code-repo-template

Toolkit for XXXX

空的代码 Repo 模板，全局替换 MFOD 即可 python setup.py develop

• Installation
  • Step 1: Create a conda environment
  • Step 2: Install PyTorch
  • Step 3: Install OpenMMLab 2.x Codebases
  • Step 4: Install MFOD
• Model Zoo and Benchmark
  • Leaderboard
  • Model Zoo
    • Method A
    • Method B

Installation

Step 1: Create a conda environment

$ conda create --name MFOD python=3.9
$ source activate MFOD

Step 2: Install PyTorch

conda install pytorch torchvision torchaudio pytorch-cuda=11.8 -c pytorch -c nvidia

Step 3: Install OpenMMLab 2.x Codebases

# openmmlab codebases
pip install -U openmim dadaptation --no-input
mim install mmengine "mmcv>=2.0.0" "mmdet>=3.0.0" "mmsegmentation>=1.0.0" "mmrotate>=1.0.0rc1" mmyolo "mmpretrain>=1.0.0rc7" 'mmagic'
# other dependencies
pip install -U ninja scikit-image --no-input

Step 4: Install MFOD

python setup.py develop

Note: make sure you have cd to the root directory of MFOD

$ git clone [email protected]:GrokCV/MFOD.git
$ cd MFOD

Model Zoo and Benchmark

Note: Both passwords for BaiduYun and OneDrive is grok.

Leaderboard

Model Zoo

Method A

Model	mAP	#Params	FLOPs	Config	Training Log	Checkpoint	Visualization
				百度网盘 | OneDirve

Method B

Model	mAP	#Params	FLOPs	Config	Training Log	Checkpoint	Visualization
				百度网盘 | OneDirve