PyGlow
PyGlow copied to clipboard
spino17
This package is an attempt to implement Keras like API functionalities on PyTorch backend with functionalities supporting information theoretic methods which are relevant for understanding neural netw...
I get this error when compiling and training the model on MNIST dataset on Google Colab using their GPU. `model = IBSequential(input_shape=(1, 28, 28), gpu=True, track_dynamics=True, save_dynamics=True) model.add(Conv2d(filters=16, kernel_size=3, stride=1,...
I was running the test code in the page https://pyglow.github.io/ on google colab. It gave me this error: ``` --------------------------------------------------------------------------- AttributeError Traceback (most recent call last) in () 35 36...
Corrected EDGE estimator implementation in `glow.information_bottleneck`. - Updated `addcdiv` utility to match the updated format. - Function `g_hat = min{g(w), U}` had `U` optional. `g(w)` can be used instead if...
Implement KNN, KSG, KDE and Parzen Windom estimation methods in information bottleneck module.
Base implementations for HSIC networks is available. Using that implement HSIC sigma networks as a classifier.
Implementations for Deep variational information bottleneck encoders and other related models.
Throughout the code there are comments as - ** NOTE - This can be done in parallel ! Which means that the loop can be done in parallel with instruction...
Current implementation uses sequential training of all the models of sigma network but it would massively speed up the computation if those models can be trained parallely.
Currently PyGlow uses tqdm progress bar api but it would be more natural to implement one just like keras (Note: to see keras implementation of progress bar see generic_utils in...