• Stars
    star
    120
  • Rank 295,983 (Top 6 %)
  • Language
    Python
  • License
    Apache License 2.0
  • Created over 2 years ago
  • Updated almost 2 years ago

Reviews

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Repository Details

DenseTeacher: Dense Pseudo-Label for Semi-supervised Object Detection

DenseTeacher

This project provides an implementation for our ECCV2022 paper "DenseTeacher: Dense Pseudo-Label for Semi-supervised Object Detection" on PyTorch.

Requirements

Get Started

  • install cvpods locally (requires cuda to compile)
python3 -m pip install 'git+https://github.com/Megvii-BaseDetection/cvpods.git'
# (add --user if you don't have permission)

# Or, to install it from a local clone:
git clone https://github.com/Megvii-BaseDetection/cvpods.git
python3 -m pip install -e cvpods

# Or,
pip install -r requirements.txt
python3 setup.py build develop
  • prepare datasets
cd /path/to/cvpods/datasets
ln -s /path/to/your/coco/dataset coco
  • start training
cd DenseTeacher/coco-p10
pods_train --dir .
# Evaluation will be automatically start after each epoch

Acknowledgement

This repo is developed based on cvpods. Please check cvpods for more details and features.

License

This repo is released under the Apache 2.0 license. Please see the LICENSE file for more information.

More Repositories

1

YOLOX

YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with MegEngine, ONNX, TensorRT, ncnn, and OpenVINO supported. Documentation: https://yolox.readthedocs.io/
Python
9,231
star
2

BEVDepth

Official code for BEVDepth.
Python
709
star
3

cvpods

All-in-one Toolbox for Computer Vision Research.
Python
643
star
4

DeFCN

End-to-End Object Detection with Fully Convolutional Network
Python
494
star
5

BorderDet

BorderDet: Border Feature for Dense Object Detection(ECCV2020 Oral)
Python
431
star
6

DynamicRouting

Learning Dynamic Routing for Semantic Segmentation
Python
378
star
7

BEVStereo

Official code for BEVStereo
Python
253
star
8

OTA

Official implementation of our CVPR2021 paper "OTA: Optimal Transport Assignment for Object Detection" in Pytorch.
Python
241
star
9

AutoAssign

Pytorch implementation of "AutoAssign: Differentiable Label Assignment for Dense Object Detection"
Python
140
star
10

TreeFilter-Torch

Learnable Tree Filter for Structure-preserving Feature Transform
Python
139
star
11

DisAlign

Implementation of "Distribution Alignment: A Unified Framework for Long-tail Visual Recognition"(CVPR 2021)
Python
117
star
12

Megvii-BaseDetection

You are welcomed to join us!
50
star
13

GFSD

This project provides an implementation for "Generalized Few-Shot Object Detection without Forgetting" (CVPR2021) on PyTorch.
Python
45
star
14

LLA

Official implementation of our paper "LLA: Loss-aware Label Assignment for Dense Pedestrian Detection" in Pytorch.
Python
35
star
15

4K-Face

4K-Face: A Dataset with Huge Scale-variance Faces
32
star
16

storage

provide Checkpoint for users.
1
star