Fast and memory-efficient exact attention

Lion: Adversarial Distillation of Closed-Source Large Language Model

CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image

Image inpainting tool powered by SOTA AI Model. Remove any unwanted object, defect, people from your pictures or erase and replace(powered by stable diffusion) any thing on your pictures.

Grounded Language-Image Pre-training

PyTorch code for Vision Transformers training with the Self-Supervised learning method DINO

ncnn is a high-performance neural network inference framework optimized for the mobile platform

PyTorch Neural Network eXchange

Adan: Adaptive Nesterov Momentum Algorithm for Faster Optimizing Deep Models

support deepsort and bytetrack MOT(Multi-object tracking) using yolov5 with C++

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

Kuhn-Munkres (Hungarian) Algorithm in C++

A PyTorch Toolbox for Face Recognition

ByteTrack: Multi-Object Tracking by Associating Every Detection Box

YOLOv5 🚀 in PyTorch > ONNX > CoreML > TFLite

Simplify your onnx model

Non-official implement of Paper：CBAM: Convolutional Block Attention Module

ONNX-TensorRT: TensorRT backend for ONNX

An easy to use PyTorch to TensorRT converter

A quickstart and benchmark for pytorch distributed training.

If you want to keep a secret, you must also hide it from yourself.

Avatars for Zoom and Skype

Retinaface get 80.99% in widerface hard val using mobilenet0.25.

Google Brain AutoML

A simple baseline for one-shot multi-object tracking

A pytorch reimplement of paper "Momentum Contrast for Unsupervised Visual Representation Learning"