TypeError: Input 'input_sizes' of 'Conv2DBackpropInput' Op has type float32 that does not match expected type of int32.

[fabrahman]

Hello,

When running train.py I got this error which raise from deconv2d:

During handling of the above exception, another exception occurred:

Traceback (most recent call last): File "train.py", line 128, in main(args) File "train.py", line 112, in main model = network(args) File "/home/hannahbrahman/ADV ML CMPS 290/GANS/ImageCompletion_IncompleteData/network.py", line 16, in init self.build_model() File "/home/hannahbrahman/ADV ML CMPS 290/GANS/ImageCompletion_IncompleteData/network.py", line 28, in build_model self.X_g, self.g_nets = self.completion_net(self.Y_r, name="generator") File "/home/hannahbrahman/ADV ML CMPS 290/GANS/ImageCompletion_IncompleteData/network.py", line 165, in completion_net deconv1 = deconv2d(conv8, 4, [self.batch_size, input_shape[1]/2, input_shape[2]/2, 128], name="deconv1") File "/home/hannahbrahman/ADV ML CMPS 290/GANS/ImageCompletion_IncompleteData/architecture.py", line 50, in deconv2d strides=[1, 2, 2, 1]) File "/soe/hannahbrahman/anaconda3/lib/python3.6/site-packages/tensorflow/python/ops/nn_ops.py", line 1048, in conv2d_transpose name=name) File "/soe/hannahbrahman/anaconda3/lib/python3.6/site-packages/tensorflow/python/ops/gen_nn_ops.py", line 486, in conv2d_backprop_input data_format=data_format, name=name) File "/soe/hannahbrahman/anaconda3/lib/python3.6/site-packages/tensorflow/python/framework/op_def_library.py", line 513, in apply_op (prefix, dtypes.as_dtype(input_arg.type).name)) TypeError: Input 'input_sizes' of 'Conv2DBackpropInput' Op has type float32 that does not match expected type of int32.

Anyone has any idea to fix?

[gonwalk]

I have encountered the same problem. Have you solved it?

[Yonv1943]

I have encountered the same problem. Have you solved it?

"Op has type float32 that does not match expected type of int32."

When I convert the codes from Python2 to Python3, I met the same problem.

netwrok.py line 165 deconv1 = deconv2d(conv8, 4, [self.batch_size, input_shape[1]/2, input_shape[2]/2, 128], name="deconv1")

input_shape[1]/2 ↓ input_shape[1]//2

problem solved