Input dimensions mismatch

[anujgupta82]

In keras_transfer_cifar10.ipynb
When you train a shallow net

      model.add(Conv2D(filters=100, kernel_size=2, input_shape=features.shape[1:]))

features since they come from bottle neck, they are of dimensions [:, 2048]
The above code line is trying to run a 2D CNN on this ?

[smiler96]

In keras_transfer_cifar10.ipynb
When you train a shallow net

      model.add(Conv2D(filters=100, kernel_size=2, input_shape=features.shape[1:]))

features since they come from bottle neck, they are of dimensions [:, 2048]
The above code line is trying to run a 2D CNN on this ?

have you solved it ? also i came across the same problem.