search

tdeboissiere / DeepLearningImplementations

Implementation of recent Deep Learning papers
MIT License
1.81k stars 650 forks source link

When I run the source code, should I use TensorFlow as my backend or Theano? #9

Closed johnny5550822 closed 7 years ago

johnny5550822 commented 7 years ago

When I run the source code, should I use TensorFlow as my backend or Theano?

Because it look like it want Theano. I have an error when U try to use tf as backend.

Traceback (most recent call last):
  File "/home/kcho/lib/tensorflow/DeepLearningImplementations/DeconvNet/VGG_deconv.py", line 176, in <module>
    Dec = KerasDeconv.DeconvNet(model)
  File "/home/kcho/lib/tensorflow/DeepLearningImplementations/DeconvNet/KerasDeconv.py", line 29, in __init__
    self.x = K.T.tensor4('x')
AttributeError: 'module' object has no attribute 'T'
tdeboissiere commented 7 years ago

Yes, theano backend only for the moment. You are welcome to try a PR with tensorflow!

johnny5550822 commented 7 years ago

@tdeboissiere WHat do you mean by PR with tensorflow?

Also, for the DeconvNet/VGG_deconv.py implementation, will there by Tf backend soon?

tdeboissiere commented 7 years ago

PR = push request

I was inviting you to have a go at porting the code to the TF backend. I have no plan to do so in the foreseeable future.

johnny5550822 commented 7 years ago

@tdeboissiere Ah, I see. Ok, if I happen to do so. I will subit a pull request.