jack1yang
Follow
Stars
A toolkit for developing and comparing reinforcement learning algorithms.
The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (V…
OpenMMLab Detection Toolbox and Benchmark
中文LLaMA&Alpaca大语言模型+本地CPU/GPU训练部署 (Chinese LLaMA & Alpaca LLMs)
Python bindings for FFmpeg - with complex filtering support
中文LLaMA-2 & Alpaca-2大模型二期项目 + 64K超长上下文模型 (Chinese LLaMA-2 & Alpaca-2 LLMs with 64K long context models)
A series of large language models developed by Baichuan Intelligent Technology
label-smooth, amsoftmax, partial-fc, focal-loss, triplet-loss, lovasz-softmax. Maybe useful
PyTorch implementation of SwAV https//arxiv.org/abs/2006.09882
一个用于提取简体中文字符串中省，市和区并能够进行映射，检验和简单绘图的python模块
A PyTorch-based library for semi-supervised learning (NeurIPS'21)
[CVPR 2021] Involution: Inverting the Inherence of Convolution for Visual Recognition, a brand new neural operator
Unofficial pytorch implementation for Self-critical Sequence Training for Image Captioning. and others.
This repository contains code for the paper "Decoupling Representation and Classifier for Long-Tailed Recognition", published at ICLR 2020
基于深度学习的肿瘤辅助诊断系统，以图像分割为核心，利用人工智能完成肿瘤区域的识别勾画并提供肿瘤区域的特征来辅助医生进行诊断。有完整的模型构建、后端架设、工业级部署和前端访问功能。TensorRT、PyTorch 、OpenCV 、Flask、Vue
Code for Neural Motifs: Scene Graph Parsing with Global Context (CVPR 2018)
PyTorch implementation of EfficientNetV2 family
Awesome AI Memory | LLM Memory | A curated knowledge base on AI memory for LLMs and agents, covering long-term memory, reasoning, retrieval, and memory-native system design. Awesome-AI-Memory 是一个 集…
Show, Control and Tell: A Framework for Generating Controllable and Grounded Captions. CVPR 2019
Code for Unsupervised Image Captioning
Yet another easy-to-use tool to extract frames from videos, for deep learning and computer vision.
Pytorch implementation of three Multiple Instance Learning or Multi-classification papers
PyTorch-style and human-readable RegNet with a spectrum of pre-trained models
A Hierarchical Approach for Generating Descriptive Image Paragraphs