_loss_21: 0.0961 - dense_2_loss_22: 0.0945 - dense_2_loss_23: 0.0896 - dense_2_loss_24: 0.0876 - dense_2_loss_25: 0.0940 - dense_2_loss_26: 0.0856 - dense_2_loss_27: 0.1006 - dense_2_loss_28: 0.1019 - dense_2_loss_29: 0.1173 - dense_2_loss_30: 0.0000e+00 - dense_2_acc_1: 0.1000 - dense_2_acc_2: 0.5667 - dense_2_acc_3: 0.8500 - dense_2_acc_4: 0.9667 - dense_2_acc_5: 0.9833 - dense_2_acc_6: 0.9833 - dense_2_acc_7: 1.0000 - dense_2_acc_8: 1.0000 - dense_2_acc_9: 1.0000 - dense_2_acc_10: 1.0000 - dense_2_acc_11: 1.0000 - dense_2_acc_12: 1.0000 - dense_2_acc_13: 1.0000 - dense_2_acc_14: 1.0000 - dense_2_acc_15: 1.0000 - dense_2_acc_16: 1.0000 - dense_2_acc_17: 1.0000 - dense_2_acc_18: 1.0000 - dense_2_acc_19: 1.0000 - dense_2_acc_20: 1.0000 - dense_2_acc_21: 1.0000 - dense_2_acc_22: 1.0000 - dense_2_acc_23: 1.0000 - dense_2_acc_24: 1.0000 - dense_2_acc_25: 1.0000 - dense_2_acc_26: 1.0000 - dense_2_acc_27: 1.0000 - dense_2_acc_28: 1.0000 - dense_2_acc_29: 1.0000 - dense_2_acc_30: 0.0167 Epoch 59/100 60/60 [==============================] - 0s - loss: 8.9613 - dense_2_loss_1: 3.8840 - dense_2_loss_2: 1.7265 - dense_2_loss_3: 0.6844 - dense_2_loss_4: 0.3110 - dense_2_loss_5: 0.1955 - dense_2_loss_6: 0.1454 - dense_2_loss_7: 0.1181 - dense_2_loss_8: 0.0929 - dense_2_loss_9: 0.0996 - dense_2_loss_10: 0.0820 - dense_2_loss_11: 0.0837 - dense_2_loss_12: 0.0778 - dense_2_loss_13: 0.0707 - dense_2_loss_14: 0.0779 - dense_2_loss_15: 0.0832 - dense_2_loss_16: 0.0845 - dense_2_loss_17: 0.0810 - dense_2_loss_18: 0.0759 - dense_2_loss_19: 0.0800 - dense_2_loss_20: 0.0878 - dense_2_loss_21: 0.0912 - dense_2_loss_22: 0.0892 - dense_2_loss_23: 0.0841 - dense_2_loss_24: 0.0828 - dense_2_loss_25: 0.0901 - dense_2_loss_26: 0.0810 - dense_2_loss_27: 0.0944 - dense_2_loss_28: 0.0962 - dense_2_loss_29: 0.1105 - dense_2_loss_30: 0.0000e+00 - dense_2_acc_1: 0.1000 - dense_2_acc_2: 0.5667 - dense_2_acc_3: 0.8500 - dense_2_acc_4: 0.9667 - dense_2_acc_5: 0.9833 - dense_2_acc_6: 0.9833 - dense_2_acc_7: 1.0000 - dense_2_acc_8: 1.0000 - dense_2_acc_9: 1.0000 - dense_2_acc_10: 1.0000 - dense_2_acc_11: 1.0000 - dense_2_acc_12: 1.0000 - dense_2_acc_13: 1.0000 - dense_2_acc_14: 1.0000 - dense_2_acc_15: 1.0000 - dense_2_acc_16: 1.0000 - dense_2_acc_17: 1.0000 - dense_2_acc_18: 1.0000 - dense_2_acc_19: 1.0000 - dense_2_acc_20: 1.0000 - dense_2_acc_21: 1.0000 - dense_2_acc_22: 1.0000 - dense_2_acc_23: 1.0000 - dense_2_acc_24: 1.0000 - dense_2_acc_25: 1.0000 - dense_2_acc_26: 1.0000 - dense_2_acc_27: 1.0000 - dense_2_acc_28: 1.0000 - dense_2_acc_29: 1.0000 - dense_2_acc_30: 0.0167 Epoch 60/100 60/60 [==============================] - 0s - loss: 8.7732 - dense_2_loss_1: 3.8801 - dense_2_loss_2: 1.6999 - dense_2_loss_3: 0.6668 - dense_2_loss_4: 0.2976 - dense_2_loss_5: 0.1843 - dense_2_loss_6: 0.1384 - dense_2_loss_7: 0.1106 - dense_2_loss_8: 0.0884 - dense_2_loss_9: 0.0931 - dense_2_loss_10: 0.0771 - dense_2_loss_11: 0.0798 - dense_2_loss_12: 0.0740 - dense_2_loss_13: 0.0667 - dense_2_loss_14: 0.0749 - dense_2_loss_15: 0.0779 - dense_2_loss_16: 0.0798 - dense_2_loss_17: 0.0769 - dense_2_loss_18: 0.0714 - dense_2_loss_19: 0.0761 - dense_2_loss_20: 0.0827 - dense_2_loss_21: 0.0862 - dense_2_loss_22: 0.0852 - dense_2_loss_23: 0.0797 - dense_2_loss_24: 0.0787 - dense_2_loss_25: 0.0836 - dense_2_loss_26: 0.0767 - dense_2_loss_27: 0.0908 - dense_2_loss_28: 0.0927 - dense_2_loss_29: 0.1032 - dense_2_loss_30: 0.0000e+00 - dense_2_acc_1: 0.1000 - dense_2_acc_2: 0.5500 - dense_2_acc_3: 0.8500 - dense_2_acc_4: 0.9667 - dense_2_acc_5: 0.9833 - dense_2_acc_6: 1.0000 - dense_2_acc_7: 1.0000 - dense_2_acc_8: 1.0000 - dense_2_acc_9: 1.0000 - dense_2_acc_10: 1.0000 - dense_2_acc_11: 1.0000 - dense_2_acc_12: 1.0000 - dense_2_acc_13: 1.0000 - dense_2_acc_14: 1.0000 - dense_2_acc_15: 1.0000 - dense_2_acc_16: 1.0000 - dense_2_acc_17: 1.0000 - dense_2_acc_18: 1.0000 - dense_2_acc_19: 1.0000 - dense_2_acc_20: 1.0000 - dense_2_acc_21: 1.0000 - dense_2_acc_22: 1.0000 - dense_2_acc_23: 1.0000 - dense_2_acc_24: 1.0000 - dense_2_acc_25: 1.0000 - dense_2_acc_26: 1.0000 - dense_2_acc_27: 1.0000 - dense_2_acc_28: 1.0000 - dense_2_acc_29: 1.0000 - dense_2_acc_30: 0.0167 Epoch 61/100 60/60 [==============================] - 0s - loss: 8.6075 - dense_2_loss_1: 3.8762 - dense_2_loss_2: 1.6750 - dense_2_loss_3: 0.6493 - dense_2_loss_4: 0.2846 - dense_2_loss_5: 0.1764 - dense_2_loss_6: 0.1326 - dense_2_loss_7: 0.1053 - dense_2_loss_8: 0.0847 - dense_2_loss_9: 0.0883 - dense_2_loss_10: 0.0730 - dense_2_loss_11: 0.0754 - dense_2_loss_12: 0.0700 - dense_2_loss_13: 0.0638 - dense_2_loss_14: 0.0704 - dense_2_loss_15: 0.0748 - dense_2_loss_16: 0.0755 - dense_2_loss_17: 0.0734 - dense_2_loss_18: 0.0673 - dense_2_loss_19: 0.0722 - dense_2_loss_20: 0.0789 - dense_2_loss_21: 0.0819 - dense_2_loss_22: 0.0805 - dense_2_loss_23: 0.0761 - dense_2_loss_24: 0.0747 - dense_2_loss_25: 0.0772 - dense_2_loss_26: 0.0731 - dense_2_loss_27: 0.0890 - dense_2_loss_28: 0.0900 - dense_2_loss_29: 0.0979 - dense_2_loss_30: 0.0000e+00 - dense_2_acc_1: 0.1000 - dense_2_acc_2: 0.5500 - dense_2_acc_3: 0.8500 - dense_2_acc_4: 0.9667 - dense_2_acc_5: 0.9833 - dense_2_acc_6: 1.0000 - dense_2_acc_7: 1.0000 - dense_2_acc_8: 1.0000 - dense_2_acc_9: 1.0000 - dense_2_acc_10: 1.0000 - dense_2_acc_11: 1.0000 - dense_2_acc_12: 1.0000 - dense_2_acc_13: 1.0000 - dense_2_acc_14: 1.0000 - dense_2_acc_15: 1.0000 - dense_2_acc_16: 1.0000 - dense_2_acc_17: 1.0000 - dense_2_acc_18: 1.0000 - dense_2_acc_19: 1.0000 - dense_2_acc_20: 1.0000 - dense_2_acc_21: 1.0000 - dense_2_acc_22: 1.0000 - dense_2_acc_23: 1.0000 - dense_2_acc_24: 1.0000 - dense_2_acc_25: 1.0000 - dense_2_acc_26: 1.0000 - dense_2_acc_27: 1.0000 - dense_2_acc_28: 1.0000 - dense_2_acc_29: 1.0000 - dense_2_acc_30: 0.0167 Epoch 62/100 60/60 [==============================] - 0s - loss: 8.4464 - dense_2_loss_1: 3.8725 - dense_2_loss_2: 1.6496 - dense_2_loss_3: 0.6329 - dense_2_loss_4: 0.2733 - dense_2_loss_5: 0.1678 - dense_2_loss_6: 0.1264 - dense_2_loss_7: 0.0996 - dense_2_loss_8: 0.0807 - dense_2_loss_9: 0.0838 - dense_2_loss_10: 0.0696 - dense_2_loss_11: 0.0723 - dense_2_loss_12: 0.0664 - dense_2_loss_13: 0.0611 - dense_2_loss_14: 0.0665 - dense_2_loss_15: 0.0718 - dense_2_loss_16: 0.0719 - dense_2_loss_17: 0.0699 - dense_2_loss_18: 0.0633 - dense_2_loss_19: 0.0692 - dense_2_loss_20: 0.0751 - dense_2_loss_21: 0.0784 - dense_2_loss_22: 0.0758 - dense_2_loss_23: 0.0721 - dense_2_loss_24: 0.0708 - dense_2_loss_25: 0.0747 - dense_2_loss_26: 0.0699 - dense_2_loss_27: 0.0831 - dense_2_loss_28: 0.0841 - dense_2_loss_29: 0.0940 - dense_2_loss_30: 0.0000e+00 - dense_2_acc_1: 0.1000 - dense_2_acc_2: 0.5500 - dense_2_acc_3: 0.8500 - dense_2_acc_4: 0.9833 - dense_2_acc_5: 0.9833 - dense_2_acc_6: 1.0000 - dense_2_acc_7: 1.0000 - dense_2_acc_8: 1.0000 - dense_2_acc_9: 1.0000 - dense_2_acc_10: 1.0000 - dense_2_acc_11: 1.0000 - dense_2_acc_12: 1.0000 - dense_2_acc_13: 1.0000 - dense_2_acc_14: 1.0000 - dense_2_acc_15: 1.0000 - dense_2_acc_16: 1.0000 - dense_2_acc_17: 1.0000 - dense_2_acc_18: 1.0000 - dense_2_acc_19: 1.0000 - dense_2_acc_20: 1.0000 - dense_2_acc_21: 1.0000 - dense_2_acc_22: 1.0000 - dense_2_acc_23: 1.0000 - dense_2_acc_24: 1.0000 - dense_2_acc_25: 1.0000 - dense_2_acc_26: 1.0000 - dense_2_acc_27: 1.0000 - dense_2_acc_28: 1.0000 - dense_2_acc_29: 1.0000 - dense_2_acc_30: 0.0167 Epoch 63/100 60/60 [==============================] - 0s - loss: 8.2979 - dense_2_loss_1: 3.8689 - dense_2_loss_2: 1.6260 - dense_2_loss_3: 0.6167 - dense_2_loss_4: 0.2620 - dense_2_loss_5: 0.1598 - dense_2_loss_6: 0.1205 - dense_2_loss_7: 0.0944 - dense_2_loss_8: 0.0771 - dense_2_loss_9: 0.0798 - dense_2_loss_10: 0.0662 - dense_2_loss_11: 0.0692 - dense_2_loss_12: 0.0632 - dense_2_loss_13: 0.0581 - dense_2_loss_14: 0.0639 - dense_2_loss_15: 0.0679 - dense_2_loss_16: 0.0687 - dense_2_loss_17: 0.0661 - dense_2_loss_18: 0.0601 - dense_2_loss_19: 0.0658 - dense_2_loss_20: 0.0714 - dense_2_loss_21: 0.0747 - dense_2_loss_22: 0.0722 - dense_2_loss_23: 0.0681 - dense_2_loss_24: 0.0670 - dense_2_loss_25: 0.0752 - dense_2_loss_26: 0.0685 - dense_2_loss_27: 0.0763 - dense_2_loss_28: 0.0778 - dense_2_loss_29: 0.0922 - dense_2_loss_30: 0.0000e+00 - dense_2_acc_1: 0.1000 - dense_2_acc_2: 0.5500 - dense_2_acc_3: 0.8500 - dense_2_acc_4: 0.9833 - dense_2_acc_5: 0.9833 - dense_2_acc_6: 1.0000 - dense_2_acc_7: 1.0000 - dense_2_acc_8: 1.0000 - dense_2_acc_9: 1.0000 - dense_2_acc_10: 1.0000 - dense_2_acc_11: 1.0000 - dense_2_acc_12: 1.0000 - dense_2_acc_13: 1.0000 - dense_2_acc_14: 1.0000 - dense_2_acc_15: 1.0000 - dense_2_acc_16: 1.0000 - dense_2_acc_17: 1.0000 - dense_2_acc_18: 1.0000 - dense_2_acc_19: 1.0000 - dense_2_acc_20: 1.0000 - dense_2_acc_21: 1.0000 - dense_2_acc_22: 1.0000 - dense_2_acc_23: 1.0000 - dense_2_acc_24: 1.0000 - dense_2_acc_25: 1.0000 - dense_2_acc_26: 1.0000 - dense_2_acc_27: 1.0000 - dense_2_acc_28: 1.0000 - dense_2_acc_29: 1.0000 - dense_2_acc_30: 0.0167 Epoch 64/100 60/60 [==============================] - 0s - loss: 8.1514 - dense_2_loss_1: 3.8652 - dense_2_loss_2: 1.6033 - dense_2_loss_3: 0.6005 - dense_2_loss_4: 0.2516 - dense_2_loss_5: 0.1520 - dense_2_loss_6: 0.1152 - dense_2_loss_7: 0.0898 - dense_2_loss_8: 0.0736 - dense_2_loss_9: 0.0760 - dense_2_loss_10: 0.0632 - dense_2_loss_11: 0.0657 - dense_2_loss_12: 0.0604 - dense_2_loss_13: 0.0553 - dense_2_loss_14: 0.0614 - dense_2_loss_15: 0.0643 - dense_2_loss_16: 0.0651 - dense_2_loss_17: 0.0629 - dense_2_loss_18: 0.0580 - dense_2_loss_19: 0.0625 - dense_2_loss_20: 0.0675 - dense_2_loss_21: 0.0707 - dense_2_loss_22: 0.0691 - dense_2_loss_23: 0.0654 - dense_2_loss_24: 0.0641 - dense_2_loss_25: 0.0692 - dense_2_loss_26: 0.0640 - dense_2_loss_27: 0.0740 - dense_2_loss_28: 0.0748 - dense_2_loss_29: 0.0867 - dense_2_loss_30: 0.0000e+00 - dense_2_acc_1: 0.1000 - dense_2_acc_2: 0.5500 - dense_2_acc_3: 0.8500 - dense_2_acc_4: 0.9833 - dense_2_acc_5: 1.0000 - dense_2_acc_6: 1.0000 - dense_2_acc_7: 1.0000 - dense_2_acc_8: 1.0000 - dense_2_acc_9: 1.0000 - dense_2_acc_10: 1.0000 - dense_2_acc_11: 1.0000 - dense_2_acc_12: 1.0000 - dense_2_acc_13: 1.0000 - dense_2_acc_14: 1.0000 - dense_2_acc_15: 1.0000 - dense_2_acc_16: 1.0000 - dense_2_acc_17: 1.0000 - dense_2_acc_18: 1.0000 - dense_2_acc_19: 1.0000 - dense_2_acc_20: 1.0000 - dense_2_acc_21: 1.0000 - dense_2_acc_22: 1.0000 - dense_2_acc_23: 1.0000 - dense_2_acc_24: 1.0000 - dense_2_acc_25: 1.0000 - dense_2_acc_26: 1.0000 - dense_2_acc_27: 1.0000 - dense_2_acc_28: 1.0000 - dense_2_acc_29: 1.0000 - dense_2_acc_30: 0.0167 Epoch 65/100 60/60 [==============================] - 0s - loss: 8.0224 - dense_2_loss_1: 3.8619 - dense_2_loss_2: 1.5806 - dense_2_loss_3: 0.5866 - dense_2_loss_4: 0.2420 - dense_2_loss_5: 0.1455 - dense_2_loss_6: 0.1105 - dense_2_loss_7: 0.0859 - dense_2_loss_8: 0.0705 - dense_2_loss_9: 0.0723 - dense_2_loss_10: 0.0603 - dense_2_loss_11: 0.0623 - dense_2_loss_12: 0.0580 - dense_2_loss_13: 0.0529 - dense_2_loss_14: 0.0584 - dense_2_loss_15: 0.0616 - dense_2_loss_16: 0.0622 - dense_2_loss_17: 0.0600 - dense_2_loss_18: 0.0561 - dense_2_loss_19: 0.0596 - dense_2_loss_20: 0.0644 - dense_2_loss_21: 0.0675 - dense_2_loss_22: 0.0656 - dense_2_loss_23: 0.0629 - dense_2_loss_24: 0.0617 - dense_2_loss_25: 0.0640 - dense_2_loss_26: 0.0600 - dense_2_loss_27: 0.0738 - dense_2_loss_28: 0.0735 - dense_2_loss_29: 0.0818 - dense_2_loss_30: 0.0000e+00 - dense_2_acc_1: 0.1000 - dense_2_acc_2: 0.5500 - dense_2_acc_3: 0.8667 - dense_2_acc_4: 0.9833 - dense_2_acc_5: 1.0000 - dense_2_acc_6: 1.0000 - dense_2_acc_7: 1.0000 - dense_2_acc_8: 1.0000 - dense_2_acc_9: 1.0000 - dense_2_acc_10: 1.0000 - dense_2_acc_11: 1.0000 - dense_2_acc_12: 1.0000 - dense_2_acc_13: 1.0000 - dense_2_acc_14: 1.0000 - dense_2_acc_15: 1.0000 - dense_2_acc_16: 1.0000 - dense_2_acc_17: 1.0000 - dense_2_acc_18: 1.0000 - dense_2_acc_19: 1.0000 - dense_2_acc_20: 1.0000 - dense_2_acc_21: 1.0000 - dense_2_acc_22: 1.0000 - dense_2_acc_23: 1.0000 - dense_2_acc_24: 1.0000 - dense_2_acc_25: 1.0000 - dense_2_acc_26: 1.0000 - dense_2_acc_27: 1.0000 - dense_2_acc_28: 1.0000 - dense_2_acc_29: 1.0000 - dense_2_acc_30: 0.0167 Epoch 66/100 60/60 [==============================] - 0s - loss: 7.8958 - dense_2_loss_1: 3.8585 - dense_2_loss_2: 1.5587 - dense_2_loss_3: 0.5719 - dense_2_loss_4: 0.2327 - dense_2_loss_5: 0.1386 - dense_2_loss_6: 0.1059 - dense_2_loss_7: 0.0818 - dense_2_loss_8: 0.0675 - dense_2_loss_9: 0.0685 - dense_2_loss_10: 0.0578 - dense_2_loss_11: 0.0593 - dense_2_loss_12: 0.0556 - dense_2_loss_13: 0.0508 - dense_2_loss_14: 0.0555 - dense_2_loss_15: 0.0594 - dense_2_loss_16: 0.0599 - dense_2_loss_17: 0.0576 - dense_2_loss_18: 0.0531 - dense_2_loss_19: 0.0571 - dense_2_loss_20: 0.0618 - dense_2_loss_21: 0.0649 - dense_2_loss_22: 0.0626 - dense_2_loss_23: 0.0599 - dense_2_loss_24: 0.0589 - dense_2_loss_25: 0.0619 - dense_2_loss_26: 0.0573 - dense_2_loss_27: 0.0702 - dense_2_loss_28: 0.0700 - dense_2_loss_29: 0.0779 - dense_2_loss_30: 0.0000e+00 - dense_2_acc_1: 0.1000 - dense_2_acc_2: 0.5500 - dense_2_acc_3: 0.8667 - dense_2_acc_4: 0.9833 - dense_2_acc_5: 1.0000 - dense_2_acc_6: 1.0000 - dense_2_acc_7: 1.0000 - dense_2_acc_8: 1.0000 - dense_2_acc_9: 1.0000 - dense_2_acc_10: 1.0000 - dense_2_acc_11: 1.0000 - dense_2_acc_12: 1.0000 - dense_2_acc_13: 1.0000 - dense_2_acc_14: 1.0000 - dense_2_acc_15: 1.0000 - dense_2_acc_16: 1.0000 - dense_2_acc_17: 1.0000 - dense_2_acc_18: 1.0000 - dense_2_acc_19: 1.0000 - dense_2_acc_20: 1.0000 - dense_2_acc_21: 1.0000 - dense_2_acc_22: 1.0000 - dense_2_acc_23: 1.0000 - dense_2_acc_24: 1.0000 - dense_2_acc_25: 1.0000 - dense_2_acc_26: 1.0000 - dense_2_acc_27: 1.0000 - dense_2_acc_28: 1.0000 - dense_2_acc_29: 1.0000 - dense_2_acc_30: 0.0167 Epoch 67/100 60/60 [==============================] - 0s - loss: 7.7812 - dense_2_loss_1: 3.8548 - dense_2_loss_2: 1.5375 - dense_2_loss_3: 0.5588 - dense_2_loss_4: 0.2250 - dense_2_loss_5: 0.1336 - dense_2_loss_6: 0.1022 - dense_2_loss_7: 0.0784 - dense_2_loss_8: 0.0650 - dense_2_loss_9: 0.0659 - dense_2_loss_10: 0.0554 - dense_2_loss_11: 0.0573 - dense_2_loss_12: 0.0534 - dense_2_loss_13: 0.0488 - dense_2_loss_14: 0.0535 - dense_2_loss_15: 0.0564 - dense_2_loss_16: 0.0578 - dense_2_loss_17: 0.0552 - dense_2_loss_18: 0.0503 - dense_2_loss_19: 0.0547 - dense_2_loss_20: 0.0596 - dense_2_loss_21: 0.0621 - dense_2_loss_22: 0.0601 - dense_2_loss_23: 0.0564 - dense_2_loss_24: 0.0562 - dense_2_loss_25: 0.0613 - dense_2_loss_26: 0.0555 - dense_2_loss_27: 0.0653 - dense_2_loss_28: 0.0661 - dense_2_loss_29: 0.0746 - dense_2_loss_30: 0.0000e+00 - dense_2_acc_1: 0.1000 - dense_2_acc_2: 0.5500 - dense_2_acc_3: 0.8667 - dense_2_acc_4: 0.9833 - dense_2_acc_5: 1.0000 - dense_2_acc_6: 1.0000 - dense_2_acc_7: 1.0000 - dense_2_acc_8: 1.0000 - dense_2_acc_9: 1.0000 - dense_2_acc_10: 1.0000 - dense_2_acc_11: 1.0000 - dense_2_acc_12: 1.0000 - dense_2_acc_13: 1.0000 - dense_2_acc_14: 1.0000 - dense_2_acc_15: 1.0000 - dense_2_acc_16: 1.0000 - dense_2_acc_17: 1.0000 - dense_2_acc_18: 1.0000 - dense_2_acc_19: 1.0000 - dense_2_acc_20: 1.0000 - dense_2_acc_21: 1.0000 - dense_2_acc_22: 1.0000 - dense_2_acc_23: 1.0000 - dense_2_acc_24: 1.0000 - dense_2_acc_25: 1.0000 - dense_2_acc_26: 1.0000 - dense_2_acc_27: 1.0000 - dense_2_acc_28: 1.0000 - dense_2_acc_29: 1.0000 - dense_2_acc_30: 0.0167 Epoch 68/100 60/60 [==============================] - 0s - loss: 7.6714 - dense_2_loss_1: 3.8513 - dense_2_loss_2: 1.5171 - dense_2_loss_3: 0.5458 - dense_2_loss_4: 0.2170 - dense_2_loss_5: 0.1277 - dense_2_loss_6: 0.0983 - dense_2_loss_7: 0.0751 - dense_2_loss_8: 0.0624 - dense_2_loss_9: 0.0632 - dense_2_loss_10: 0.0530 - dense_2_loss_11: 0.0555 - dense_2_loss_12: 0.0514 - dense_2_loss_1 154e8 3: 0.0466 - dense_2_loss_14: 0.0520 - dense_2_loss_15: 0.0537 - dense_2_loss_16: 0.0554 - dense_2_loss_17: 0.0529 - dense_2_loss_18: 0.0483 - dense_2_loss_19: 0.0523 - dense_2_loss_20: 0.0573 - dense_2_loss_21: 0.0594 - dense_2_loss_22: 0.0580 - dense_2_loss_23: 0.0538 - dense_2_loss_24: 0.0539 - dense_2_loss_25: 0.0584 - dense_2_loss_26: 0.0536 - dense_2_loss_27: 0.0627 - dense_2_loss_28: 0.0638 - dense_2_loss_29: 0.0716 - dense_2_loss_30: 0.0000e+00 - dense_2_acc_1: 0.1000 - dense_2_acc_2: 0.5500 - dense_2_acc_3: 0.8667 - dense_2_acc_4: 1.0000 - dense_2_acc_5: 1.0000 - dense_2_acc_6: 1.0000 - dense_2_acc_7: 1.0000 - dense_2_acc_8: 1.0000 - dense_2_acc_9: 1.0000 - dense_2_acc_10: 1.0000 - dense_2_acc_11: 1.0000 - dense_2_acc_12: 1.0000 - dense_2_acc_13: 1.0000 - dense_2_acc_14: 1.0000 - dense_2_acc_15: 1.0000 - dense_2_acc_16: 1.0000 - dense_2_acc_17: 1.0000 - dense_2_acc_18: 1.0000 - dense_2_acc_19: 1.0000 - dense_2_acc_20: 1.0000 - dense_2_acc_21: 1.0000 - dense_2_acc_22: 1.0000 - dense_2_acc_23: 1.0000 - dense_2_acc_24: 1.0000 - dense_2_acc_25: 1.0000 - dense_2_acc_26: 1.0000 - dense_2_acc_27: 1.0000 - dense_2_acc_28: 1.0000 - dense_2_acc_29: 1.0000 - dense_2_acc_30: 0.0167 Epoch 69/100 60/60 [==============================] - 0s - loss: 7.5665 - dense_2_loss_1: 3.8479 - dense_2_loss_2: 1.4976 - dense_2_loss_3: 0.5334 - dense_2_loss_4: 0.2090 - dense_2_loss_5: 0.1226 - dense_2_loss_6: 0.0939 - dense_2_loss_7: 0.0721 - dense_2_loss_8: 0.0599 - dense_2_loss_9: 0.0606 - dense_2_loss_10: 0.0508 - dense_2_loss_11: 0.0526 - dense_2_loss_12: 0.0493 - dense_2_loss_13: 0.0450 - dense_2_loss_14: 0.0488 - dense_2_loss_15: 0.0526 - dense_2_loss_16: 0.0529 - dense_2_loss_17: 0.0510 - dense_2_loss_18: 0.0469 - dense_2_loss_19: 0.0499 - dense_2_loss_20: 0.0552 - dense_2_loss_21: 0.0569 - dense_2_loss_22: 0.0549 - dense_2_loss_23: 0.0521 - dense_2_loss_24: 0.0522 - dense_2_loss_25: 0.0548 - dense_2_loss_26: 0.0510 - dense_2_loss_27: 0.0617 - dense_2_loss_28: 0.0621 - dense_2_loss_29: 0.0688 - dense_2_loss_30: 0.0000e+00 - dense_2_acc_1: 0.1000 - dense_2_acc_2: 0.5500 - dense_2_acc_3: 0.8667 - dense_2_acc_4: 1.0000 - dense_2_acc_5: 1.0000 - dense_2_acc_6: 1.0000 - dense_2_acc_7: 1.0000 - dense_2_acc_8: 1.0000 - dense_2_acc_9: 1.0000 - dense_2_acc_10: 1.0000 - dense_2_acc_11: 1.0000 - dense_2_acc_12: 1.0000 - dense_2_acc_13: 1.0000 - dense_2_acc_14: 1.0000 - dense_2_acc_15: 1.0000 - dense_2_acc_16: 1.0000 - dense_2_acc_17: 1.0000 - dense_2_acc_18: 1.0000 - dense_2_acc_19: 1.0000 - dense_2_acc_20: 1.0000 - dense_2_acc_21: 1.0000 - dense_2_acc_22: 1.0000 - dense_2_acc_23: 1.0000 - dense_2_acc_24: 1.0000 - dense_2_acc_25: 1.0000 - dense_2_acc_26: 1.0000 - dense_2_acc_27: 1.0000 - dense_2_acc_28: 1.0000 - dense_2_acc_29: 1.0000 - dense_2_acc_30: 0.0167 Epoch 70/100 60/60 [==============================] - 0s - loss: 7.4674 - dense_2_loss_1: 3.8446 - dense_2_loss_2: 1.4776 - dense_2_loss_3: 0.5205 - dense_2_loss_4: 0.2018 - dense_2_loss_5: 0.1177 - dense_2_loss_6: 0.0903 - dense_2_loss_7: 0.0694 - dense_2_loss_8: 0.0577 - dense_2_loss_9: 0.0583 - dense_2_loss_10: 0.0485 - dense_2_loss_11: 0.0508 - dense_2_loss_12: 0.0476 - dense_2_loss_13: 0.0431 - dense_2_loss_14: 0.0473 - dense_2_loss_15: 0.0503 - dense_2_loss_16: 0.0507 - dense_2_loss_17: 0.0491 - dense_2_loss_18: 0.0452 - dense_2_loss_19: 0.0480 - dense_2_loss_20: 0.0529 - dense_2_loss_21: 0.0547 - dense_2_loss_22: 0.0530 - dense_2_loss_23: 0.0504 - dense_2_loss_24: 0.0501 - dense_2_loss_25: 0.0525 - dense_2_loss_26: 0.0492 - dense_2_loss_27: 0.0598 - dense_2_loss_28: 0.0598 - dense_2_loss_29: 0.0664 - dense_2_loss_30: 0.0000e+00 - dense_2_acc_1: 0.1000 - dense_2_acc_2: 0.5500 - dense_2_acc_3: 0.8667 - dense_2_acc_4: 1.0000 - dense_2_acc_5: 1.0000 - dense_2_acc_6: 1.0000 - dense_2_acc_7: 1.0000 - dense_2_acc_8: 1.0000 - dense_2_acc_9: 1.0000 - dense_2_acc_10: 1.0000 - dense_2_acc_11: 1.0000 - dense_2_acc_12: 1.0000 - dense_2_acc_13: 1.0000 - dense_2_acc_14: 1.0000 - dense_2_acc_15: 1.0000 - dense_2_acc_16: 1.0000 - dense_2_acc_17: 1.0000 - dense_2_acc_18: 1.0000 - dense_2_acc_19: 1.0000 - dense_2_acc_20: 1.0000 - dense_2_acc_21: 1.0000 - dense_2_acc_22: 1.0000 - dense_2_acc_23: 1.0000 - dense_2_acc_24: 1.0000 - dense_2_acc_25: 1.0000 - dense_2_acc_26: 1.0000 - dense_2_acc_27: 1.0000 - dense_2_acc_28: 1.0000 - dense_2_acc_29: 1.0000 - dense_2_acc_30: 0.0167 Epoch 71/100 60/60 [==============================] - 0s - loss: 7.3731 - dense_2_loss_1: 3.8413 - dense_2_loss_2: 1.4596 - dense_2_loss_3: 0.5088 - dense_2_loss_4: 0.1942 - dense_2_loss_5: 0.1132 - dense_2_loss_6: 0.0870 - dense_2_loss_7: 0.0668 - dense_2_loss_8: 0.0556 - dense_2_loss_9: 0.0560 - dense_2_loss_10: 0.0467 - dense_2_loss_11: 0.0494 - dense_2_loss_12: 0.0458 - dense_2_loss_13: 0.0415 - dense_2_loss_14: 0.0459 - dense_2_loss_15: 0.0482 - dense_2_loss_16: 0.0490 - dense_2_loss_17: 0.0471 - dense_2_loss_18: 0.0431 - dense_2_loss_19: 0.0463 - dense_2_loss_20: 0.0507 - dense_2_loss_21: 0.0527 - dense_2_loss_22: 0.0513 - dense_2_loss_23: 0.0485 - dense_2_loss_24: 0.0478 - dense_2_loss_25: 0.0510 - dense_2_loss_26: 0.0479 - dense_2_loss_27: 0.0568 - dense_2_loss_28: 0.0564 - dense_2_loss_29: 0.0642 - dense_2_loss_30: 0.0000e+00 - dense_2_acc_1: 0.1000 - dense_2_acc_2: 0.5500 - dense_2_acc_3: 0.8667 - dense_2_acc_4: 1.0000 - dense_2_acc_5: 1.0000 - dense_2_acc_6: 1.0000 - dense_2_acc_7: 1.0000 - dense_2_acc_8: 1.0000 - dense_2_acc_9: 1.0000 - dense_2_acc_10: 1.0000 - dense_2_acc_11: 1.0000 - dense_2_acc_12: 1.0000 - dense_2_acc_13: 1.0000 - dense_2_acc_14: 1.0000 - dense_2_acc_15: 1.0000 - dense_2_acc_16: 1.0000 - dense_2_acc_17: 1.0000 - dense_2_acc_18: 1.0000 - dense_2_acc_19: 1.0000 - dense_2_acc_20: 1.0000 - dense_2_acc_21: 1.0000 - dense_2_acc_22: 1.0000 - dense_2_acc_23: 1.0000 - dense_2_acc_24: 1.0000 - dense_2_acc_25: 1.0000 - dense_2_acc_26: 1.0000 - dense_2_acc_27: 1.0000 - dense_2_acc_28: 1.0000 - dense_2_acc_29: 1.0000 - dense_2_acc_30: 0.0167 Epoch 72/100 60/60 [==============================] - 0s - loss: 7.2849 - dense_2_loss_1: 3.8381 - dense_2_loss_2: 1.4410 - dense_2_loss_3: 0.4972 - dense_2_loss_4: 0.1883 - dense_2_loss_5: 0.1091 - dense_2_loss_6: 0.0839 - dense_2_loss_7: 0.0645 - dense_2_loss_8: 0.0537 - dense_2_loss_9: 0.0540 - dense_2_loss_10: 0.0451 - dense_2_loss_11: 0.0476 - dense_2_loss_12: 0.0441 - dense_2_loss_13: 0.0400 - dense_2_loss_14: 0.0443 - dense_2_loss_15: 0.0466 - dense_2_loss_16: 0.0473 - dense_2_loss_17: 0.0454 - dense_2_loss_18: 0.0413 - dense_2_loss_19: 0.0448 - dense_2_loss_20: 0.0489 - dense_2_loss_21: 0.0509 - dense_2_loss_22: 0.0496 - dense_2_loss_23: 0.0466 - dense_2_loss_24: 0.0458 - dense_2_loss_25: 0.0501 - dense_2_loss_26: 0.0467 - dense_2_loss_27: 0.0539 - dense_2_loss_28: 0.0537 - dense_2_loss_29: 0.0624 - dense_2_loss_30: 0.0000e+00 - dense_2_acc_1: 0.1000 - dense_2_acc_2: 0.6000 - dense_2_acc_3: 0.9000 - dense_2_acc_4: 1.0000 - dense_2_acc_5: 1.0000 - dense_2_acc_6: 1.0000 - dense_2_acc_7: 1.0000 - dense_2_acc_8: 1.0000 - dense_2_acc_9: 1.0000 - dense_2_acc_10: 1.0000 - dense_2_acc_11: 1.0000 - dense_2_acc_12: 1.0000 - dense_2_acc_13: 1.0000 - dense_2_acc_14: 1.0000 - dense_2_acc_15: 1.0000 - dense_2_acc_16: 1.0000 - dense_2_acc_17: 1.0000 - dense_2_acc_18: 1.0000 - dense_2_acc_19: 1.0000 - dense_2_acc_20: 1.0000 - dense_2_acc_21: 1.0000 - dense_2_acc_22: 1.0000 - dense_2_acc_23: 1.0000 - dense_2_acc_24: 1.0000 - dense_2_acc_25: 1.0000 - dense_2_acc_26: 1.0000 - dense_2_acc_27: 1.0000 - dense_2_acc_28: 1.0000 - dense_2_acc_29: 1.0000 - dense_2_acc_30: 0.0167 Epoch 73/100 60/60 [==============================] - 0s - loss: 7.2019 - dense_2_loss_1: 3.8347 - dense_2_loss_2: 1.4238 - dense_2_loss_3: 0.4867 - dense_2_loss_4: 0.1821 - dense_2_loss_5: 0.1056 - dense_2_loss_6: 0.0810 - dense_2_loss_7: 0.0625 - dense_2_loss_8: 0.0520 - dense_2_loss_9: 0.0522 - dense_2_loss_10: 0.0435 - dense_2_loss_11: 0.0458 - dense_2_loss_12: 0.0427 - dense_2_loss_13: 0.0388 - dense_2_loss_14: 0.0425 - dense_2_loss_15: 0.0453 - dense_2_loss_16: 0.0457 - dense_2_loss_17: 0.0439 - dense_2_loss_18: 0.0398 - dense_2_loss_19: 0.0434 - dense_2_loss_20: 0.0470 - dense_2_loss_21: 0.0492 - dense_2_loss_22: 0.0477 - dense_2_loss_23: 0.0450 - dense_2_loss_24: 0.0443 - dense_2_loss_25: 0.0477 - dense_2_loss_26: 0.0446 - dense_2_loss_27: 0.0526 - dense_2_loss_28: 0.0525 - dense_2_loss_29: 0.0595 - dense_2_loss_30: 0.0000e+00 - dense_2_acc_1: 0.1000 - dense_2_acc_2: 0.6000 - dense_2_acc_3: 0.9000 - dense_2_acc_4: 1.0000 - dense_2_acc_5: 1.0000 - dense_2_acc_6: 1.0000 - dense_2_acc_7: 1.0000 - dense_2_acc_8: 1.0000 - dense_2_acc_9: 1.0000 - dense_2_acc_10: 1.0000 - dense_2_acc_11: 1.0000 - dense_2_acc_12: 1.0000 - dense_2_acc_13: 1.0000 - dense_2_acc_14: 1.0000 - dense_2_acc_15: 1.0000 - dense_2_acc_16: 1.0000 - dense_2_acc_17: 1.0000 - dense_2_acc_18: 1.0000 - dense_2_acc_19: 1.0000 - dense_2_acc_20: 1.0000 - dense_2_acc_21: 1.0000 - dense_2_acc_22: 1.0000 - dense_2_acc_23: 1.0000 - dense_2_acc_24: 1.0000 - dense_2_acc_25: 1.0000 - dense_2_acc_26: 1.0000 - dense_2_acc_27: 1.0000 - dense_2_acc_28: 1.0000 - dense_2_acc_29: 1.0000 - dense_2_acc_30: 0.0167 Epoch 74/100 60/60 [==============================] - 0s - loss: 7.1201 - dense_2_loss_1: 3.8313 - dense_2_loss_2: 1.4073 - dense_2_loss_3: 0.4755 - dense_2_loss_4: 0.1755 - dense_2_loss_5: 0.1016 - dense_2_loss_6: 0.0778 - dense_2_loss_7: 0.0604 - dense_2_loss_8: 0.0502 - dense_2_loss_9: 0.0502 - dense_2_loss_10: 0.0420 - dense_2_loss_11: 0.0440 - dense_2_loss_12: 0.0413 - dense_2_loss_13: 0.0375 - dense_2_loss_14: 0.0410 - dense_2_loss_15: 0.0438 - dense_2_loss_16: 0.0441 - dense_2_loss_17: 0.0425 - dense_2_loss_18: 0.0387 - dense_2_loss_19: 0.0418 - dense_2_loss_20: 0.0452 - dense_2_loss_21: 0.0475 - dense_2_loss_22: 0.0458 - dense_2_loss_23: 0.0436 - dense_2_loss_24: 0.0430 - dense_2_loss_25: 0.0451 - dense_2_loss_26: 0.0427 - dense_2_loss_27: 0.0522 - dense_2_loss_28: 0.0518 - dense_2_loss_29: 0.0570 - dense_2_loss_30: 0.0000e+00 - dense_2_acc_1: 0.1000 - dense_2_acc_2: 0.6000 - dense_2_acc_3: 0.9000 - dense_2_acc_4: 1.0000 - dense_2_acc_5: 1.0000 - dense_2_acc_6: 1.0000 - dense_2_acc_7: 1.0000 - dense_2_acc_8: 1.0000 - dense_2_acc_9: 1.0000 - dense_2_acc_10: 1.0000 - dense_2_acc_11: 1.0000 - dense_2_acc_12: 1.0000 - dense_2_acc_13: 1.0000 - dense_2_acc_14: 1.0000 - dense_2_acc_15: 1.0000 - dense_2_acc_16: 1.0000 - dense_2_acc_17: 1.0000 - dense_2_acc_18: 1.0000 - dense_2_acc_19: 1.0000 - dense_2_acc_20: 1.0000 - dense_2_acc_21: 1.0000 - dense_2_acc_22: 1.0000 - dense_2_acc_23: 1.0000 - dense_2_acc_24: 1.0000 - dense_2_acc_25: 1.0000 - dense_2_acc_26: 1.0000 - dense_2_acc_27: 1.0000 - dense_2_acc_28: 1.0000 - dense_2_acc_29: 1.0000 - dense_2_acc_30: 0.0167 Epoch 75/100 60/60 [==============================] - 0s - loss: 7.0455 - dense_2_loss_1: 3.8284 - dense_2_loss_2: 1.3909 - dense_2_loss_3: 0.4650 - dense_2_loss_4: 0.1699 - dense_2_loss_5: 0.0981 - dense_2_loss_6: 0.0753 - dense_2_loss_7: 0.0585 - dense_2_loss_8: 0.0487 - dense_2_loss_9: 0.0486 - dense_2_loss_10: 0.0405 - dense_2_loss_11: 0.0426 - dense_2_loss_12: 0.0400 - dense_2_loss_13: 0.0361 - dense_2_loss_14: 0.0398 - dense_2_loss_15: 0.0421 - dense_2_loss_16: 0.0428 - dense_2_loss_17: 0.0410 - dense_2_loss_18: 0.0375 - dense_2_loss_19: 0.0405 - dense_2_loss_20: 0.0437 - dense_2_loss_21: 0.0460 - dense_2_loss_22: 0.0444 - dense_2_loss_23: 0.0422 - dense_2_loss_24: 0.0417 - dense_2_loss_25: 0.0438 - dense_2_loss_26: 0.0413 - dense_2_loss_27: 0.0505 - dense_2_loss_28: 0.0502 - dense_2_loss_29: 0.0552 - dense_2_loss_30: 0.0000e+00 - dense_2_acc_1: 0.1000 - dense_2_acc_2: 0.6167 - dense_2_acc_3: 0.9000 - dense_2_acc_4: 1.0000 - dense_2_acc_5: 1.0000 - dense_2_acc_6: 1.0000 - dense_2_acc_7: 1.0000 - dense_2_acc_8: 1.0000 - dense_2_acc_9: 1.0000 - dense_2_acc_10: 1.0000 - dense_2_acc_11: 1.0000 - dense_2_acc_12: 1.0000 - dense_2_acc_13: 1.0000 - dense_2_acc_14: 1.0000 - dense_2_acc_15: 1.0000 - dense_2_acc_16: 1.0000 - dense_2_acc_17: 1.0000 - dense_2_acc_18: 1.0000 - dense_2_acc_19: 1.0000 - dense_2_acc_20: 1.0000 - dense_2_acc_21: 1.0000 - dense_2_acc_22: 1.0000 - dense_2_acc_23: 1.0000 - dense_2_acc_24: 1.0000 - dense_2_acc_25: 1.0000 - dense_2_acc_26: 1.0000 - dense_2_acc_27: 1.0000 - dense_2_acc_28: 1.0000 - dense_2_acc_29: 1.0000 - dense_2_acc_30: 0.0167 Epoch 76/100 60/60 [==============================] - 0s - loss: 6.9724 - dense_2_loss_1: 3.8251 - dense_2_loss_2: 1.3748 - dense_2_loss_3: 0.4548 - dense_2_loss_4: 0.1652 - dense_2_loss_5: 0.0949 - dense_2_loss_6: 0.0728 - dense_2_loss_7: 0.0566 - dense_2_loss_8: 0.0471 - dense_2_loss_9: 0.0470 - dense_2_loss_10: 0.0393 - dense_2_loss_11: 0.0415 - dense_2_loss_12: 0.0388 - dense_2_loss_13: 0.0351 - dense_2_loss_14: 0.0387 - dense_2_loss_15: 0.0406 - dense_2_loss_16: 0.0416 - dense_2_loss_17: 0.0396 - dense_2_loss_18: 0.0361 - dense_2_loss_19: 0.0392 - dense_2_loss_20: 0.0424 - dense_2_loss_21: 0.0445 - dense_2_loss_22: 0.0430 - dense_2_loss_23: 0.0406 - dense_2_loss_24: 0.0402 - dense_2_loss_25: 0.0437 - dense_2_loss_26: 0.0406 - dense_2_loss_27: 0.0473 - dense_2_loss_28: 0.0476 - dense_2_loss_29: 0.0536 - dense_2_loss_30: 0.0000e+00 - dense_2_acc_1: 0.1000 - dense_2_acc_2: 0.6167 - dense_2_acc_3: 0.9000 - dense_2_acc_4: 1.0000 - dense_2_acc_5: 1.0000 - dense_2_acc_6: 1.0000 - dense_2_acc_7: 1.0000 - dense_2_acc_8: 1.0000 - dense_2_acc_9: 1.0000 - dense_2_acc_10: 1.0000 - dense_2_acc_11: 1.0000 - dense_2_acc_12: 1.0000 - dense_2_acc_13: 1.0000 - dense_2_acc_14: 1.0000 - dense_2_acc_15: 1.0000 - dense_2_acc_16: 1.0000 - dense_2_acc_17: 1.0000 - dense_2_acc_18: 1.0000 - dense_2_acc_19: 1.0000 - dense_2_acc_20: 1.0000 - dense_2_acc_21: 1.0000 - dense_2_acc_22: 1.0000 - dense_2_acc_23: 1.0000 - dense_2_acc_24: 1.0000 - dense_2_acc_25: 1.0000 - dense_2_acc_26: 1.0000 - dense_2_acc_27: 1.0000 - dense_2_acc_28: 1.0000 - dense_2_acc_29: 1.0000 - dense_2_acc_30: 0.0167 Epoch 77/100 60/60 [==============================] - 0s - loss: 6.9051 - dense_2_loss_1: 3.8221 - dense_2_loss_2: 1.3597 - dense_2_loss_3: 0.4453 - dense_2_loss_4: 0.1608 - dense_2_loss_5: 0.0923 - dense_2_loss_6: 0.0708 - dense_2_loss_7: 0.0550 - dense_2_loss_8: 0.0459 - dense_2_loss_9: 0.0456 - dense_2_loss_10: 0.0381 - dense_2_loss_11: 0.0403 - dense_2_loss_12: 0.0377 - dense_2_loss_13: 0.0340 - dense_2_loss_14: 0.0375 - dense_2_loss_15: 0.0394 - dense_2_loss_16: 0.0403 - dense_2_loss_17: 0.0383 - dense_2_loss_18: 0.0349 - dense_2_loss_19: 0.0379 - dense_2_loss_20: 0.0411 - dense_2_loss_21: 0.0430 - dense_2_loss_22: 0.0415 - dense_2_loss_23: 0.0393 - dense_2_loss_24: 0.0389 - dense_2_loss_25: 0.0420 - dense_2_loss_26: 0.0393 - dense_2_loss_27: 0.0460 - dense_2_loss_28: 0.0462 - dense_2_loss_29: 0.0519 - dense_2_loss_30: 0.0000e+00 - dense_2_acc_1: 0.1000 - dense_2_acc_2: 0.6167 - dense_2_acc_3: 0.9000 - dense_2_acc_4: 1.0000 - dense_2_acc_5: 1.0000 - dense_2_acc_6: 1.0000 - dense_2_acc_7: 1.0000 - dense_2_acc_8: 1.0000 - dense_2_acc_9: 1.0000 - dense_2_acc_10: 1.0000 - dense_2_acc_11: 1.0000 - dense_2_acc_12: 1.0000 - dense_2_acc_13: 1.0000 - dense_2_acc_14: 1.0000 - dense_2_acc_15: 1.0000 - dense_2_acc_16: 1.0000 - dense_2_acc_17: 1.0000 - dense_2_acc_18: 1.0000 - dense_2_acc_19: 1.0000 - dense_2_acc_20: 1.0000 - dense_2_acc_21: 1.0000 - dense_2_acc_22: 1.0000 - dense_2_acc_23: 1.0000 - dense_2_acc_24: 1.0000 - dense_2_acc_25: 1.0000 - dense_2_acc_26: 1.0000 - dense_2_acc_27: 1.0000 - dense_2_acc_28: 1.0000 - dense_2_acc_29: 1.0000 - dense_2_acc_30: 0.0167 Epoch 78/100 60/60 [==============================] - 0s - loss: 6.8380 - dense_2_loss_1: 3.8188 - dense_2_loss_2: 1.3446 - dense_2_loss_3: 0.4357 - dense_2_loss_4: 0.1560 - dense_2_loss_5: 0.0895 - dense_2_loss_6: 0.0685 - dense_2_loss_7: 0.0533 - dense_2_loss_8: 0.0445 - dense_2_loss_9: 0.0441 - dense_2_loss_10: 0.0369 - dense_2_loss_11: 0.0389 - dense_2_loss_12: 0.0366 - dense_2_loss_13: 0.0331 - dense_2_loss_14: 0.0360 - dense_2_loss_15: 0.0385 - dense_2_loss_16: 0.0392 - dense_2_loss_17: 0.0372 - dense_2_loss_18: 0.0339 - dense_2_loss_19: 0.0368 - dense_2_loss_20: 0.0398 - dense_2_loss_21: 0.0415 - dense_2_loss_22: 0.0401 - dense_2_loss_23: 0.0383 - dense_2_loss_24: 0.0379 - dense_2_loss_25: 0.0403 - dense_2_loss_26: 0.0380 - dense_2_loss_27: 0.0452 - dense_2_loss_28: 0.0449 - dense_2_loss_29: 0.0504 - dense_2_loss_30: 0.0000e+00 - dense_2_acc_1: 0.1000 - dense_2_acc_2: 0.6333 - dense_2_acc_3: 0.9000 - dense_2_acc_4: 1.0000 - dense_2_acc_5: 1.0000 - dense_2_acc_6: 1.0000 - dense_2_acc_7: 1.0000 - dense_2_acc_8: 1.0000 - dense_2_acc_9: 1.0000 - dense_2_acc_10: 1.0000 - dense_2_acc_11: 1.0000 - dense_2_acc_12: 1.0000 - dense_2_acc_13: 1.0000 - dense_2_acc_14: 1.0000 - dense_2_acc_15: 1.0000 - dense_2_acc_16: 1.0000 - dense_2_acc_17: 1.0000 - dense_2_acc_18: 1.0000 - dense_2_acc_19: 1.0000 - dense_2_acc_20: 1.0000 - dense_2_acc_21: 1.0000 - dense_2_acc_22: 1.0000 - dense_2_acc_23: 1.0000 - dense_2_acc_24: 1.0000 - dense_2_acc_25: 1.0000 - dense_2_acc_26: 1.0000 - dense_2_acc_27: 1.0000 - dense_2_acc_28: 1.0000 - dense_2_acc_29: 1.0000 - dense_2_acc_30: 0.0167 Epoch 79/100 60/60 [==============================] - 0s - loss: 6.7730 - dense_2_loss_1: 3.8159 - dense_2_loss_2: 1.3299 - dense_2_loss_3: 0.4253 - dense_2_loss_4: 0.1512 - dense_2_loss_5: 0.0865 - dense_2_loss_6: 0.0663 - dense_2_loss_7: 0.0516 - dense_2_loss_8: 0.0430 - dense_2_loss_9: 0.0427 - dense_2_loss_10: 0.0358 - dense_2_loss_11: 0.0377 - dense_2_loss_12: 0.0355 - dense_2_loss_13: 0.0321 - dense_2_loss_14: 0.0349 - dense_2_loss_15: 0.0374 - dense_2_loss_16: 0.0381 - dense_2_loss_17: 0.0360 - dense_2_loss_18: 0.0330 - dense_2_loss_19: 0.0356 - dense_2_loss_20: 0.0386 - dense_2_loss_21: 0.0404 - dense_2_loss_22: 0.0388 - dense_2_loss_23: 0.0372 - dense_2_loss_24: 0.0370 - dense_2_loss_25: 0.0386 - dense_2_loss_26: 0.0366 - dense_2_loss_27: 0.0446 - dense_2_loss_28: 0.0439 - dense_2_loss_29: 0.0487 - dense_2_loss_30: 0.0000e+00 - dense_2_acc_1: 0.1000 - dense_2_acc_2: 0.6333 - dense_2_acc_3: 0.9000 - dense_2_acc_4: 1.0000 - dense_2_acc_5: 1.0000 - dense_2_acc_6: 1.0000 - dense_2_acc_7: 1.0000 - dense_2_acc_8: 1.0000 - dense_2_acc_9: 1.0000 - dense_2_acc_10: 1.0000 - dense_2_acc_11: 1.0000 - dense_2_acc_12: 1.0000 - dense_2_acc_13: 1.0000 - dense_2_acc_14: 1.0000 - dense_2_acc_15: 1.0000 - dense_2_acc_16: 1.0000 - dense_2_acc_17: 1.0000 - dense_2_acc_18: 1.0000 - dense_2_acc_19: 1.0000 - dense_2_acc_20: 1.0000 - dense_2_acc_21: 1.0000 - dense_2_acc_22: 1.0000 - dense_2_acc_23: 1.0000 - dense_2_acc_24: 1.0000 - dense_2_acc_25: 1.0000 - dense_2_acc_26: 1.0000 - dense_2_acc_27: 1.0000 - dense_2_acc_28: 1.0000 - dense_2_acc_29: 1.0000 - dense_2_acc_30: 0.0167 Epoch 80/100 60/60 [==============================] - 0s - loss: 6.7127 - dense_2_loss_1: 3.8127 - dense_2_loss_2: 1.3156 - dense_2_loss_3: 0.4170 - dense_2_loss_4: 0.1474 - dense_2_loss_5: 0.0844 - dense_2_loss_6: 0.0646 - dense_2_loss_7: 0.0503 - dense_2_loss_8: 0.0419 - dense_2_loss_9: 0.0415 - dense_2_loss_10: 0.0348 - dense_2_loss_11: 0.0367 - dense_2_loss_12: 0.0345 - dense_2_loss_13: 0.0311 - dense_2_loss_14: 0.0341 - dense_2_loss_15: 0.0362 - dense_2_loss_16: 0.0371 - dense_2_loss_17: 0.0349 - dense_2_loss_18: 0.0320 - dense_2_loss_19: 0.0345 - dense_2_loss_20: 0.0374 - dense_2_loss_21: 0.0392 - dense_2_loss_22: 0.0376 - dense_2_loss_23: 0.0360 - dense_2_loss_24: 0.0359 - dense_2_loss_25: 0.0379 - dense_2_loss_26: 0.0354 - dense_2_loss_27: 0.0428 - dense_2_loss_28: 0.0424 - dense_2_loss_29: 0.0469 - dense_2_loss_30: 0.0000e+00 - dense_2_acc_1: 0.1000 - dense_2_acc_2: 0.6333 - dense_2_acc_3: 0.9000 - dense_2_acc_4: 1.0000 - dense_2_acc_5: 1.0000 - dense_2_acc_6: 1.0000 - dense_2_acc_7: 1.0000 - dense_2_acc_8: 1.0000 - dense_2_acc_9: 1.0000 - dense_2_acc_10: 1.0000 - dense_2_acc_11: 1.0000 - dense_2_acc_12: 1.0000 - dense_2_acc_13: 1.0000 - dense_2_acc_14: 1.0000 - dense_2_acc_15: 1.0000 - dense_2_acc_16: 1.0000 - dense_2_acc_17: 1.0000 - dense_2_acc_18: 1.0000 - dense_2_acc_19: 1.0000 - dense_2_acc_20: 1.0000 - dense_2_acc_21: 1.0000 - dense_2_acc_22: 1.0000 - dense_2_acc_23: 1.0000 - dense_2_acc_24: 1.0000 - dense_2_acc_25: 1.0000 - dense_2_acc_26: 1.0000 - dense_2_acc_27: 1.0000 - dense_2_acc_28: 1.0000 - dense_2_acc_29: 1.0000 - dense_2_acc_30: 0.0167 Epoch 81/100 60/60 [==============================] - 0s - loss: 6.6540 - dense_2_loss_1: 3.8097 - dense_2_loss_2: 1.3018 - dense_2_loss_3: 0.4080 - dense_2_loss_4: 0.1433 - dense_2_loss_5: 0.0817 - dense_2_loss_6: 0.0626 - dense_2_loss_7: 0.0489 - dense_2_loss_8: 0.0405 - dense_2_loss_9: 0.0402 - dense_2_loss_10: 0.0337 - dense_2_loss_11: 0.0359 - dense_2_loss_12: 0.0336 - dense_2_loss_13: 0.0301 - dense_2_loss_14: 0.0334 - dense_2_loss_15: 0.0349 - dense_2_loss_16: 0.0361 - dense_2_loss_17: 0.0338 - dense_2_loss_18: 0.0312 - dense_2_loss_19: 0.0335 - dense_2_loss_20: 0.0364 - dense_2_loss_21: 0.0381 - dense_2_loss_22: 0.0367 - dense_2_loss_23: 0.0349 - dense_2_loss_24: 0.0349 - dense_2_loss_25: 0.0370 - dense_2_loss_26: 0.0346 - dense_2_loss_27: 0.0416 - dense_2_loss_28: 0.0413 - dense_2_loss_29: 0.0458 - dense_2_loss_30: 0.0000e+00 - dense_2_acc_1: 0.1000 - dense_2_acc_2: 0.6333 - dense_2_acc_3: 0.9000 - dense_2_acc_4: 1.0000 - dense_2_acc_5: 1.0000 - dense_2_acc_6: 1.0000 - dense_2_acc_7: 1.0000 - dense_2_acc_8: 1.0000 - dense_2_acc_9: 1.0000 - dense_2_acc_10: 1.0000 - dense_2_acc_11: 1.0000 - dense_2_acc_12: 1.0000 - dense_2_acc_13: 1.0000 - dense_2_acc_14: 1.0000 - dense_2_acc_15: 1.0000 - dense_2_acc_16: 1.0000 - dense_2_acc_17: 1.0000 - dense_2_acc_18: 1.0000 - dense_2_acc_19: 1.0000 - dense_2_acc_20: 1.0000 - dense_2_acc_21: 1.0000 - dense_2_acc_22: 1.0000 - dense_2_acc_23: 1.0000 - dense_2_acc_24: 1.0000 - dense_2_acc_25: 1.0000 - dense_2_acc_26: 1.0000 - dense_2_acc_27: 1.0000 - dense_2_acc_28: 1.0000 - dense_2_acc_29: 1.0000 - dense_2_acc_30: 0.0167 Epoch 82/100 60/60 [==============================] - 0s - loss: 6.5994 - dense_2_loss_1: 3.8066 - dense_2_loss_2: 1.2888 - dense_2_loss_3: 0.4002 - dense_2_loss_4: 0.1395 - dense_2_loss_5: 0.0797 - dense_2_loss_6: 0.0611 - dense_2_loss_7: 0.0476 - dense_2_loss_8: 0.0394 - dense_2_loss_9: 0.0391 - dense_2_loss_10: 0.0328 - dense_2_loss_11: 0.0349 - dense_2_loss_12: 0.0326 - dense_2_loss_13: 0.0294 - dense_2_loss_14: 0.0324 - dense_2_loss_15: 0.0341 - dense_2_loss_16: 0.0350 - dense_2_loss_17: 0.0329 - dense_2_loss_18: 0.0302 - dense_2_loss_19: 0.0327 - dense_2_loss_20: 0.0355 - dense_2_loss_21: 0.0370 - dense_2_loss_22: 0.0357 - dense_2_loss_23: 0.0339 - dense_2_loss_24: 0.0336 - dense_2_loss_25: 0.0364 - dense_2_loss_26: 0.0339 - dense_2_loss_27: 0.0399 - dense_2_loss_28: 0.0399 - dense_2_loss_29: 0.0447 - dense_2_loss_30: 0.0000e+00 - dense_2_acc_1: 0.1000 - dense_2_acc_2: 0.6333 - dense_2_acc_3: 0.9000 - dense_2_acc_4: 1.0000 - dense_2_acc_5: 1.0000 - dense_2_acc_6: 1.0000 - dense_2_acc_7: 1.0000 - dense_2_acc_8: 1.0000 - dense_2_acc_9: 1.0000 - dense_2_acc_10: 1.0000 - dense_2_acc_11: 1.0000 - dense_2_acc_12: 1.0000 - dense_2_acc_13: 1.0000 - dense_2_acc_14: 1.0000 - dense_2_acc_15: 1.0000 - dense_2_acc_16: 1.0000 - dense_2_acc_17: 1.0000 - dense_2_acc_18: 1.0000 - dense_2_acc_19: 1.0000 - dense_2_acc_20: 1.0000 - dense_2_acc_21: 1.0000 - dense_2_acc_22: 1.0000 - dense_2_acc_23: 1.0000 - dense_2_acc_24: 1.0000 - dense_2_acc_25: 1.0000 - dense_2_acc_26: 1.0000 - dense_2_acc_27: 1.0000 - dense_2_acc_28: 1.0000 - dense_2_acc_29: 1.0000 - dense_2_acc_30: 0.0167 Epoch 83/100 60/60 [==============================] - 0s - loss: 6.5432 - dense_2_loss_1: 3.8037 - dense_2_loss_2: 1.2748 - dense_2_loss_3: 0.3916 - dense_2_loss_4: 0.1356 - dense_2_loss_5: 0.0773 - dense_2_loss_6: 0.0594 - dense_2_loss_7: 0.0462 - dense_2_loss_8: 0.0382 - dense_2_loss_9: 0.0381 - dense_2_loss_10: 0.0319 - dense_2_loss_11: 0.0337 - dense_2_loss_12: 0.0318 - dense_2_loss_13: 0.0287 - dense_2_loss_14: 0.0312 - dense_2_loss_15: 0.0335 - dense_2_loss_16: 0.0338 - dense_2_loss_17: 0.0320 - dense_2_loss_18: 0.0294 - dense_2_loss_19: 0.0319 - dense_2_loss_20: 0.0345 - dense_2_loss_21: 0.0360 - dense_2_loss_22: 0.0345 - dense_2_loss_23: 0.0331 - dense_2_loss_24: 0.0326 - dense_2_loss_25: 0.0350 - dense_2_loss_26: 0.0330 - dense_2_loss_27: 0.0391 - dense_2_loss_28: 0.0389 - dense_2_loss_29: 0.0436 - dense_2_loss_30: 0.0000e+00 - dense_2_acc_1: 0.1000 - dense_2_acc_2: 0.6333 - dense_2_acc_3: 0.9000 - dense_2_acc_4: 1.0000 - dense_2_acc_5: 1.0000 - dense_2_acc_6: 1.0000 - dense_2_acc_7: 1.0000 - dense_2_acc_8: 1.0000 - dense_2_acc_9: 1.0000 - dense_2_acc_10: 1.0000 - dense_2_acc_11: 1.0000 - dense_2_acc_12: 1.0000 - dense_2_acc_13: 1.0000 - dense_2_acc_14: 1.0000 - dense_2_acc_15: 1.0000 - dense_2_acc_16: 1.0000 - dense_2_acc_17: 1.0000 - dense_2_acc_18: 1.0000 - dense_2_acc_19: 1.0000 - dense_2_acc_20: 1.0000 - dense_2_acc_21: 1.0000 - dense_2_acc_22: 1.0000 - dense_2_acc_23: 1.0000 - dense_2_acc_24: 1.0000 - dense_2_acc_25: 1.0000 - dense_2_acc_26: 1.0000 - dense_2_acc_27: 1.0000 - dense_2_acc_28: 1.0000 - dense_2_acc_29: 1.0000 - dense_2_acc_30: 0.0167 Epoch 84/100 60/60 [==============================] - 0s - loss: 6.4917 - dense_2_loss_1: 3.8007 - dense_2_loss_2: 1.2618 - dense_2_loss_3: 0.3839 - dense_2_loss_4: 0.1322 - dense_2_loss_5: 0.0753 - dense_2_loss_6: 0.0578 - dense_2_loss_7: 0.0451 - dense_2_loss_8: 0.0373 - dense_2_loss_9: 0.0371 - dense_2_loss_10: 0.0310 - dense_2_loss_11: 0.0328 - dense_2_loss_12: 0.0310 - dense_2_loss_13: 0.0279 - dense_2_loss_14: 0.0304 - dense_2_loss_15: 0.0326 - dense_2_loss_16: 0.0329 - dense_2_loss_17: 0.0312 - dense_2_loss_18: 0.0286 - dense_2_loss_19: 0.0311 - dense_2_loss_20: 0.0335 - dense_2_loss_21: 0.0350 - dense_2_loss_22: 0.0337 - dense_2_loss_23: 0.0323 - dense_2_loss_24: 0.0318 - dense_2_loss_25: 0.0339 - dense_2_loss_26: 0.0320 - dense_2_loss_27: 0.0383 - dense_2_loss_28: 0.0379 - dense_2_loss_29: 0.0425 - dense_2_loss_30: 0.0000e+00 - dense_2_acc_1: 0.1000 - dense_2_acc_2: 0.6333 - dense_2_acc_3: 0.9000 - dense_2_acc_4: 1.0000 - dense_2_acc_5: 1.0000 - dense_2_acc_6: 1.0000 - dense_2_acc_7: 1.0000 - dense_2_acc_8: 1.0000 - dense_2_acc_9: 1.0000 - dense_2_acc_10: 1.0000 - dense_2_acc_11: 1.0000 - dense_2_acc_12: 1.0000 - dense_2_acc_13: 1.0000 - dense_2_acc_14: 1.0000 - dense_2_acc_15: 1.0000 - dense_2_acc_16: 1.0000 - dense_2_acc_17: 1.0000 - dense_2_acc_18: 1.0000 - dense_2_acc_19: 1.0000 - dense_2_acc_20: 1.0000 - dense_2_acc_21: 1.0000 - dense_2_acc_22: 1.0000 - dense_2_acc_23: 1.0000 - dense_2_acc_24: 1.0000 - dense_2_acc_25: 1.0000 - dense_2_acc_26: 1.0000 - dense_2_acc_27: 1.0000 - dense_2_acc_28: 1.0000 - dense_2_acc_29: 1.0000 - dense_2_acc_30: 0.0167 Epoch 85/100 60/60 [==============================] - 0s - loss: 6.4416 - dense_2_loss_1: 3.7976 - dense_2_loss_2: 1.2499 - dense_2_loss_3: 0.3756 - dense_2_loss_4: 0.1289 - dense_2_loss_5: 0.0733 - dense_2_loss_6: 0.0564 - dense_2_loss_7: 0.0439 - dense_2_loss_8: 0.0363 - dense_2_loss_9: 0.0361 - dense_2_loss_10: 0.0301 - dense_2_loss_11: 0.0321 - dense_2_loss_12: 0.0303 - dense_2_loss_13: 0.0272 - dense_2_loss_14: 0.0298 - dense_2_loss_15: 0.0315 - dense_2_loss_16: 0.0322 - dense_2_loss_17: 0.0304 - dense_2_loss_18: 0.0279 - dense_2_loss_19: 0.0303 - dense_2_loss_20: 0.0325 - dense_2_loss_21: 0.0341 - dense_2_loss_22: 0.0331 - dense_2_loss_23: 0.0313 - dense_2_loss_24: 0.0311 - dense_2_loss_25: 0.0329 - dense_2_loss_26: 0.0311 - dense_2_loss_27: 0.0375 - dense_2_loss_28: 0.0370 - dense_2_loss_29: 0.0413 - dense_2_loss_30: 0.0000e+00 - dense_2_acc_1: 0.1000 - dense_2_acc_2: 0.6333 - dense_2_acc_3: 0.9167 - dense_2_acc_4: 1.0000 - dense_2_acc_5: 1.0000 - dense_2_acc_6: 1.0000 - dense_2_acc_7: 1.0000 - dense_2_acc_8: 1.0000 - dense_2_acc_9: 1.0000 - dense_2_acc_10: 1.0000 - dense_2_acc_11: 1.0000 - dense_2_acc_12: 1.0000 - dense_2_acc_13: 1.0000 - dense_2_acc_14: 1.0000 - dense_2_acc_15: 1.0000 - dense_2_acc_16: 1.0000 - dense_2_acc_17: 1.0000 - dense_2_acc_18: 1.0000 - dense_2_acc_19: 1.0000 - dense_2_acc_20: 1.0000 - dense_2_acc_21: 1.0000 - dense_2_acc_22: 1.0000 - dense_2_acc_23: 1.0000 - dense_2_acc_24: 1.0000 - dense_2_acc_25: 1.0000 - dense_2_acc_26: 1.0000 - dense_2_acc_27: 1.0000 - dense_2_acc_28: 1.0000 - dense_2_acc_29: 1.0000 - dense_2_acc_30: 0.0167 Epoch 86/100 60/60 [==============================] - 0s - loss: 6.3940 - dense_2_loss_1: 3.7949 - dense_2_loss_2: 1.2372 - dense_2_loss_3: 0.3686 - dense_2_loss_4: 0.1260 - dense_2_loss_5: 0.0717 - dense_2_loss_6: 0.0550 - dense_2_loss_7: 0.0428 - dense_2_loss_8: 0.0354 - dense_2_loss_9: 0.0351 - dense_2_loss_10: 0.0294 - dense_2_loss_11: 0.0314 - dense_2_loss_12: 0.0295 - dense_2_loss_13: 0.0265 - dense_2_loss_14: 0.0291 - dense_2_loss_15: 0.0307 - dense_2_loss_16: 0.0315 - dense_2_loss_17: 0.0296 - dense_2_loss_18: 0.0272 - dense_2_loss_19: 0.0295 - dense_2_loss_20: 0.0317 - dense_2_loss_21: 0.0333 - dense_2_loss_22: 0.0322 - dense_2_loss_23: 0.0305 - dense_2_loss_24: 0.0304 - dense_2_loss_25: 0.0323 - dense_2_loss_26: 0.0302 - dense_2_loss_27: 0.0364 - dense_2_loss_28: 0.0360 - dense_2_loss_29: 0.0400 - dense_2_loss_30: 0.0000e+00 - dense_2_acc_1: 0.1000 - dense_2_acc_2: 0.6333 - dense_2_acc_3: 0.9167 - dense_2_acc_4: 1.0000 - dense_2_acc_5: 1.0000 - dense_2_acc_6: 1.0000 - dense_2_acc_7: 1.0000 - dense_2_acc_8: 1.0000 - dense_2_acc_9: 1.0000 - dense_2_acc_10: 1.0000 - dense_2_acc_11: 1.0000 - dense_2_acc_12: 1.0000 - dense_2_acc_13: 1.0000 - dense_2_acc_14: 1.0000 - dense_2_acc_15: 1.0000 - dense_2_acc_16: 1.0000 - dense_2_acc_17: 1.0000 - dense_2_acc_18: 1.0000 - dense_2_acc_19: 1.0000 - dense_2_acc_20: 1.0000 - dense_2_acc_21: 1.0000 - dense_2_acc_22: 1.0000 - dense_2_acc_23: 1.0000 - dense_2_acc_24: 1.0000 - dense_2_acc_25: 1.0000 - dense_2_acc_26: 1.0000 - dense_2_acc_27: 1.0000 - dense_2_acc_28: 1.0000 - dense_2_acc_29: 1.0000 - dense_2_acc_30: 0.0167 Epoch 87/100 60/60 [==============================] - 0s - loss: 6.3483 - dense_2_loss_1: 3.7918 - dense_2_loss_2: 1.2261 - dense_2_loss_3: 0.3614 - dense_2_loss_4: 0.1230 - dense_2_loss_5: 0.0701 - dense_2_loss_6: 0.0536 - dense_2_loss_7: 0.0419 - dense_2_loss_8: 0.0345 - dense_2_loss_9: 0.0343 - dense_2_loss_10: 0.0287 - dense_2_loss_11: 0.0306 - dense_2_loss_12: 0.0288 - dense_2_loss_13: 0.0259 - dense_2_loss_14: 0.0282 - dense_2_loss_15: 0.0300 - dense_2_loss_16: 0.0308 - dense_2_loss_17: 0.0289 - dense_2_loss_18: 0.0265 - dense_2_loss_19: 0.0288 - dense_2_loss_20: 0.0309 - dense_2_loss_21: 0.0325 - dense_2_loss_22: 0.0313 - dense_2_loss_23: 0.0297 - dense_2_loss_24: 0.0297 - dense_2_loss_25: 0.0318 - dense_2_loss_26: 0.0296 - dense_2_loss_27: 0.0352 - dense_2_loss_28: 0.0350 - dense_2_loss_29: 0.0390 - dense_2_loss_30: 0.0000e+00 - dense_2_acc_1: 0.1000 - dense_2_acc_2: 0.6333 - dense_2_acc_3: 0.9167 - dense_2_acc_4: 1.0000 - dense_2_acc_5: 1.0000 - dense_2_acc_6: 1.0000 - dense_2_acc_7: 1.0000 - dense_2_acc_8: 1.0000 - dense_2_acc_9: 1.0000 - dense_2_acc_10: 1.0000 - dense_2_acc_11: 1.0000 - dense_2_acc_12: 1.0000 - dense_2_acc_13: 1.0000 - dense_2_acc_14: 1.0000 - dense_2_acc_15: 1.0000 - dense_2_acc_16: 1.0000 - dense_2_acc_17: 1.0000 - dense_2_acc_18: 1.0000 - dense_2_acc_19: 1.0000 - dense_2_acc_20: 1.0000 - dense_2_acc_21: 1.0000 - dense_2_acc_22: 1.0000 - dense_2_acc_23: 1.0000 - dense_2_acc_24: 1.0000 - dense_2_acc_25: 1.0000 - dense_2_acc_26: 1.0000 - dense_2_acc_27: 1.0000 - dense_2_acc_28: 1.0000 - dense_2_acc_29: 1.0000 - dense_2_acc_30: 0.0167 Epoch 88/100 60/60 [==============================] - 0s - loss: 6.3026 - dense_2_loss_1: 3.7888 - dense_2_loss_2: 1.2141 - dense_2_loss_3: 0.3541 - dense_2_loss_4: 0.1202 - dense_2_loss_5: 0.0685 - dense_2_loss_6: 0.0522 - dense_2_loss_7: 0.0409 - dense_2_loss_8: 0.0337 - dense_2_loss_9: 0.0334 - dense_2_loss_10: 0.0280 - dense_2_loss_11: 0.0299 - dense_2_loss_12: 0.0282 - dense_2_loss_13: 0.0253 - dense_2_loss_14: 0.0274 - dense_2_loss_15: 0.0294 - dense_2_loss_16: 0.0301 - dense_2_loss_17: 0.0282 - dense_2_loss_18: 0.0258 - dense_2_loss_19: 0.0280 - dense_2_loss_20: 0.0302 - dense_2_loss_21: 0.0317 - dense_2_loss_22: 0.0304 - dense_2_loss_23: 0.0289 - dense_2_loss_24: 0.0289 - dense_2_loss_25: 0.0309 - dense_2_loss_26: 0.0288 - dense_2_loss_27: 0.0345 - dense_2_loss_28: 0.0340 - dense_2_loss_29: 0.0381 - dense_2_loss_30: 0.0000e+00 - dense_2_acc_1: 0.1000 - dense_2_acc_2: 0.6333 - dense_2_acc_3: 0.9167 - dense_2_acc_4: 1.0000 - dense_2_acc_5: 1.0000 - dense_2_acc_6: 1.0000 - dense_2_acc_7: 1.0000 - dense_2_acc_8: 1.0000 - dense_2_acc_9: 1.0000 - dense_2_acc_10: 1.0000 - dense_2_acc_11: 1.0000 - dense_2_acc_12: 1.0000 - dense_2_acc_13: 1.0000 - dense_2_acc_14: 1.0000 - dense_2_acc_15: 1.0000 - dense_2_acc_16: 1.0000 - dense_2_acc_17: 1.0000 - dense_2_acc_18: 1.0000 - dense_2_acc_19: 1.0000 - dense_2_acc_20: 1.0000 - dense_2_acc_21: 1.0000 - dense_2_acc_22: 1.0000 - dense_2_acc_23: 1.0000 - dense_2_acc_24: 1.0000 - dense_2_acc_25: 1.0000 - dense_2_acc_26: 1.0000 - dense_2_acc_27: 1.0000 - dense_2_acc_28: 1.0000 - dense_2_acc_29: 1.0000 - dense_2_acc_30: 0.0167 Epoch 89/100 60/60 [==============================] - 0s - loss: 6.2585 - dense_2_loss_1: 3.7859 - dense_2_loss_2: 1.2023 - dense_2_loss_3: 0.3472 - dense_2_loss_4: 0.1171 - dense_2_loss_5: 0.0668 - dense_2_loss_6: 0.0509 - dense_2_loss_7: 0.0399 - dense_2_loss_8: 0.0329 - dense_2_loss_9: 0.0325 - dense_2_loss_10: 0.0274 - dense_2_loss_11: 0.0291 - dense_2_loss_12: 0.0275 - dense_2_loss_13: 0.0247 - dense_2_loss_14: 0.0268 - dense_2_loss_15: 0.0287 - dense_2_loss_16: 0.0293 - dense_2_loss_17: 0.0275 - dense_2_loss_18: 0.0252 - dense_2_loss_19: 0.0273 - dense_2_loss_20: 0.0295 - dense_2_loss_21: 0.0309 - dense_2_loss_22: 0.0298 - dense_2_loss_23: 0.0283 - dense_2_loss_24: 0.0283 - dense_2_loss_25: 0.0301 - dense_2_loss_26: 0.0282 - dense_2_loss_27: 0.0339 - dense_2_loss_28: 0.0333 - dense_2_loss_29: 0.0373 - dense_2_loss_30: 0.0000e+00 - dense_2_acc_1: 0.1000 - dense_2_acc_2: 0.6333 - dense_2_acc_3: 0.9167 - dense_2_acc_4: 1.0000 - dense_2_acc_5: 1.0000 - dense_2_acc_6: 1.0000 - dense_2_acc_7: 1.0000 - dense_2_acc_8: 1.0000 - dense_2_acc_9: 1.0000 - dense_2_acc_10: 1.0000 - dense_2_acc_11: 1.0000 - dense_2_acc_12: 1.0000 - dense_2_acc_13: 1.0000 - dense_2_acc_14: 1.0000 - dense_2_acc_15: 1.0000 - dense_2_acc_16: 1.0000 - dense_2_acc_17: 1.0000 - dense_2_acc_18: 1.0000 - dense_2_acc_19: 1.0000 - dense_2_acc_20: 1.0000 - dense_2_acc_21: 1.0000 - dense_2_acc_22: 1.0000 - dense_2_acc_23: 1.0000 - dense_2_acc_24: 1.0000 - dense_2_acc_25: 1.0000 - dense_2_acc_26: 1.0000 - dense_2_acc_27: 1.0000 - dense_2_acc_28: 1.0000 - dense_2_acc_29: 1.0000 - dense_2_acc_30: 0.0167 Epoch 90/100 60/60 [==============================] - 0s - loss: 6.2175 - dense_2_loss_1: 3.7831 - dense_2_loss_2: 1.1917 - dense_2_loss_3: 0.3408 - dense_2_loss_4: 0.1144 - dense_2_loss_5: 0.0654 - dense_2_loss_6: 0.0498 - dense_2_loss_7: 0.0390 - dense_2_loss_8: 0.0321 - dense_2_loss_9: 0.0318 - dense_2_loss_10: 0.0267 - dense_2_loss_11: 0.0285 - dense_2_loss_12: 0.0269 - dense_2_loss_13: 0.0240 - dense_2_loss_14: 0.0263 - dense_2_loss_15: 0.0280 - dense_2_loss_16: 0.0285 - dense_2_loss_17: 0.0268 - dense_2_loss_18: 0.0246 - dense_2_loss_19: 0.0267 - dense_2_loss_20: 0.0288 - dense_2_loss_21: 0.0301 - dense_2_loss_22: 0.0291 - dense_2_loss_23: 0.0276 - dense_2_loss_24: 0.0275 - dense_2_loss_25: 0.0292 - dense_2_loss_26: 0.0275 - dense_2_loss_27: 0.0333 - dense_2_loss_28: 0.0326 - dense_2_loss_29: 0.0364 - dense_2_loss_30: 0.0000e+00 - dense_2_acc_1: 0.1000 - dense_2_acc_2: 0.6333 - dense_2_acc_3: 0.9167 - dense_2_acc_4: 1.0000 - dense_2_acc_5: 1.0000 - dense_2_acc_6: 1.0000 - dense_2_acc_7: 1.0000 - dense_2_acc_8: 1.0000 - dense_2_acc_9: 1.0000 - dense_2_acc_10: 1.0000 - dense_2_acc_11: 1.0000 - dense_2_acc_12: 1.0000 - dense_2_acc_13: 1.0000 - dense_2_acc_14: 1.0000 - dense_2_acc_15: 1.0000 - dense_2_acc_16: 1.0000 - dense_2_acc_17: 1.0000 - dense_2_acc_18: 1.0000 - dense_2_acc_19: 1.0000 - dense_2_acc_20: 1.0000 - dense_2_acc_21: 1.0000 - dense_2_acc_22: 1.0000 - dense_2_acc_23: 1.0000 - dense_2_acc_24: 1.0000 - dense_2_acc_25: 1.0000 - dense_2_acc_26: 1.0000 - dense_2_acc_27: 1.0000 - dense_2_acc_28: 1.0000 - dense_2_acc_29: 1.0000 - dense_2_acc_30: 0.0167 Epoch 91/100 60/60 [==============================] - 0s - loss: 6.1774 - dense_2_loss_1: 3.7804 - dense_2_loss_2: 1.1811 - dense_2_loss_3: 0.3349 - dense_2_loss_4: 0.1118 - dense_2_loss_5: 0.0639 - dense_2_loss_6: 0.0486 - dense_2_loss_7: 0.0381 - dense_2_loss_8: 0.0314 - dense_2_loss_9: 0.0310 - dense_2_loss_10: 0.0261 - dense_2_loss_11: 0.0279 - dense_2_loss_12: 0.0263 - dense_2_loss_13: 0.0235 - dense_2_loss_14: 0.0256 - dense_2_loss_15: 0.0274 - dense_2_loss_16: 0.0279 - dense_2_loss_17: 0.0262 - dense_2_loss_18: 0.0240 - dense_2_loss_19: 0.0261 - dense_2_loss_20: 0.0282 - dense_2_loss_21: 0.0294 - dense_2_loss_22: 0.0284 - dense_2_loss_23: 0.0269 - dense_2_loss_24: 0.0269 - dense_2_loss_25: 0.0286 - dense_2_loss_26: 0.0269 - dense_2_loss_27: 0.0324 - dense_2_loss_28: 0.0318 - dense_2_loss_29: 0.0355 - dense_2_loss_30: 0.0000e+00 - dense_2_acc_1: 0.1000 - dense_2_acc_2: 0.6333 - dense_2_acc_3: 0.9333 - dense_2_acc_4: 1.0000 - dense_2_acc_5: 1.0000 - dense_2_acc_6: 1.0000 - dense_2_acc_7: 1.0000 - dense_2_acc_8: 1.0000 - dense_2_acc_9: 1.0000 - dense_2_acc_10: 1.0000 - dense_2_acc_11: 1.0000 - dense_2_acc_12: 1.0000 - dense_2_acc_13: 1.0000 - dense_2_acc_14: 1.0000 - dense_2_acc_15: 1.0000 - dense_2_acc_16: 1.0000 - dense_2_acc_17: 1.0000 - dense_2_acc_18: 1.0000 - dense_2_acc_19: 1.0000 - dense_2_acc_20: 1.0000 - dense_2_acc_21: 1.0000 - dense_2_acc_22: 1.0000 - dense_2_acc_23: 1.0000 - dense_2_acc_24: 1.0000 - dense_2_acc_25: 1.0000 - dense_2_acc_26: 1.0000 - dense_2_acc_27: 1.0000 - dense_2_acc_28: 1.0000 - dense_2_acc_29: 1.0000 - dense_2_acc_30: 0.0167 Epoch 92/100 60/60 [==============================] - 0s - loss: 6.1372 - dense_2_loss_1: 3.7773 - dense_2_loss_2: 1.1703 - dense_2_loss_3: 0.3285 - dense_2_loss_4: 0.1093 - dense_2_loss_5: 0.0626 - dense_2_loss_6: 0.0475 - dense_2_loss_7: 0.0373 - dense_2_loss_8: 0.0306 - dense_2_loss_9: 0.0303 - dense_2_loss_10: 0.0256 - dense_2_loss_11: 0.0273 - dense_2_loss_12: 0.0257 - dense_2_loss_13: 0.0229 - dense_2_loss_14: 0.0250 - dense_2_loss_15: 0.0268 - dense_2_loss_16: 0.0273 - dense_2_loss_17: 0.0256 - dense_2_loss_18: 0.0235 - dense_2_loss_19: 0.0255 - dense_2_loss_20: 0.0276 - dense_2_loss_21: 0.0288 - dense_2_loss_22: 0.0277 - dense_2_loss_23: 0.0263 - dense_2_loss_24: 0.0262 - dense_2_loss_25: 0.0282 - dense_2_loss_26: 0.0264 - dense_2_loss_27: 0.0314 - dense_2_loss_28: 0.0310 - dense_2_loss_29: 0.0346 - dense_2_loss_30: 0.0000e+00 - dense_2_acc_1: 0.1000 - dense_2_acc_2: 0.6333 - dense_2_acc_3: 0.9333 - dense_2_acc_4: 1.0000 - dense_2_acc_5: 1.0000 - dense_2_acc_6: 1.0000 - dense_2_acc_7: 1.0000 - dense_2_acc_8: 1.0000 - dense_2_acc_9: 1.0000 - dense_2_acc_10: 1.0000 - dense_2_acc_11: 1.0000 - dense_2_acc_12: 1.0000 - dense_2_acc_13: 1.0000 - dense_2_acc_14: 1.0000 - dense_2_acc_15: 1.0000 - dense_2_acc_16: 1.0000 - dense_2_acc_17: 1.0000 - dense_2_acc_18: 1.0000 - dense_2_acc_19: 1.0000 - dense_2_acc_20: 1.0000 - dense_2_acc_21: 1.0000 - dense_2_acc_22: 1.0000 - dense_2_acc_23: 1.0000 - dense_2_acc_24: 1.0000 - dense_2_acc_25: 1.0000 - dense_2_acc_26: 1.0000 - dense_2_acc_27: 1.0000 - dense_2_acc_28: 1.0000 - dense_2_acc_29: 1.0000 - dense_2_acc_30: 0.0167 Epoch 93/100 60/60 [==============================] - 0s - loss: 6.1003 - dense_2_loss_1: 3.7744 - dense_2_loss_2: 1.1604 - dense_2_loss_3: 0.3229 - dense_2_loss_4: 0.1071 - dense_2_loss_5: 0.0613 - dense_2_loss_6: 0.0465 - dense_2_loss_7: 0.0365 - dense_2_loss_8: 0.0300 - dense_2_loss_9: 0.0297 - dense_2_loss_10: 0.0250 - dense_2_loss_11: 0.0267 - dense_2_loss_12: 0.0251 - dense_2_loss_13: 0.0224 - dense_2_loss_14: 0.0245 - dense_2_loss_15: 0.0262 - dense_2_loss_16: 0.0267 - dense_2_loss_17: 0.0250 - dense_2_loss_18: 0.0230 - dense_2_loss_19: 0.0249 - dense_2_loss_20: 0.0270 - dense_2_loss_21: 0.0281 - dense_2_loss_22: 0.0271 - dense_2_loss_23: 0.0257 - dense_2_loss_24: 0.0257 - dense_2_loss_25: 0.0276 - dense_2_loss_26: 0.0258 - dense_2_loss_27: 0.0307 - dense_2_loss_28: 0.0304 - dense_2_loss_29: 0.0338 - dense_2_loss_30: 0.0000e+00 - dense_2_acc_1: 0.1000 - dense_2_acc_2: 0.6333 - dense_2_acc_3: 0.9333 - dense_2_acc_4: 1.0000 - dense_2_acc_5: 1.0000 - dense_2_acc_6: 1.0000 - dense_2_acc_7: 1.0000 - dense_2_acc_8: 1.0000 - dense_2_acc_9: 1.0000 - dense_2_acc_10: 1.0000 - dense_2_acc_11: 1.0000 - dense_2_acc_12: 1.0000 - dense_2_acc_13: 1.0000 - dense_2_acc_14: 1.0000 - dense_2_acc_15: 1.0000 - dense_2_acc_16: 1.0000 - dense_2_acc_17: 1.0000 - dense_2_acc_18: 1.0000 - dense_2_acc_19: 1.0000 - dense_2_acc_20: 1.0000 - dense_2_acc_21: 1.0000 - dense_2_acc_22: 1.0000 - dense_2_acc_23: 1.0000 - dense_2_acc_24: 1.0000 - dense_2_acc_25: 1.0000 - dense_2_acc_26: 1.0000 - dense_2_acc_27: 1.0000 - dense_2_acc_28: 1.0000 - dense_2_acc_29: 1.0000 - dense_2_acc_30: 0.0167 Epoch 94/100 60/60 [==============================] - 0s - loss: 6.0638 - dense_2_loss_1: 3.7719 - dense_2_loss_2: 1.1503 - dense_2_loss_3: 0.3168 - dense_2_loss_4: 0.1049 - dense_2_loss_5: 0.0600 - dense_2_loss_6: 0.0456 - dense_2_loss_7: 0.0358 - dense_2_loss_8: 0.0294 - dense_2_loss_9: 0.0290 - dense_2_loss_10: 0.0245 - dense_2_loss_11: 0.0261 - dense_2_loss_12: 0.0246 - dense_2_loss_13: 0.0219 - dense_2_loss_14: 0.0239 - dense_2_loss_15: 0.0257 - dense_2_loss_16: 0.0261 - dense_2_loss_17: 0.0245 - dense_2_loss_18: 0.0225 - dense_2_loss_19: 0.0244 - dense_2_loss_20: 0.0264 - dense_2_loss_21: 0.0275 - dense_2_loss_22: 0.0265 - dense_2_loss_23: 0.0252 - dense_2_loss_24: 0.0252 - dense_2_loss_25: 0.0268 - dense_2_loss_26: 0.0252 - dense_2_loss_27: 0.0303 - dense_2_loss_28: 0.0297 - dense_2_loss_29: 0.0330 - dense_2_loss_30: 0.0000e+00 - dense_2_acc_1: 0.1000 - dense_2_acc_2: 0.6333 - dense_2_acc_3: 0.9333 - dense_2_acc_4: 1.0000 - dense_2_acc_5: 1.0000 - dense_2_acc_6: 1.0000 - dense_2_acc_7: 1.0000 - dense_2_acc_8: 1.0000 - dense_2_acc_9: 1.0000 - dense_2_acc_10: 1.0000 - dense_2_acc_11: 1.0000 - dense_2_acc_12: 1.0000 - dense_2_acc_13: 1.0000 - dense_2_acc_14: 1.0000 - dense_2_acc_15: 1.0000 - dense_2_acc_16: 1.0000 - dense_2_acc_17: 1.0000 - dense_2_acc_18: 1.0000 - dense_2_acc_19: 1.0000 - dense_2_acc_20: 1.0000 - dense_2_acc_21: 1.0000 - dense_2_acc_22: 1.0000 - dense_2_acc_23: 1.0000 - dense_2_acc_24: 1.0000 - dense_2_acc_25: 1.0000 - dense_2_acc_26: 1.0000 - dense_2_acc_27: 1.0000 - dense_2_acc_28: 1.0000 - dense_2_acc_29: 1.0000 - dense_2_acc_30: 0.0167 Epoch 95/100 60/60 [==============================] - 0s - loss: 6.0277 - dense_2_loss_1: 3.7691 - dense_2_loss_2: 1.1406 - dense_2_loss_3: 0.3106 - dense_2_loss_4: 0.1027 - dense_2_loss_5: 0.0587 - dense_2_loss_6: 0.0446 - dense_2_loss_7: 0.0350 - dense_2_loss_8: 0.0288 - dense_2_loss_9: 0.0284 - dense_2_loss_10: 0.0239 - dense_2_loss_11: 0.0255 - dense_2_loss_12: 0.0241 - dense_2_loss_13: 0.0215 - dense_2_loss_14: 0.0234 - dense_2_loss_15: 0.0252 - dense_2_loss_16: 0.0256 - dense_2_loss_17: 0.0240 - dense_2_loss_18: 0.0220 - dense_2_loss_19: 0.0238 - dense_2_loss_20: 0.0258 - dense_2_loss_21: 0.0269 - dense_2_loss_22: 0.0260 - dense_2_loss_23: 0.0247 - dense_2_loss_24: 0.0247 - dense_2_loss_25: 0.0261 - dense_2_loss_26: 0.0247 - dense_2_loss_27: 0.0297 - dense_2_loss_28: 0.0291 - dense_2_loss_29: 0.0325 - dense_2_loss_30: 0.0000e+00 - dense_2_acc_1: 0.1000 - dense_2_acc_2: 0.6333 - dense_2_acc_3: 0.9333 - dense_2_acc_4: 1.0000 - dense_2_acc_5: 1.0000 - dense_2_acc_6: 1.0000 - dense_2_acc_7: 1.0000 - dense_2_acc_8: 1.0000 - dense_2_acc_9: 1.0000 - dense_2_acc_10: 1.0000 - dense_2_acc_11: 1.0000 - dense_2_acc_12: 1.0000 - dense_2_acc_13: 1.0000 - dense_2_acc_14: 1.0000 - dense_2_acc_15: 1.0000 - dense_2_acc_16: 1.0000 - dense_2_acc_17: 1.0000 - dense_2_acc_18: 1.0000 - dense_2_acc_19: 1.0000 - dense_2_acc_20: 1.0000 - dense_2_acc_21: 1.0000 - dense_2_acc_22: 1.0000 - dense_2_acc_23: 1.0000 - dense_2_acc_24: 1.0000 - dense_2_acc_25: 1.0000 - dense_2_acc_26: 1.0000 - dense_2_acc_27: 1.0000 - dense_2_acc_28: 1.0000 - dense_2_acc_29: 1.0000 - dense_2_acc_30: 0.0167 Epoch 96/100 60/60 [==============================] - 0s - loss: 5.9935 - dense_2_loss_1: 3.7663 - dense_2_loss_2: 1.1307 - dense_2_loss_3: 0.3055 - dense_2_loss_4: 0.1008 - dense_2_loss_5: 0.0577 - dense_2_loss_6: 0.0438 - dense_2_loss_7: 0.0343 - dense_2_loss_8: 0.0282 - dense_2_loss_9: 0.0279 - dense_2_loss_10: 0.0234 - dense_2_loss_11: 0.0250 - dense_2_loss_12: 0.0237 - dense_2_loss_13: 0.0210 - dense_2_loss_14: 0.0230 - dense_2_loss_15: 0.0246 - dense_2_loss_16: 0.0250 - dense_2_loss_17: 0.0234 - dense_2_loss_18: 0.0216 - dense_2_loss_19: 0.0233 - dense_2_loss_20: 0.0252 - dense_2_loss_21: 0.0263 - dense_2_loss_22: 0.0255 - dense_2_loss_23: 0.0241 - dense_2_loss_24: 0.0241 - dense_2_loss_25: 0.0256 - dense_2_loss_26: 0.0242 - dense_2_loss_27: 0.0291 - dense_2_loss_28: 0.0283 - dense_2_loss_29: 0.0317 - dense_2_loss_30: 0.0000e+00 - dense_2_acc_1: 0.1000 - dense_2_acc_2: 0.6333 - dense_2_acc_3: 0.9333 - dense_2_acc_4: 1.0000 - dense_2_acc_5: 1.0000 - dense_2_acc_6: 1.0000 - dense_2_acc_7: 1.0000 - dense_2_acc_8: 1.0000 - dense_2_acc_9: 1.0000 - dense_2_acc_10: 1.0000 - dense_2_acc_11: 1.0000 - dense_2_acc_12: 1.0000 - dense_2_acc_13: 1.0000 - dense_2_acc_14: 1.0000 - dense_2_acc_15: 1.0000 - dense_2_acc_16: 1.0000 - dense_2_acc_17: 1.0000 - dense_2_acc_18: 1.0000 - dense_2_acc_19: 1.0000 - dense_2_acc_20: 1.0000 - dense_2_acc_21: 1.0000 - dense_2_acc_22: 1.0000 - dense_2_acc_23: 1.0000 - dense_2_acc_24: 1.0000 - dense_2_acc_25: 1.0000 - dense_2_acc_26: 1.0000 - dense_2_acc_27: 1.0000 - dense_2_acc_28: 1.0000 - dense_2_acc_29: 1.0000 - dense_2_acc_30: 0.0167 Epoch 97/100 60/60 [==============================] - 0s - loss: 5.9590 - dense_2_loss_1: 3.7636 - dense_2_loss_2: 1.1208 - dense_2_loss_3: 0.3002 - dense_2_loss_4: 0.0988 - dense_2_loss_5: 0.0563 - dense_2_loss_6: 0.0429 - dense_2_loss_7: 0.0335 - dense_2_loss_8: 0.0276 - dense_2_loss_9: 0.0273 - dense_2_loss_10: 0.0230 - dense_2_loss_11: 0.0245 - dense_2_loss_12: 0.0232 - dense_2_loss_13: 0.0206 - dense_2_loss_14: 0.0225 - dense_2_loss_15: 0.0241 - dense_2_loss_16: 0.0245 - dense_2_loss_17: 0.0229 - dense_2_loss_18: 0.0211 - dense_2_loss_19: 0.0229 - dense_2_loss_20: 0.0247 - dense_2_loss_21: 0.0258 - dense_2_loss_22: 0.0249 - dense_2_loss_23: 0.0236 - dense_2_loss_24: 0.0237 - dense_2_loss_25: 0.0252 - dense_2_loss_26: 0.0238 - dense_2_loss_27: 0.0284 - dense_2_loss_28: 0.0277 - dense_2_loss_29: 0.0310 - dense_2_loss_30: 0.0000e+00 - dense_2_acc_1: 0.1000 - dense_2_acc_2: 0.6333 - dense_2_acc_3: 0.9333 - dense_2_acc_4: 1.0000 - dense_2_acc_5: 1.0000 - dense_2_acc_6: 1.0000 - dense_2_acc_7: 1.0000 - dense_2_acc_8: 1.0000 - dense_2_acc_9: 1.0000 - dense_2_acc_10: 1.0000 - dense_2_acc_11: 1.0000 - dense_2_acc_12: 1.0000 - dense_2_acc_13: 1.0000 - dense_2_acc_14: 1.0000 - dense_2_acc_15: 1.0000 - dense_2_acc_16: 1.0000 - dense_2_acc_17: 1.0000 - dense_2_acc_18: 1.0000 - dense_2_acc_19: 1.0000 - dense_2_acc_20: 1.0000 - dense_2_acc_21: 1.0000 - dense_2_acc_22: 1.0000 - dense_2_acc_23: 1.0000 - dense_2_acc_24: 1.0000 - dense_2_acc_25: 1.0000 - dense_2_acc_26: 1.0000 - dense_2_acc_27: 1.0000 - dense_2_acc_28: 1.0000 - dense_2_acc_29: 1.0000 - dense_2_acc_30: 0.0167 Epoch 98/100 60/60 [==============================] - 0s - loss: 5.9280 - dense_2_loss_1: 3.7608 - dense_2_loss_2: 1.1124 - dense_2_loss_3: 0.2956 - dense_2_loss_4: 0.0968 - dense_2_loss_5: 0.0552 - dense_2_loss_6: 0.0421 - dense_2_loss_7: 0.0330 - dense_2_loss_8: 0.0270 - dense_2_loss_9: 0.0268 - dense_2_loss_10: 0.0225 - dense_2_loss_11: 0.0240 - dense_2_loss_12: 0.0227 - dense_2_loss_13: 0.0202 - dense_2_loss_14: 0.0220 - dense_2_loss_15: 0.0237 - dense_2_loss_16: 0.0241 - dense_2_loss_17: 0.0225 - dense_2_loss_18: 0.0207 - dense_2_loss_19: 0.0224 - dense_2_loss_20: 0.0242 - dense_2_loss_21: 0.0253 - dense_2_loss_22: 0.0244 - dense_2_loss_23: 0.0232 - dense_2_loss_24: 0.0232 - dense_2_loss_25: 0.0247 - dense_2_loss_26: 0.0234 - dense_2_loss_27: 0.0278 - dense_2_loss_28: 0.0272 - dense_2_loss_29: 0.0302 - dense_2_loss_30: 0.0000e+00 - dense_2_acc_1: 0.1000 - dense_2_acc_2: 0.6333 - dense_2_acc_3: 0.9333 - dense_2_acc_4: 1.0000 - dense_2_acc_5: 1.0000 - dense_2_acc_6: 1.0000 - dense_2_acc_7: 1.0000 - dense_2_acc_8: 1.0000 - dense_2_acc_9: 1.0000 - dense_2_acc_10: 1.0000 - dense_2_acc_11: 1.0000 - dense_2_acc_12: 1.0000 - dense_2_acc_13: 1.0000 - dense_2_acc_14: 1.0000 - dense_2_acc_15: 1.0000 - dense_2_acc_16: 1.0000 - dense_2_acc_17: 1.0000 - dense_2_acc_18: 1.0000 - dense_2_acc_19: 1.0000 - dense_2_acc_20: 1.0000 - dense_2_acc_21: 1.0000 - dense_2_acc_22: 1.0000 - dense_2_acc_23: 1.0000 - dense_2_acc_24: 1.0000 - dense_2_acc_25: 1.0000 - dense_2_acc_26: 1.0000 - dense_2_acc_27: 1.0000 - dense_2_acc_28: 1.0000 - dense_2_acc_29: 1.0000 - dense_2_acc_30: 0.0167 Epoch 99/100 60/60 [==============================] - 0s - loss: 5.8968 - dense_2_loss_1: 3.7581 - dense_2_loss_2: 1.1032 - dense_2_loss_3: 0.2908 - dense_2_loss_4: 0.0950 - dense_2_loss_5: 0.0542 - dense_2_loss_6: 0.0413 - dense_2_loss_7: 0.0323 - dense_2_loss_8: 0.0266 - dense_2_loss_9: 0.0263 - dense_2_loss_10: 0.0221 - dense_2_loss_11: 0.0235 - dense_2_loss_12: 0.0223 - dense_2_loss_13: 0.0198 - dense_2_loss_14: 0.0214 - dense_2_loss_15: 0.0233 - dense_2_loss_16: 0.0236 - dense_2_loss_17: 0.0220 - dense_2_loss_18: 0.0203 - dense_2_loss_19: 0.0220 - dense_2_loss_20: 0.0238 - dense_2_loss_21: 0.0249 - dense_2_loss_22: 0.0238 - dense_2_loss_23: 0.0227 - dense_2_loss_24: 0.0228 - dense_2_loss_25: 0.0242 - dense_2_loss_26: 0.0230 - dense_2_loss_27: 0.0273 - dense_2_loss_28: 0.0266 - dense_2_loss_29: 0.0296 - dense_2_loss_30: 0.0000e+00 - dense_2_acc_1: 0.1000 - dense_2_acc_2: 0.6333 - dense_2_acc_3: 0.9333 - dense_2_acc_4: 1.0000 - dense_2_acc_5: 1.0000 - dense_2_acc_6: 1.0000 - dense_2_acc_7: 1.0000 - dense_2_acc_8: 1.0000 - dense_2_acc_9: 1.0000 - dense_2_acc_10: 1.0000 - dense_2_acc_11: 1.0000 - dense_2_acc_12: 1.0000 - dense_2_acc_13: 1.0000 - dense_2_acc_14: 1.0000 - dense_2_acc_15: 1.0000 - dense_2_acc_16: 1.0000 - dense_2_acc_17: 1.0000 - dense_2_acc_18: 1.0000 - dense_2_acc_19: 1.0000 - dense_2_acc_20: 1.0000 - dense_2_acc_21: 1.0000 - dense_2_acc_22: 1.0000 - dense_2_acc_23: 1.0000 - dense_2_acc_24: 1.0000 - dense_2_acc_25: 1.0000 - dense_2_acc_26: 1.0000 - dense_2_acc_27: 1.0000 - dense_2_acc_28: 1.0000 - dense_2_acc_29: 1.0000 - dense_2_acc_30: 0.0167 Epoch 100/100 60/60 [==============================] - 0s - loss: 5.8666 - dense_2_loss_1: 3.7555 - dense_2_loss_2: 1.0946 - dense_2_loss_3: 0.2862 - dense_2_loss_4: 0.0933 - dense_2_loss_5: 0.0533 - dense_2_loss_6: 0.0405 - dense_2_loss_7: 0.0317 - dense_2_loss_8: 0.0261 - dense_2_loss_9: 0.0257 - dense_2_loss_10: 0.0217 - dense_2_loss_11: 0.0230 - dense_2_loss_12: 0.0219 - dense_2_loss_13: 0.0194 - dense_2_loss_14: 0.0210 - dense_2_loss_15: 0.0228 - dense_2_loss_16: 0.0232 - dense_2_loss_17: 0.0216 - dense_2_loss_18: 0.0199 - dense_2_loss_19: 0.0215 - dense_2_loss_20: 0.0233 - dense_2_loss_21: 0.0244 - dense_2_loss_22: 0.0234 - dense_2_loss_23: 0.0223 - dense_2_loss_24: 0.0223 - dense_2_loss_25: 0.0237 - dense_2_loss_26: 0.0226 - dense_2_loss_27: 0.0267 - dense_2_loss_28: 0.0261 - dense_2_loss_29: 0.0289 - dense_2_loss_30: 0.0000e+00 - dense_2_acc_1: 0.1000 - dense_2_acc_2: 0.6333 - dense_2_acc_3: 0.9500 - dense_2_acc_4: 1.0000 - dense_2_acc_5: 1.0000 - dense_2_acc_6: 1.0000 - dense_2_acc_7: 1.0000 - dense_2_acc_8: 1.0000 - dense_2_acc_9: 1.0000 - dense_2_acc_10: 1.0000 - dense_2_acc_11: 1.0000 - dense_2_acc_12: 1.0000 - dense_2_acc_13: 1.0000 - dense_2_acc_14: 1.0000 - dense_2_acc_15: 1.0000 - dense_2_acc_16: 1.0000 - dense_2_acc_17: 1.0000 - dense_2_acc_18: 1.0000 - dense_2_acc_19: 1.0000 - dense_2_acc_20: 1.0000 - dense_2_acc_21: 1.0000 - dense_2_acc_22: 1.0000 - dense_2_acc_23: 1.0000 - dense_2_acc_24: 1.0000 - dense_2_acc_25: 1.0000 - dense_2_acc_26: 1.0000 - dense_2_acc_27: 1.0000 - dense_2_acc_28: 1.0000 - dense_2_acc_29: 1.0000 - dense_2_acc_30: 0.0167 <keras.callbacks.History at 0x7f92292b23c8>
You should see the model loss going down. Now that you have trained a model, lets go on the the final section to implement an inference algorithm, and generate some music!
3 - Generating music
You now have a trained model which has learned the patterns of the jazz soloist. Lets now use this model to synthesize new music.3.1 - Predicting & Sampling
At each step of sampling, you will take as input the activation
aand cell state
cfrom the previous state of the LSTM, forward propagate by one step, and get a new output activation as well as cell state. The new activation
acan then be used to generate the output, using
densoras before.
To start off the model, we will initialize
x0as well as the LSTM activation and and cell value
a0and
c0to be zeros.
Exercise: Implement the function below to sample a sequence of musical values. Here are some of the key steps you’ll need to implement inside the for-loop that generates the TyTy output characters:
Step 2.A: Use
LSTM_Cell, which inputs the previous step’s
cand
ato generate the current step’s
cand
a.
Step 2.B: Use
densor(defined previously) to compute a softmax on
ato get the output for the current step.
Step 2.C: Save the output you have just generated by appending it to
outputs.
Step 2.D: Sample x to the be “out“‘s one-hot version (the prediction) so that you can pass it to the next LSTM’s step. We have already provided this line of code, which uses a Lambda function.
x = Lambda(one_hot)(out)
[Minor technical note: Rather than sampling a value at random according to the probabilities in
out, this line of code actually chooses the single most likely note at each step using an argmax.]
# GRADED FUNCTION: music_inference_model def music_inference_model(LSTM_cell, densor, n_values = 78, n_a = 64, Ty = 100): """ Uses the trained "LSTM_cell" and "densor" from model() to generate a sequence of values. Arguments: LSTM_cell -- the trained "LSTM_cell" from model(), Keras layer object densor -- the trained "densor" from model(), Keras layer object n_values -- integer, umber of unique values n_a -- number of units in the LSTM_cell Ty -- integer, number of time steps to generate Returns: inference_model -- Keras model instance """ # Define the input of your model with a shape x0 = Input(shape=(1, n_values)) # Define s0, initial hidden state for the decoder LSTM a0 = Input(shape=(n_a,), name='a0') c0 = Input(shape=(n_a,), name='c0') a = a0 c = c0 x = x0 ### START CODE HERE ### # Step 1: Create an empty list of "outputs" to later store your predicted values (≈1 line) outputs = [] # Step 2: Loop over Ty and generate a value at every time step for t in range(Ty): # Step 2.A: Perform one step of LSTM_cell (≈1 line) a, _, c = LSTM_cell(x, initial_state=[a, c]) # Step 2.B: Apply Dense layer to the hidden state output of the LSTM_cell (≈1 line) out = densor(a) # Step 2.C: Append the prediction "out" to "outputs". out.shape = (None, 78) (≈1 line) outputs.append(out) # Step 2.D: Select the next value according to "out", and set "x" to be the one-hot representation of the # selected value, which will be passed as the input to LSTM_cell on the next step. We have provided # the line of code you need to do this. x = Lambda(one_hot)(out) # Step 3: Create model instance with the correct "inputs" and "outputs" (≈1 line) inference_model = Model(inputs=[x0,a0,c0],outputs=outputs) ### END CODE HERE ### return inference_model
Run the cell below to define your inference model. This model is hard coded to generate 50 values.
inference_model = music_inference_model(LSTM_cell, densor, n_values = 78, n_a = 64, Ty = 50)
Finally, this creates the zero-valued vectors you will use to initialize
xand the LSTM state variables
aand
c.
x_initializer = np.zeros((1, 1, 78)) a_initializer = np.zeros((1, n_a)) c_initializer = np.zeros((1, n_a))
Exercise: Implement
predict_and_sample(). This function takes many arguments including the inputs [x_initializer, a_initializer, c_initializer]. In order to predict the output corresponding to this input, you will need to carry-out 3 steps:
1. Use your inference model to predict an output given your set of inputs. The output
predshould be a list of length 20 where each element is a numpy-array of shape (TyTy, n_values)
2. Convert
predinto a numpy array of TyTy indices. Each index corresponds is computed by taking the
argmaxof an element of the
predlist. Hint.
3. Convert the indices into their one-hot vector representations. Hint.
# GRADED FUNCTION: predict_and_sample def predict_and_sample(inference_model, x_initializer = x_initializer, a_initializer = a_initializer, c_initializer = c_initializer): """ Predicts the next value of values using the inference model. Arguments: inference_model -- Keras model instance for inference time x_initializer -- numpy array of shape (1, 1, 78), one-hot vector initializing the values generation a_initializer -- numpy array of shape (1, n_a), initializing the hidden state of the LSTM_cell c_initializer -- numpy array of shape (1, n_a), initializing the cell state of the LSTM_cel Returns: results -- numpy-array of shape (Ty, 78), matrix of one-hot vectors representing the values generated indices -- numpy-array of shape (Ty, 1), matrix of indices representing the values generated """ ### START CODE HERE ### # Step 1: Use your inference model to predict an output sequence given x_initializer, a_initializer and c_initializer. pred = inference_model.predict([x_initializer,a_initializer,c_initializer]) # Step 2: Convert "pred" into an np.array() of indices with the maximum probabilities indices = np.argmax(pred, axis = -1) # Step 3: Convert indices to one-hot vectors, the shape of the results should be (1, ) results = to_categorical(indices,num_classes=78) ### END CODE HERE ### return results, indices
results, indices = predict_and_sample(inference_model, x_initializer, a_initializer, c_initializer)
print("np.argmax(results[12]) =", np.argmax(results[12]))
print("np.argmax(results[17]) =", np.argmax(results[17]))
print("list(indices[12:18]) =", list(indices[12:18]))np.argmax(results[12]) = 67 np.argmax(results[17]) = 74 list(indices[12:18]) = [array([67]), array([54]), array([67]), array([56]), array([76]), array([74])]
Expected Output: Your results may differ because Keras’ results are not completely predictable. However, if you have trained your LSTM_cell with model.fit() for exactly 100 epochs as described above, you should very likely observe a sequence of indices that are not all identical. Moreover, you should observe that: np.argmax(results[12]) is the first element of list(indices[12:18]) and np.argmax(results[17]) is the last element of list(indices[12:18]).
| **np.argmax(results[12])** = | 1 |
| **np.argmax(results[12])** = | 42 |
| **list(indices[12:18])** = | [array([1]), array([42]), array([54]), array([17]), array([1]), array([42])] |
3.3 - Generate music
Finally, you are ready to generate music. Your RNN generates a sequence of values. The following code generates music by first calling yourpredict_and_sample()function. These values are then post-processed into musical chords (meaning that multiple values or notes can be played at the same time).
Most computational music algorithms use some post-processing because it is difficult to generate music that sounds good without such post-processing. The post-processing does things such as clean up the generated audio by making sure the same sound is not repeated too many times, that two successive notes are not too far from each other in pitch, and so on. One could argue that a lot of these post-processing steps are hacks; also, a lot the music generation literature has also focused on hand-crafting post-processors, and a lot of the output quality depends on the quality of the post-processing and not just the quality of the RNN. But this post-processing does make a huge difference, so lets use it in our implementation as well.
Lets make some music!
Run the following cell to generate music and record it into your
out_stream. This can take a couple of minutes.
out_stream = generate_music(inference_model)
Predicting new values for different set of chords.
Generated 51 sounds using the predicted values for the set of chords ("1") and after pruning
Generated 51 sounds using the predicted values for the set of chords ("2") and after pruning
Generated 51 sounds using the predicted values for the set of chords ("3") and after pruning
Generated 51 sounds using the predicted values for the set of chords ("4") and after pruning
Generated 51 sounds using the predicted values for the set of chords ("5") and after pruning
Your generated music is saved in output/my_music.midiTo listen to your music, click File->Open… Then go to “output/” and download “my_music.midi”. Either play it on your computer with an application that can read midi files if you have one, or use one of the free online “MIDI to mp3” conversion tools to convert this to mp3.
As reference, here also is a 30sec audio clip we generated using this algorithm.
内容来自用户分享和网络整理，不保证内容的准确性，如有侵权内容，可联系管理员处理 
相关文章推荐
- [coursera/SequenceModels/week1]Improvise a Jazz Solo with an LSTM Network - v1[assignment]
- Coursera 吴恩达DeepLearning.AI 第五课 sequence model 序列模型 第一周 Improvise a Jazz Solo with an LSTM Network
- 吴恩达 深度学习 编程作业（5-1）Part 3 - Improvise a Jazz Solo with an LSTM Network
- 吴恩达深度学习第5课第一周作业3 Improvise a Jazz Solo with an LSTM Network - v1
- Assignment | 05-week1 -Improvise a Jazz Solo with an LSTM Network
- Improvise a Jazz Solo with an LSTM Network
- Becoming an Xperf Xpert Part 9: Where’s My Network? (With Stack Walk)
- An Introduction to Network Programming with Java
- org.springframework.beans.factory.BeanDefinitionStoreException: Invalid bean definition with name 'd
- Sqlachemy的警告SAWarning: The IN-predicate on "sns_object.BIZ_ID" was invoked with an empty sequence. This results in a contradiction, which nonetheless can be expensive to evaluate.
- Applying Use Case Driven Object Modeling with UML: An Annotated e-Commerce Example
- 源码安装apache，报错：Cannot use an external APR with the bundled APR-util
- tf 报错提示ValueError: setting an array element with a sequence.
- Backbone.js Basics: Bringing an App to Life with Events
- （virt-install）ERROR Network not found: no network with matching name 'default'
- get an array of arrays with unique elements
- [Windows]_[连接错误fatal error C1047--with an older compiler]
- Fw:An interesting Poem of C Language (extracts with a new title)