Implements an efficient softmax approximation as described in the paper "Efficient softmax approximation for GPUs" (http://arxiv.org/abs/1609.04309)
☆396Mar 22, 2019Updated 6 years ago
Alternatives and similar repositories for adaptive-softmax
Users that are interested in adaptive-softmax are comparing it to the libraries listed below
Sorting:
- This library provides utilities for creating and manipulating RNNs to model sequential data.☆191Jul 28, 2017Updated 8 years ago
- Mixed Incremental Cross-Entropy REINFORCE ICLR 2016☆333Mar 1, 2017Updated 9 years ago
- Code and models from the paper "Layer Normalization"☆243Nov 8, 2016Updated 9 years ago
- Recurrent Highway Networks - Implementations for Tensorflow, Torch7, Theano and Brainstorm☆401Oct 9, 2019Updated 6 years ago
- Batch-Normalized LSTM (Recurrent Batch Normalization) implementation in Torch.☆90May 22, 2016Updated 9 years ago
- Torch-twrl is a package that enables reinforcement learning in Torch.☆250May 27, 2017Updated 8 years ago
- ☆58May 26, 2016Updated 9 years ago
- deep extensions to nn☆193May 26, 2017Updated 8 years ago
- Torch implementation reproducing MNIST experiments from DeepMind's DNI paper.☆44Mar 4, 2017Updated 8 years ago
- The experiment result of LSTM language models on PTB (Penn Treebank) and GBW (Google Billion Word) using AdaptiveSoftmax on TensorFlow.☆99Oct 17, 2018Updated 7 years ago
- Low precision Torch nn library using uint8_t GEMM (experiment)☆19Mar 13, 2016Updated 9 years ago
- TargetProp for RNNs☆27Mar 22, 2019Updated 6 years ago
- Sequence-to-sequence model with LSTM encoder/decoders and attention☆1,282Dec 30, 2020Updated 5 years ago
- Torch implementation of seq2seq machine translation with GRU RNN and attention☆77Dec 4, 2016Updated 9 years ago
- A set of primitives for parallel computation in Torch☆95Oct 21, 2021Updated 4 years ago
- OptNet - Reducing memory usage in torch neural nets☆282Apr 19, 2017Updated 8 years ago
- Simple PuddleWorld DQN example using torch7☆29Jun 16, 2016Updated 9 years ago
- Implementation of the paper [Using Fast Weights to Attend to the Recent Past](https://arxiv.org/abs/1610.06258)☆174Nov 3, 2016Updated 9 years ago
- An implementation of the deep convolutional generative adversarial network, combined with a varational autoencoder☆109Mar 18, 2017Updated 8 years ago
- Deep Networks with Stochastic Depth☆481Aug 13, 2018Updated 7 years ago
- Faster-RCNN based on Densecap(deprecated)☆84Sep 12, 2016Updated 9 years ago
- Recurrent Neural Network library for Torch7's nn☆943Dec 21, 2017Updated 8 years ago
- Generate captions for an image using convolutional and recurrent networks☆12Feb 25, 2016Updated 10 years ago
- Learning What and Where to Draw☆336Nov 1, 2016Updated 9 years ago
- Reinforcement learning environments for Torch7☆91Dec 15, 2016Updated 9 years ago
- Review Network for Caption Generation☆181Jan 2, 2018Updated 8 years ago
- ByteNet for character-level language modelling☆318Aug 23, 2017Updated 8 years ago
- Use torch in python for deep learning.☆233Feb 9, 2017Updated 9 years ago
- Fast Recurrent Networks Library☆578Sep 20, 2016Updated 9 years ago
- Autograd automatically differentiates native Torch code☆559Oct 21, 2021Updated 4 years ago
- Torch7 implementation of Grid LSTM as described here: http://arxiv.org/pdf/1507.01526v2.pdf☆186Feb 10, 2016Updated 10 years ago
- Torch implementations of various types of autoencoders☆476Aug 28, 2017Updated 8 years ago
- ☆21May 24, 2016Updated 9 years ago
- Weight initialisation schemes for Torch7 neural network modules☆100Jun 21, 2017Updated 8 years ago
- torch data augmentation toolbox (supports affine transform)☆54May 29, 2017Updated 8 years ago
- Memory Networks implementations☆1,753Jul 28, 2020Updated 5 years ago
- This is the project for LS-GAN (Loss-Sensitive GAN)☆215Mar 12, 2017Updated 8 years ago
- PyTorch implementation of the Quasi-Recurrent Neural Network - up to 16 times faster than NVIDIA's cuDNN LSTM☆1,265Feb 12, 2022Updated 4 years ago
- Training RNNs as Fast as CNNs (https://arxiv.org/abs/1709.02755)☆2,113Jan 4, 2022Updated 4 years ago