weightnorm
weightnorm copied to clipboard
openai
Example code for Weight Normalization, from "Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural Networks"
I'm able to get a summary of the model and while using the adam optimizer, I'm able to train the model. But while using the SGDWithWeightNorm, I'm getting an error....
Traceback (most recent call last): File "C:\Users\vkswa\Downloads\weightnorm\cifar10_cnn.py", line 67, in validation_data=(x_test, y_test)) File "C:\Users\vkswa\AppData\Local\Programs\Python\Python36\lib\site-packages\keras\engine\training.py", line 1008, in fit self._make_train_function() File "C:\Users\vkswa\AppData\Local\Programs\Python\Python36\lib\site-packages\keras\engine\training.py", line 498, in _make_train_function loss=self.total_loss) TypeError: get_updates() missing 1...
This PR contains the required changes to get `SGDWithWeightnorm` and `AdamWithWeightnorm` running with Keras 2.2.3 and Tensorflow 1.11.0. I tested `cifar10_cnn.py` with both updated optimizers and training shows reasonable convergence....
Hi, I have a simple Keras CNN working fine as it is. When trying to apply weightnorm, either with SGD or Adam, the first updated weights are all always return...
https://github.com/openai/weightnorm/blob/dff0cd132e9c6e0a31b76cb243d47a07e0c453cc/tensorflow/nn.py#L188 I've been re-implementing ImprovedGAN for semi-supervised learning for cifar10 using nn.py. This line is defining a variable by initializing it by a tensor from the build-up graph. Initializing a...
Fixed compatibility issues when running with newer version of Keras. Fix has been tested to run on Keras v. 2.1.2 and Tensorflow 1.4.0
hi, I am doing some topic in deep metric learning and I have some proof the normalization for the fully connected layer can help us. But I am wondering whether...
It seems that the weight norm code for keras uses tensorflow backend. I try to modify it as a theano backend based code, but failed. So hope to release a...
