FinGLM: 致力于构建一个开放的、公益的、持久的金融大模型项目，利用开源开放来促进「AI+金融」。

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

医学影像数据集列表

label-smooth, amsoftmax, partial-fc, focal-loss, triplet-loss, lovasz-softmax. Maybe useful

YOLOv5 in PyTorch > ONNX > CoreML > TFLite

YOLOv5 🚀 in PyTorch > ONNX > CoreML > TFLite

Winning solution for the Kaggle TGS Salt Identification Challenge.

This is a tensorflow-based rotation detection benchmark, also called UranusDet.

A PyTorch implementation of EfficientNet

Lung Nodule segmentation from CT scan using Python

Nvidia Semantic Segmentation monorepo

Personal ubuntu misc files (e.g., zshrc, vimrc, flake8, terminator)

Official code for "Boundary loss for highly unbalanced segmentation", runner-up for best paper award at MIDL 2019. Extended version in MedIA, volume 67, January 2021.

Implement Face Recognition Code in PyTorch. Such as SphereFace with A-Softmax.

Relation-Shape Convolutional Neural Network for Point Cloud Analysis (CVPR 2019 Oral & Best paper finalist)

用keras实现OCR定位、识别

A simple code for creating licence plate images and train e2e network

M2Det: A Single-Shot Object Detector based on Multi-Level Feature Pyramid Network

sniper version for arm tiny input and network training.

SNIPER / AutoFocus is an efficient multi-scale object detection training / inference algorithm

Open3D: A Modern Library for 3D Data Processing

Feature Pyramid Network with ResNext implemented in Keras

Open3D: A Modern Library for 3D Data Processing

My code for Tianchi competition-Aluminum surface defect detection(held by Alibaba Cloud). My final rank is 10/2972(top 0.3%).