Alan's repositories
deit
Official DeiT repository
detectron2
Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.
difflogic
A Library for Differentiable Logic Gate Networks
FGD
Focal and Global Knowledge Distillation for Detectors (CVPR 2022)
DMAE
[CVPR 2023] This repository includes the official implementation our paper "Masked Autoencoders Enable Efficient Knowledge Distillers"
External-Attention-pytorch
🍀 Pytorch implementation of various Attention Mechanisms, MLP, Re-parameter, Convolution, which is helpful to further understand papers.⭐⭐⭐
FasterViT
Official PyTorch implementation of FasterViT: Fast Vision Transformers with Hierarchical Attention
FastestDet
:zap: A newly designed ultra lightweight anchor free target detection algorithm， weight only 250K parameters， reduces the time consumption by 10% compared with yolo-fastest, and the post-processing is simpler
flash-attention
Fast and memory-efficient exact attention
ISTDU-Net
code of article ISTDU-Net：Infrared Small-Target Detection U-Net
labelme
Image Polygonal Annotation with Python (polygon, rectangle, circle, line, point and image-level flag annotation).
LD
Localization Distillation for Dense Object Detection (CVPR 2022)
LSHFM.detection
Object detection of Distilling Knowledge by Mimicking Features.
multispectral-object-detection
Multispectral Object Detection with Yolov5 and Transformer
prepare_detection_dataset
convert dataset to coco/voc format
pytorch-loss
label-smooth, amsoftmax, partial-fc, focal-loss, triplet-loss, lovasz-softmax. Maybe useful
QueryDet-PyTorch
[CVPR 2022 Oral] QueryDet: Cascaded Sparse Query for Accelerating High-Resolution Small Object Detection
tiny-training
On-Device Training Under 256KB Memory [NeurIPS'22]
torchdistill
A coding-free framework built on PyTorch for reproducible deep learning studies. 🏆20 knowledge distillation methods presented at CVPR, ICLR, ECCV, NeurIPS, ICCV, etc are implemented so far. 🎁 Trained models, training logs and configurations are available for ensuring the reproducibiliy and benchmark.
vovnet-detectron2
VoVNet backbone networks for detectron2, in CVPR 2020
Yolo-Fastest
:zap: Based on yolo's ultra-lightweight universal target detection algorithm, the calculation amount is only 250mflops, the ncnn model size is only 666kb, the Raspberry Pi 3b can run up to 15fps+, and the mobile terminal can run up to 178fps+
Yolo_Detectron2
Implementation of Yolo using Facebook's Detectron2 (https://github.com/facebookresearch/detectron2) Framework with Quantization support based on AQD: Towards Accurate Quantized Object Detection (https://github.com/aim-uofa/model-quantization)
yoloret
Implementation for the paper 'YOLO-ReT: Towards High Accuracy Real-time Object Detection on Edge GPUs'
yolov5-gradcam
Visualizing Yolov5's layers using GradCam
ZZUClock
郑大健康状况上报平台脚本