sockeye
Sequence-to-sequence framework
An open-source sequence-to-sequence framework for neural machine translation built on PyTorch.
Sequence-to-sequence framework with a focus on Neural Machine Translation based on PyTorch
1k stars
50 watching
323 forks
Language: Python
last commit: 5 months ago
Linked from 1 awesome list
attention-is-all-you-needattention-mechanismattention-modeldeep-learningdeep-neural-networksencoder-decodermachine-learningmachine-translationneural-machine-translationpytorchseq2seqsequence-to-sequencesequence-to-sequence-modelssockeyetransformertransformer-architecturetransformer-networktranslation
Related projects:
Repository | Description | Stars |
---|---|---|
| Provides tools and frameworks for training sequence-to-sequence models using PyTorch | 523 |
| A PyTorch-based framework for building and training sequence-to-sequence models | 1,499 |
| An attention-based sequence-to-sequence learning framework | 389 |
| A PyTorch implementation of 2D convolutional neural networks for sequence-to-sequence prediction in machine translation | 502 |
| An implementation of a sequence-to-sequence model with attention mechanism using LSTMs and character embeddings for neural machine translation | 1,263 |
| A toolkit for training custom sequence-to-sequence models for various NLP tasks | 30,675 |
| Automates generation of discrete sequence text using adversarially regularized autoencoders | 20 |
| An implementation of Sequence to Sequence models in PyTorch with various attention mechanisms and extensions for machine translation tasks. | 738 |
| A comprehensive Python library for developing state-of-the-art sequence understanding models, providing pre-trained models and tools for natural language processing tasks. | 426 |
| A Pytorch implementation of a neural network model for machine translation | 47 |
| Deep learning framework for spiking neural networks | 685 |
| An implementation of unsupervised learning for multi-frame optical flow with occlusions using PyTorch. | 112 |
| A PyTorch-based tool for sequence labeling using a combination of CRF and LSTM models to capture label dependencies and leverage contextualized representations. | 846 |
| Enhances PyTorch modules by adding sequence step layers with implicit parentheses and supports custom activation functions. | 9 |
| An open-source deep learning framework for time series forecasting and analysis | 2,080 |