tensorflow报错:Shape must be rank 2 but is rank 3 for 'MatMul' (op: 'MatMul')
2017-07-03 09:58
597 查看
tensorflow矩阵相乘,秩不同报错
在tensorflow中写了这样一句:y_out = tf.matmul(outputs, W)
其中,outputs的shape为[16,336,400],W的shape为[400,1]
出现以下报错:
Shape must be rank 2 but is rank 3 for 'MatMul' (op: 'MatMul') with input shapes: [16,336,400], [400,1].
Numpy下同样的写法没有问题
import numpy as np A = np.array([[[1, 2, 3, 4], [5, 6, 7, 8], [9, 0, 1, 2]], [[4, 3, 2, 1], [8, 7, 6, 5], [2, 1, 0, 9]]]) print(A) print(A.shape) print('---------------------------') B = np.array([[1], [2], [3], [4]]) print(B) print(B.shape) print('---------------------------') C = np.matmul(A, B) print(C) print(C.shape)
输出结果:
[[[1 2 3 4] [5 6 7 8] [9 0 1 2]] [[4 3 2 1] [8 7 6 5] [2 1 0 9]]] (2, 3, 4) --------------------------- [[1] [2] [3] [4]] (4, 1) --------------------------- [[[30] [70] [20]] [[20] [60] [40]]] (2, 3, 1)
解决办法
方案一
import numpy as np import tensorflow as tf sess = tf.Session() A = np.array([[[1, 2, 3, 4], [5, 6, 7, 8], [9, 0, 1, 2]], [[4, 3, 2, 1], [8, 7, 6, 5], [2, 1, 0, 9]]]) B = np.array([[1], [2], [3], [4]]) A = tf.cast(tf.convert_to_tensor(A), tf.int32) # shape=[2, 3, 4] B = tf.cast(tf.convert_to_tensor(B), tf.int32) # shape=[4, 1] #-----------------------------------------修改部分(开始)----------------------------------------- #要想让A和B进行tf.matmul操作,第一个维数必须一致。因此要把B先tile后转成[2, 4, 1]维 B_ = tf.tile(B, [2, 1])# B的第一维复制2倍,第二维复制1倍 B = tf.reshape(B_, [2, 4, 1]) # 或 更通用的改法: #B_ = tf.tile(B, [tf.shape(A)[0], 1]) #B = tf.reshape(B_, [tf.shape(A)[0], tf.shape(B)[0], tf.shape(B)[1]]) #-----------------------------------------修改部分(结束)----------------------------------------- #此时就可以matmul了 C = tf.matmul(A, B) print('C:',C.get_shape().as_list()) sess.run(C)
输出结果:
('C:', [2, 3, 1]) array([[[30], [70], [20]], [[20], [60], [40]]], dtype=int32)
方案二
import numpy as npimport tensorflow as tf
sess = tf.Session()
A = np.array([[[1, 2, 3, 4],
[5, 6, 7, 8],
[9, 0, 1, 2]],
[[4, 3, 2, 1],
[8, 7, 6, 5],
[2, 1, 0, 9]]])
B = np.array([[1], [2], [3], [4]])
A = tf.cast(tf.convert_to_tensor(A), tf.int32) # shape=[2, 3, 4]
B = tf.cast(tf.convert_to_tensor(B), tf.int32) # shape=[4, 1]
#-----------------------------------------修改部分(开始)------
8ea5
-----------------------------------
#把A的前两个维度展为一个维度
A = tf.reshape(A, [-1, 4])
#此时就可以matmul了
C = tf.matmul(A, B)
# print('C:',C.get_shape().as_list()) #结果: [6, 1]
#再把C的前两个维度还原
C = tf.reshape(C, [2, 3, 1])
#-----------------------------------------修改部分(结束)-----------------------------------------
print('C:',C.get_shape().as_list())
sess.run(C)
输出结果:
('C:', [2, 3, 1])
array([[[30], [70], [20]], [[20], [60], [40]]], dtype=int32)
相关文章推荐
- tensorflow报错:Shape must be rank 2 but is rank 3 for 'MatMul' (op: 'MatMul')
- ValueError: Shape must be rank 0 but is rank 1 for 'train_data/ReadFile' (op: 'ReadFile') with input
- 180211 Keras矩阵乘法MatMul报错 Shape must be rank 2 but is rank 3 for 'MatMul'
- MPI编译C++程序出现#error "SEEK_SET is #defined but must not be for the C++ binding of MPI" 的解决方法
- MPI编译C++程序出现#error "SEEK_SET is #defined but must not be for the C++ binding of MPI" 的解决方法
- cvc-complex-type.2.4.c: The matching wildcard is strict, but no declaration can be found for element
- Openstack部署总结之:部署过程中“Error: Local ip for ovs agent must be set when tunneling is enabled”的问题
- maven引用jar报错:spring-core:jar must be a valid version but is '${spring.version}
- 关于dubbo服务的xml配置文件报错的问题--The matching wildcard is strict, but no declaration can be found for element
- 关于dubbo创建服务和引用服务时,会报错:cvc-complex-type.2.4.c: The matching wildcard is strict, but no declaration can be found for element 问题的解决
- Openstack部署总结:“部署过程Error: Local ip for ovs agent must be set when tunneling is enabled”问题
- cvc-complex-type.2.4.c: The matching wildcard is strict, but no declaration can be found for element
- dubbo配置报错:The matching wildcard is strict, but no declaration can be found for element
- According to TLD, tag fmt:formatDate must be empty, but is not 问题的解决
- SharePoint 报错: The specified file or folder name is too long. The URL path for all files and folders must be 260 characters or less
- jsp错误 According to TLD, tag form:input must be empty, but is not
- The matching wildcard is strict, but no declaration can be found for element
- According to TLD, tag s:property must be empty, but is not
- According to TLD, tag bean:write must be empty, but is not
- cvc-complex-type.2.4.c: The matching wildcard is strict, but no declaration can be found for element