Official Implementation of OCR-free Document Understanding Transformer (Donut) and Synthetic Document Generator (SynthDoG), ECCV 2022

Open Academic Research on Improving LLaMA to SOTA LLM

🐙 Guides, papers, lecture, notebooks and resources for prompt engineering

[ICCV 2023] Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation

Master programming by recreating your favorite technologies from scratch.

Efficient, scalable and enterprise-grade CPU/GPU inference server for 🤗 Hugging Face transformer models 🚀

Implementation of RLHF (Reinforcement Learning with Human Feedback) on top of the PaLM architecture. Basically ChatGPT but with PaLM

A tool convert TensorRT engine/plan to a fake onnx

YOLOv8 using TensorRT accelerate !

Code and documentation to train Stanford's Alpaca models, and generate the data.

🎯 AI Zero to Hero 👑

Code for the paper "MASTER: Multi-Aspect Non-local Network for Scene Text Recognition" (Pattern Recognition 2021)

NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source components of TensorRT.

Making large AI models cheaper, faster and more accessible

Pix2Seq codebase: multi-tasks with generative modeling (autoregressive and diffusion)

Ultralytics YOLO11 🚀

A synthetic data generator for text recognition

Differentiable IoU of rotated bounding boxes using Pytorch

deep learning for image processing including classification and object-detection etc.

深度学习论文翻译，包括分类论文，检测论文等

深度学习工程模板

A collection of libraries to optimise AI model performances

YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with MegEngine, ONNX, TensorRT, ncnn, and OpenVINO supported. Documentation: https://yolox.readthedocs.io/

Model Quantization Benchmark

YOLOv5 Series Multi-backbone(TPH-YOLOv5, Ghostnet, ShuffleNetv2, Mobilenetv3Small, EfficientNetLite, PP-LCNet, SwinTransformer YOLO), Module(CBAM, DCN), Pruning (EagleEye, Network Slimming), Quanti…

A model compression and acceleration toolbox based on pytorch.

PPL Quantization Tool (PPQ) is a powerful offline neural network quantization tool.

Open-sourced codes for MiniGPT-4 and MiniGPT-v2 (https://minigpt-4.github.io, https://minigpt-v2.github.io/)

Chinese version of CLIP which achieves Chinese cross-modal retrieval and representation generation.