HZAI-ZJNU / Mamba-YOLO

the official pytorch implementation of “Mamba-YOLO:SSMs-based for Object Detection”

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Mamba-YOLO

Official pytorch implementation of “Mamba-YOLO:SSMs-based for Object Detection”

Python 3.11 pytorch 2.3.0 docs

Installation

# pip install required packages
conda create -n mambayolo -y python=3.11
conda activate mambayolo
pip3 install torch===2.3.0 torchvision torchaudio
pip install seaborn thop timm einops
cd selective_scan && pip install . && cd ..
pip install -v -e .

Training

python mbyolo_train.py --task train --data ultralytics/cfg/datasets/coco.yaml \
 --config ultralytics/cfg/models/v8/mamba-yolo.yaml \
--amp  --project ./output_dir/mscoco --name mambayolo_n

Acknowledgement

This repo is modified from open source real-time object detection codebase Ultralytics. The selective-scan from VMamba.

About

the official pytorch implementation of “Mamba-YOLO:SSMs-based for Object Detection”

License:Apache License 2.0


Languages

Language:Python 87.8%Language:Cuda 8.0%Language:C++ 3.7%Language:C 0.2%Language:Shell 0.2%