Несовместимое измерение при обучении модели - PullRequest
0 голосов
/ 26 февраля 2020
ValueError                                Traceback (most recent call last)

<ipython-input-71-b60a6fe1387d> in <module>()
      1 print("[INFO] building autoencoder...")
----> 2 (encoder, decoder, autoencoder) = ConvAutoencoder.build(4,132, 132, 132)
      3 opt = Adam(lr=1e-3)
      4 autoencoder.compile(loss="mse", optimizer=opt)
      5 # train the convolutional autoencoder

2 frames

/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/keras/engine/input_spec.py in assert_input_compatibility(input_spec, inputs, layer_name)
    175                          'expected ndim=' + str(spec.ndim) + ', found ndim=' +
    176                          str(ndim) + '. Full shape received: ' +
--> 177                          str(x.shape.as_list()))
    178     if spec.max_ndim is not None:
    179       ndim = x.shape.ndims

ValueError: Input 0 of layer conv3d_transpose_10 is incompatible with the layer: expected ndim=5, found ndim=4. Full shape received: [None, 128, 17, 17]

this is error showing :

это 3D CNN, где я передаю inputize = (4,132,132,132), но это показывает ошибку выше

...