Simplify your onnx model

A Simple and Universal Swarm Intelligence Engine, Predicting Anything. 简洁通用的群体智能引擎，预测万物

Memory Sparse Attention - 亿级（100M）token 上下文的端到端可训练记忆框架

A memory OS that makes your OpenClaw agents more personal while saving tokens.

分享 GitHub 上有趣、入门级的开源项目。Share interesting, entry-level open source projects on GitHub.

adds Sequence Parallelism into LLaMA-Factory

C++/CUDA/Python multimedia utilities for NVIDIA Jetson

Repo for counting stars and contributing. Press F to pay respect to glorious developers.

🔥🔥High-Performance Face Recognition Library on PaddlePaddle & PyTorch🔥🔥

The Level-Navi Agent, a framework that requires no training and utilizes large language models for deep query understanding and precise search operations. The repo includes benchmarks, datasets, an…

An easy to use PyTorch to TensorRT converter

Image augmentation for machine learning experiments.

A series of convenience functions to make basic image processing operations such as translation, rotation, resizing, skeletonization, and displaying Matplotlib images easier with OpenCV and Python.

Data Augmentation For Object Detection using Pytorch and PIL

Central Difference Convolutional Networks (CVPR'20)

Simple Dynamic Batching Inference

Pytorch implementation of various Knowledge Distillation (KD) methods.

中文文本分类，TextCNN，TextRNN，FastText，TextRCNN，BiLSTM_Attention，DPCNN，Transformer，基于pytorch，开箱即用。

[ICLR 2020] Contrastive Representation Distillation (CRD), and benchmark of recent knowledge distillation methods

TensorRT is a C++ library for high performance inference on NVIDIA GPUs and deep learning accelerators.

Quantized Neural Network PACKage - mobile-optimized implementation of quantized neural network operators