diffGrad: An Optimization Method for Convolutional Neural Networks

This repository contains the code for the paper in Findings of EMNLP 2021: "EfficientBERT: Progressively Searching Multilayer Perceptron via Warm-up Knowledge Distillation".

MWPToolkit is an open-source framework for math word problem(MWP) solvers.

UniLM AI - Large-scale Self-supervised Pre-training across Tasks, Languages, and Modalities

Basic exercises of chinese information processing

This repository contains demos I made with the Transformers library by HuggingFace.

pycorrector is a toolkit for text error correction. 文本纠错，Kenlm，Seq2Seq_Attention，BERT，MacBERT，ELECTRA，ERNIE，Transformer等模型实现，开箱即用。

中文自然语言处理数据集，平时做做实验的材料。欢迎补充提交合并。

𓃡 Quadruped Robot based on MIT Cheetah I

A curated list of awesome synthetic data for text location and recognition

《动手学深度学习》：面向中文读者、能运行、可讨论。中英文版被全球175所大学采用教学。

Interactive deep learning book with multi-framework code, math, and discussions. Adopted at 175 universities.

NaturalProofs: Mathematical Theorem Proving in Natural Language

A curated list of awesome resources related to Semantic Search🔎 and Semantic Similarity tasks.

A Simple 32-bit OS lab tutorial.

C++ implementation of several image contrast enhancement techniques.

[CogSci'21] Study of human inductive biases in CNNs and Transformers.

Dive into Deep Learning Compiler

[CVPR2021] Invertible Image Signal Processing

An implementation of model parallel GPT-3-like models on GPUs, based on the DeepSpeed library. Designed to be able to train models in the hundreds of billions of parameters or larger.

FID calculation with proper image resizing and quantization steps

An implementation of model parallel GPT-2 and GPT-3-style models using the mesh-tensorflow library.

本项目将《动手学深度学习》(Dive into Deep Learning)原书中的MXNet实现改为PyTorch实现。