'TensorVariable' object has no attribute '_shape'

[raghakot]

'TensorVariable' object has no attribute '_shape'

[raghakot]

I tested it with tensor flow. I wonder if it needs more changes to work with theano. I will try it out and let u know soon.

Sent from Outlook Mobilehttps://aka.ms/qtex0l

On Sat, Apr 23, 2016 at 3:32 AM -0700, "Marko Jocić" <[email protected]mailto:[email protected]> wrote:

Hey Ragha, thank you for sharing this, nice job!

I'm having difficulties running your example. I'm using latest versions of Keras and Theano.

File "train_resnet.py", line 139, in
model = resnet()
File "resnet.py", line 110, in resnet
block1 = _residual_block(block_fn, nb_filters=64, repetations=3, is_first_layer=True)(pool1)
File "resnet.py", line 93, in f
input = block_function(nb_filters=nb_filters, init_subsample=init_subsample)(input)
File "resnet.py", line 50, in f
return _shortcut(input, residual)
File "resnet.py", line 72, in _shortcut
stride_width = input._shape[2].value / residual._shape[2].value
AttributeError: 'TensorVariable' object has no attribute '_shape'

Would you mind letting me know if have to do anything more in order to run your implementation of ResNet?

Thank you in advance,
Marko

You are receiving this because you are subscribed to this thread.
Reply to this email directly or view it on GitHubhttps://github.com//issues/1

[raghakot]

This should now be fixed. Try and let me know.

[jocicmarko]

I appreciate your effort, I also fixed the issue myself.

Thanks again and best regards,
Marko