zou jinyi's repositories
manutdzou.github.io
manutdzou's blog
flash-attention
Fast and memory-efficient exact attention
Lion
Lion: Adversarial Distillation of Closed-Source Large Language Model
CLIP
CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image
lama-cleaner
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.
GLIP
Grounded Language-Image Pre-training
dino
PyTorch code for Vision Transformers training with the Self-Supervised learning method DINO
ncnn
ncnn is a high-performance neural network inference framework optimized for the mobile platform
pnnx
PyTorch Neural Network eXchange
Adan
Adan: Adaptive Nesterov Momentum Algorithm for Faster Optimizing Deep Models
DeepSORT
support deepsort and bytetrack MOT(Multi-object tracking) using yolov5 with C++
pytorch-loss
label-smooth, amsoftmax, partial-fc, focal-loss, triplet-loss, lovasz-softmax. Maybe useful
munkres-cpp
Kuhn-Munkres (Hungarian) Algorithm in C++
FaceX-Zoo
A PyTorch Toolbox for Face Recognition
ByteTrack
ByteTrack: Multi-Object Tracking by Associating Every Detection Box
yolov5
YOLOv5 🚀 in PyTorch > ONNX > CoreML > TFLite
onnx-simplifier
Simplify your onnx model
CBAM.PyTorch
Non-official implement of Paper：CBAM: Convolutional Block Attention Module
onnx-tensorrt
ONNX-TensorRT: TensorRT backend for ONNX
torch2trt
An easy to use PyTorch to TensorRT converter
pytorch-distributed
A quickstart and benchmark for pytorch distributed training.
shadowsocks-windows
If you want to keep a secret, you must also hide it from yourself.
avatarify
Avatars for Zoom and Skype
Pytorch_Retinaface
Retinaface get 80.99% in widerface hard val using mobilenet0.25.
automl
Google Brain AutoML
FairMOT
A simple baseline for one-shot multi-object tracking
MoCo
A pytorch reimplement of paper "Momentum Contrast for Unsupervised Visual Representation Learning"