Avoid mixing `Dimension` type and `int` when defining kernel shapes in conv layers.
authorFrancois Chollet <fchollet@google.com>
Fri, 13 Apr 2018 22:33:07 +0000 (15:33 -0700)
committerTensorFlower Gardener <gardener@tensorflow.org>
Fri, 13 Apr 2018 22:37:56 +0000 (15:37 -0700)
commit026f052710475d1a5d08007e5ff7e105c653a965
treea34fc3f0573fac36ad655eadb4ce4ad26456c0ab
parenta22344f82ddd1e877f0b9f82584b9bb1d6c8dc16
Avoid mixing `Dimension` type and `int` when defining kernel shapes in conv layers.

PiperOrigin-RevId: 192834255
tensorflow/python/keras/_impl/keras/layers/convolutional.py