This is your work, valued
I am Machine Learning Researcher interested in Natural Language Processing, Generative Models and Deep Learning.
CopyNet. incorporating copying mechanism in sequence-to-sequence learning
180Squirrel. PyTorch implementation of Transformer-based Neural Machine Translation
77NA-NMT. Non-autoregressive Neural Machine Translation (not a full version)
70MetaNMT. Meta learning for Neural Machine Translation
41Efficient-Neural-Machine-Translation. PhD thesis (updating) of Jiatao Gu from HKU
19SEG-NMT. Search Engine Guided Non-Parametric Neural Machine Translation
14NMT-RDPG. Neural machine translation with Recurrent Deterministic Policy Gradient
10DepthwiseConv2d. Efficient implementation of Depthwise Conv2d. The main code is from https://github.com/MegEngine
7lm_decoder. Simple decoding with n-gram language model (KenLM)
5Dep-Compo. A dependency based RNN composition methods for phrases and sentences.
5fairseq-stable. Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
3splatter-image. Official implementation of `Splatter Image: Ultra-Fast Single-View 3D Reconstruction'
2ProgressiveDust3R. Official implementation of Continuous 3D Perception Model with Persistent State
1threestudio. A unified framework for 3D content generation.
1image2edge. image to edge with pidinet
1NLPMetrics. Python code for various NLP metrics
1pytorch-pretrained-BERT. A PyTorch implementation of Google AI's BERT model provided with Google's pre-trained models, examples and utilities.
1dl4mt-material. Python
1tiny-cuda-nn. Lightning fast & tiny C++/CUDA neural network framework
1reformer-pytorch. Reformer, the efficient Transformer, in Pytorch
1NVAE. The Official PyTorch Implementation of "NVAE: A Deep Hierarchical Variational Autoencoder" (NeurIPS 2020 spotlight paper)
1ItChat. A complete and graceful API for Wechat. 微信个人号接口、微信机器人及命令行微信,三十行即可自定义个人号机器人。
1debug.github.io. Jiatao Gu's homepage.
1stable-dreamfusion. A working implementation of text-to-3D dreamfusion, powered by stable diffusion.
1lpips-pytorch. A simple and useful implementation of LPIPS.
1