asappresearch / sru
Training RNNs as Fast as CNNs (https://arxiv.org/abs/1709.02755)
☆2,106Updated 2 years ago
Related projects ⓘ
Alternatives and complementary repositories for sru
- PyTorch implementation of the Quasi-Recurrent Neural Network - up to 16 times faster than NVIDIA's cuDNN LSTM☆1,259Updated 2 years ago
- An open source framework for seq2seq models in PyTorch.☆1,498Updated last year
- LSTM and QRNN Language Model Toolkit for PyTorch☆1,960Updated 2 years ago
- ☆3,609Updated 2 years ago
- Facebook AI Research Sequence-to-Sequence Toolkit☆3,743Updated 3 years ago
- Sequence to Sequence Models with PyTorch☆736Updated 2 years ago
- Phrase-Based & Neural Unsupervised Machine Translation☆1,506Updated 3 years ago
- Sequence-to-sequence model with LSTM encoder/decoders and attention☆1,259Updated 3 years ago
- Dynamic seq2seq in TensorFlow, step by step☆996Updated 7 years ago
- Examples of using sparse attention, as in "Generating Long Sequences with Sparse Transformers"☆1,524Updated 4 years ago
- Tutorials and implementations for "Self-normalizing networks"☆1,583Updated 2 years ago
- Sequence to Sequence Learning with Keras☆3,168Updated 2 years ago
- InferSent sentence embeddings☆2,280Updated 3 years ago
- Framework for building complex recurrent neural networks with Keras☆765Updated 2 years ago
- Basic Utilities for PyTorch Natural Language Processing (NLP)☆2,213Updated last year
- Implementation of Sequence Generative Adversarial Nets with Policy Gradient☆2,091Updated 5 years ago
- Deep learning with dynamic computation graphs in TensorFlow☆1,827Updated 3 years ago
- The Natural Language Decathlon: A Multitask Challenge for NLP☆2,344Updated 9 months ago
- Single Headed Attention RNN - "Stop thinking with your head"☆1,178Updated 2 years ago
- PyTorch implementation of "Efficient Neural Architecture Search via Parameters Sharing"☆2,704Updated last year
- TensorFlow implementation of Independently Recurrent Neural Networks☆516Updated 3 years ago
- Go to https://github.com/pytorch/tutorials - this repo is deprecated and no longer maintained☆4,523Updated 3 years ago
- Sequence-to-Sequence learning using PyTorch☆523Updated 4 years ago
- TensorFlow Code for paper "Efficient Neural Architecture Search via Parameter Sharing"☆1,582Updated 5 years ago
- Various tutorials given for welcoming new students at MILA.☆985Updated 6 years ago
- LSTM language model with CNN over characters☆826Updated 8 years ago
- Pervasive Attention: 2D Convolutional Networks for Sequence-to-Sequence Prediction☆501Updated 3 years ago
- A PyTorch implementation of the NIPS 2017 paper "Dynamic Routing Between Capsules".☆1,731Updated 6 years ago
- Unsupervised Language Modeling at scale for robust sentiment classification☆1,061Updated 4 years ago