This repository is the official implementation of Object Detection and Instance Segmentation task in the Battle of the Backbones: A Large-Scale Comparison of Pretrained Models across Computer Vision Tasks.
📌 Our implementation and instructions are based on mmdetection
Step 1. Create a conda environment and activate it.
conda create --name openmmlab python=3.8 -y
conda activate openmmlabStep 2. Install PyTorch following official instructions, e.g.
On GPU platforms:
conda install pytorch==1.13.1 torchvision==0.14.1 torchaudio==0.13.1 pytorch-cuda=11.6 -c pytorch -c nvidiaStep 3. Install MMCV using MIM.
pip install -U openmim
mim install mmcv-full==1.7.0Step 4. Install BoB-Detection.
git clone https://github.com/hsouri/bob-detection.git
cd bob-detection
pip install -v -e .
# "-v" means verbose, or more output
# "-e" means installing a project in editable mode,
# thus any local modifications made to the code will take effect without reinstallation.Step 5. Download COCO (LVIS) and unzip dataset (you can optionally delete downloaded zip files by passing '--delete').
COCO download:
python tools/misc/download_dataset.py --dataset-name coco2017 --unzipLVIS download:
python tools/misc/download_dataset.py --dataset-name lvis --save-dir data/lvis_v1/ --unzip
cd data/lvis_v1/
mkdir annotations
mv lvis_v1_train.json annotations/
mv lvis_v1_val.json annotations/Please refer to Get Started, Dataset Prepare, and Dataset Download for more detailed instructions.
The config files for all experiments in Battle of the Backbones (BoB) can be found configs/bob.
To train a detector with the existing configs, run:
bash ./tools/dist_train.sh <CONFIG_FILE> <GPU_NUM>
React
Typescript
Django
Laravel
Facebook
Microsoft
Google
Alibaba
D3
Tencent