TF:TF下CNN实现mnist数据集预测 96%采用placeholder用法+2层C及其max_pool法+隐藏层dropout法+输出层softmax法+目标函数cross_entropy法+A
2018-01-24 23:17
786 查看
TF:TF下CNN实现mnist数据集预测 96%采用placeholder用法+2层C及其max_pool法+隐藏层dropout法+输出层softmax法+目标函数cross_entropy法+AdamOptimizer算法
import tensorflow as tf from tensorflow.examples.tutorials.mnist import input_data # number 1 to 10 data mnist = input_data.read_data_sets('MNIST_data', one_hot=True) def compute_accuracy(v_xs, v_ys): global prediction y_pre = sess.run(prediction, feed_dict={xs: v_xs, keep_prob: 1}) correct_prediction = tf.equal(tf.argmax(y_pre,1), tf.argmax(v_ys,1)) accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32)) result = sess.run(accuracy, feed_dict={xs: v_xs, ys: v_ys, keep_prob: 1}) return result def weight_variable(shape): initial = tf.truncated_normal(shape, stddev=0.1) return tf.Variable(initial) def bias_variable(shape): initial = tf.constant(0.1, shape=shape) return tf.Variable(initial) def conv2d(x, W): return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME') def max_pool_2x2(x): return tf.nn.max_pool(x, ksize=[1,2,2,1], strides=[1,2,2,1], padding='SAME') xs = tf.placeholder(tf.float32, [None, 784]) # 28x28 ys = tf.placeholder(tf.float32, [None, 10]) keep_prob = tf.placeholder(tf.float32) x_image = tf.reshape(xs, [-1, 28, 28, 1]) ## conv1 layer; W_conv1 = weight_variable([5,5, 1,32]) b_conv1 = bias_variable([32]) h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1) h_pool1 = max_pool_2x2(h_conv1) W_conv2 = weight_variable([5,5, 32, 64]) b_conv2 = bias_variable([64]) h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2) h_pool2 = max_pool_2x2(h_conv2) W_fc1 = weight_variable([7*7*64, 1024]) b_fc1 = bias_variable([1024]) h_pool2_flat = tf.reshape(h_pool2, [-1, 7*7*64]) h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1) h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob) W_fc2 = weight_variable([1024, 10]) b_fc2 = bias_variable([10]) prediction = tf.nn.softmax(tf.matmul(h_fc1_drop, W_fc2) + b_fc2) # the error between prediction and real data cross_entropy = tf.reduce_mean(-tf.reduce_sum(ys * tf.log(prediction), reduction_indices=[1])) train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy) sess = tf.Session() # important step sess.run(tf.global_variables_initializer()) for i in range(10): batch_xs, batch_ys = mnist.train.next_batch(100) sess.run(train_step, feed_dict={xs: batch_xs, ys: batch_ys, keep_prob: 0.5}) if i % 50 == 0: print(compute_accuracy( mnist.test.images, mnist.test.labels))
相关文章推荐
- TF之RNN:基于顺序的RNN分类案例对手写数字图片mnist数据集实现高精度预测—Jason niu
- Tensorflow实战学习(十六)【CNN实现、数据集、TFRecord、加载图像、模型、训练、调试】
- TF:TF分类问题之MNIST手写50000数据集实现87.4%准确率识别:SGD法+softmax法+cross_entropy法—Jason niu
- tensorflow 学习专栏(六):使用卷积神经网络(CNN)在mnist数据集上实现分类
- TF之AE:AE实现TF自带数据集数字真实值对比AE先encoder后decoder预测数字的精确对比—Jason niu
- TensorFlow实例(5.3)--MNIST手写数字进阶算法(卷积神经网络CNN) 之 最大池化tf.nn.max_pool
- 学习笔记TF016:CNN实现、数据集、TFRecord、加载图像、模型、训练、调试
- TersorflowTutorial_MNIST数据集上简单CNN实现
- cnn matlab实现mnist
- tensorflow使用CNN分析mnist手写体数字数据集
- 【TensorFlow】tf.nn.max_pool实现池化操作
- tensorflow实战2:实现mnist 单层cnn分类
- TensorFlow学习笔记(5)--实现卷积神经网络(MNIST数据集)
- tensorflow 学习笔记9 卷积神经网络(CNN)实现mnist手写识别
- 第二章——用Python实现感知器模型(MNIST数据集)
- 【Natural Language Processing】TF-IDF及其Python实现
- 基于TensorFlow的mnist数据集的最近邻算法实现代码
- [置顶] java实现基于Mnist数据集的手写数字识别
- TensorFlow--tf.nn.max_pool实现池化操作
- 用tensorflow实现usps和mnist数据集的迁移学习