yangsuhui's repositories
ByteTrack
ByteTrack: Multi-Object Tracking by Associating Every Detection Box
CenterTrack
Simultaneous object detection and tracking using center points.
ClothingTransfer-NCNN
CT-Net, OpenPose, LIP_JPPNet, DensePose running with ncnn⚡服装迁移/虚拟试穿⚡ClothingTransfer/Virtual-Try-On⚡
Cream
This is a collection of our NAS and Vision Transformer work.
Crop-CLIP
Crop using CLIP
Detic
Code release for "Detecting Twenty-thousand Classes using Image-level Supervision".
Dlib_face_recognition_from_camera
Detect and recognize the faces from camera / 调用摄像头进行人脸识别，支持多张人脸同时识别
facebook-image-similarity-challenge-2021
Facebook Image Similarity Challenge 2021
GCN_classification
Multi-Modal Reasoning Graph for Scene-Text Based Fine-Grained Image Classification and Retrieval
Image-Adaptive-YOLO
The code for "Image-Adaptive YOLO for Object Detection in Adverse Weather Conditions (AAAI 2022)"
ISC-Track1-Submission
[NeurIPS Challenge Rank 1st] The codes and related files to reproduce the results for Image Similarity Challenge Track 1.
ISC-Track2-Submission
[NeurIPS Challenge Rank 3rd] The codes and related files to reproduce the results for Image Similarity Challenge Track 2.
ISC21-Descriptor-Track-1st
The 1st Place Solution of the Facebook AI Image Similarity Challenge (ISC21) : Descriptor Track.
kaggle-happywhale-1st-place
1st place solution for Kaggle "Happywhale - Whale and Dolphin Identification"
Knowledge-Distillation-Zoo
Pytorch implementation of various Knowledge Distillation (KD) methods.
LD
Localization Distillation for Dense Object Detection
MedicalGPT
MedicalGPT: Training Your Own Medical GPT Model with ChatGPT Training Pipeline. 训练医疗大模型，实现了包括增量预训练、有监督微调、RLHF(奖励建模、强化学习训练)和DPO(直接偏好优化)。
nanodet-1
⚡Super fast and lightweight anchor-free object detection model. 🔥Only 980 KB(int8) / 1.8MB (fp16) and run 97FPS on cellphone🔥
Non-local_pytorch
Implementation of Non-local Block.
pix-plot
A WebGL viewer for UMAP or TSNE-clustered images
RepDistiller
[ICLR 2020] Contrastive Representation Distillation (CRD), and benchmark of recent knowledge distillation methods
SUOD
(MLSys' 21) An Acceleration System for Large-scare Unsupervised Heterogeneous Outlier Detection (Anomaly Detection)
Torch-Pruning
Pruning channels for model acceleration
UniAD
[CVPR 2023 Best Paper] Planning-oriented Autonomous Driving