alykhantejani / nninitLinks
Weight initialization schemes for PyTorch nn.Modules
☆70Updated 8 years ago
Alternatives and similar repositories for nninit
Users that are interested in nninit are comparing it to the libraries listed below
Sorting:
- Batch-Normalized LSTM (Recurrent Batch Normalization) implementation in Torch.☆90Updated 9 years ago
- A pytorch implementation of "Self-Normalizing Neural Networks" by Klambauer et al. (still beta)☆59Updated 7 years ago
- Weight initialisation schemes for Torch7 neural network modules☆100Updated 7 years ago
- Code for Attentive Recurrent Comparators☆57Updated 8 years ago
- ☆29Updated 8 years ago
- Working Theano implementation of Pixel RNN on MNIST.☆76Updated 8 years ago
- Implementation of auxiliary deep generative models for semi-supervised learning☆28Updated 9 years ago
- Learning RNN Hierarchies☆44Updated 8 years ago
- PixelVAE with or without regularization☆66Updated 7 years ago
- Implementation of Coulomb GANs☆62Updated 3 years ago
- Lasagne code for weight normalization☆88Updated 9 years ago
- A PyTorch implementation of Recurrent Additive Networks by Lee et al. (2017)☆29Updated 7 years ago
- D-NTM paper repo☆25Updated 8 years ago
- Reference implementation for Structured Prediction with Deep Value Networks☆55Updated 7 years ago
- ☆69Updated 6 years ago
- ☆38Updated 8 years ago
- Torch implementation reproducing MNIST experiments from DeepMind's DNI paper.☆43Updated 8 years ago
- Replication of the paper "Variational Dropout and the Local Reparameterization Trick" using Lasagne.☆33Updated 7 years ago
- A collection of Torch dataset loaders☆50Updated 8 years ago
- Deep Dashboard: Machine Learning Training Visualizer☆44Updated 8 years ago
- [adversarial] examples and training cost☆19Updated 8 years ago
- ☆9Updated 8 years ago
- Torch implementation of the Deep Network for Global Optimization (DNGO)☆51Updated 8 years ago
- A Torch interface for pastalog - simple, realtime visualization of neural network training performance☆45Updated 8 years ago
- Tensorflow Implementation on "The Cramer Distance as a Solution to Biased Wasserstein Gradients" (https://arxiv.org/pdf/1705.10743.pdf)☆125Updated 7 years ago
- ☆33Updated 3 years ago
- ☆31Updated 8 years ago
- Architecture learning for CNN's☆37Updated 8 years ago
- Pytorch implementation of "Forward Thinking: Building and Training Neural Networks One Layer at a Time"☆66Updated 7 years ago
- DNI(Decoupled Neural Interfaces using Synthetic Gradients) implementation with Torch☆29Updated 8 years ago