TensorFlow错误

错误一

在反卷积tf.nn.covn2d_transpose时报错：输入和计算的输入梯度类型不匹配

ValueError: Incompatible shapes between op input and calculated input gradient.  Forward operation: inference/conv2d_transpose_3.  Input index: 2. Original input shape: (?, 115, 115, 64).  Calculated input gradient shape: (?, 124, 124, 64)

检查了下，卷积核大小和输入大小都没错，这怎么解释

问题已解决：改了output_shape

 

 

错误二

InvalidArgumentError (see above for traceback): Conv2DSlowBackpropInput: Size of out_backprop doesn't match computed: actual = 13, computed = 14spatial_dim: 1 input: 27 filter: 3 output: 13 stride: 2 dilation: 1
         [[Node: inference/conv2d_transpose = Conv2DBackpropInput[T=DT_FLOAT, data_format="NHWC", padding="SAME", strides=[1, 2, 2, 1], use_cudnn_on_gpu=true, _device="/job:localhost/replica:0/task:0/device:GPU:0"](inference/stack, inference/Variable_10/read, inference/MaxPool_3)]]

 

改完一又出来二，上哪说理去。。。