alykhantejani / nninit
Weight initialization schemes for PyTorch nn.Modules
☆70Updated 7 years ago
Related projects ⓘ
Alternatives and complementary repositories for nninit
- Batch-Normalized LSTM (Recurrent Batch Normalization) implementation in Torch.☆92Updated 8 years ago
- A pytorch implementation of "Self-Normalizing Neural Networks" by Klambauer et al. (still beta)☆59Updated 7 years ago
- Implementation of auxiliary deep generative models for semi-supervised learning☆28Updated 8 years ago
- Efficient layer normalization GPU kernel for Tensorflow☆111Updated 7 years ago
- Working Theano implementation of Pixel RNN on MNIST.☆76Updated 8 years ago
- Weight initialisation schemes for Torch7 neural network modules☆100Updated 7 years ago
- A Lasagne and Theano implementation of the paper Alireza Makhzani, Jonathon Shlens, Navdeep Jaitly, and Ian Goodfellow.☆41Updated 8 years ago
- Recurrent modules for Torch☆27Updated 8 years ago
- Lasagne code for weight normalization☆87Updated 8 years ago
- Implementation of Coulomb GANs☆62Updated 3 years ago
- Numpy format for Torch☆68Updated 7 years ago
- Architecture learning for CNN's☆37Updated 7 years ago
- A collection of Torch dataset loaders☆50Updated 8 years ago
- PixelVAE with or without regularization☆66Updated 7 years ago
- Reference implementation for Structured Prediction with Deep Value Networks☆55Updated 7 years ago
- Code for Attentive Recurrent Comparators☆57Updated 7 years ago
- [adversarial] examples and training cost☆19Updated 8 years ago
- ☆69Updated 5 years ago
- ☆93Updated 7 years ago
- Torch implementation reproducing MNIST experiments from DeepMind's DNI paper.☆44Updated 7 years ago
- Experiment files for the paper "An Analysis of Unsupervised Pre-training in Light of Recent Advances", available here: http://arxiv.org/a…☆18Updated 8 years ago
- A Torch interface for pastalog - simple, realtime visualization of neural network training performance☆45Updated 8 years ago
- Code for the "Binding via Reconstruction Clustering" paper☆21Updated 8 years ago
- Replication of the paper "Variational Dropout and the Local Reparameterization Trick" using Lasagne.☆33Updated 7 years ago
- ☆29Updated 7 years ago
- A more memory efficient Torch implementation of "Densely Connected Convolutional Networks".☆30Updated 7 years ago
- Add layer-wise learning rate schemes to Torch☆47Updated 7 years ago