錯誤一
在反捲積tf.nn.covn2d_transpose時報錯:輸入和計算的輸入梯度類型不匹配
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)
檢查了下,卷積核大小和輸入大小都沒錯,這怎麼解釋
問題已解決:改了output_shape
錯誤二
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)]]
改完一又出來二,上哪說理去。。。