Garment detection Using Detectron2
Server SPEC
OS/Version | CPU | GPU/Version |
---|---|---|
Ubuntu-server/20.04 | AMD Ryzen Threadripper PRO 5955WX | A6000/515.65.01 |
+-----------------------------------------------------------------------------+
| NVIDIA-SMI 515.65.01 Driver Version: 515.65.01 CUDA Version: 11.7 |
|-------------------------------+----------------------+----------------------+
| GPU Name Persistence-M| Bus-Id Disp.A | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap| Memory-Usage | GPU-Util Compute M. |
| | | MIG M. |
|===============================+======================+======================|
| 0 NVIDIA RTX A6000 Off | 00000000:41:00.0 Off | Off |
| 30% 57C P0 87W / 300W | 0MiB / 49140MiB | 2% Default |
| | | N/A |
+-------------------------------+----------------------+----------------------+
Detectron2 - Repository
Detectron2 - Colab Notebook
Detectron2 - Documentation
Install Container Using Dockerfile
git clone https://github.com/facebookresearch/detectron2.git
cd detectron2/docker/
# Change Dockerfile
## If you Don't change this, an error be occurs.
## https://github.com/facebookresearch/detectron2/issues/4394#issuecomment-1186037669
rm Dockerfile
wget https://github.com/facebookresearch/detectron2/files/9124785/Dockerfile.txt -O Dockerfile
# https://github.com/facebookresearch/detectron2/tree/main/docker
# Build:
docker build --build-arg USER_ID=$UID -t detectron2:v0 .
# Launch (require GPUs):
docker run --gpus all -it --shm-size=8gb --env="DISPLAY" --volume="/tmp/.X11-unix:/tmp/.X11-unix:rw" --name=detectron2 detectron2:v0
Install Container Use not Dockerfile
docker pull nvidia/cuda:11.6.0-cudnn8-devel-ubuntu20.04
docker run -i -t --gpus all --shm-size 8gb --name detectron2 nvidia/cuda:11.6.0-cudnn8-devel-ubuntu20.04
apt-get update && apt-get -y dist-upgrade
apt-get install -y wget git vim build-essential python3 python3-pip zip libgl1-mesa-glx libglib2.0-0
Setup in Container
# Apt Updata && Upgrade && install
apt-get update && apt-get -y dist-upgrade
apt-get install -y wget git vim build-essential python3 python3-pip zip libgl1-mesa-glx libglib2.0-0
Install package
Requirements
- Linux or macOS with Python ≥ 3.7
- PyTorch ≥ 1.8 and torchvision that matches the PyTorch installation. Install them together at pytorch.org to make sure of this
- OpenCV is optional but needed by demo and visualization
# pip3 install package
pip3 install torch torchvision --extra-index-url https://download.pytorch.org/whl/cu116 && pip3 install opencv-python pyyaml==5.1
# Build Detectron2 from Source
mkdir /workspace && cd /workspace
git clone https://github.com/facebookresearch/detectron2.git
cd detectron2
python -m pip install -e detectron2