Skip to content

Repository files navigation

DINO-GIWAXS

This is a GIWAXS oriented implementation of the paper "DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection".

For more information on how to run the original implementation visit the original GitHub repo.

Models trained using DINO-GIWAXS can be used in mlgidDETECT to perform inference.

Installation

We test our models under python=3.12.7,pytorch=2.5.1,cuda=12.1. Other versions might be available as well. Click the Details below for more details.

  1. Clone this repo
git clone git@github.com:mlgid-project/DINO_GIWAXS.git
cd DINO_GIWAXS
  1. Install Pytorch and torchvision

Follow the instruction on https://pytorch.org/get-started/locally/.

# an example:
pip install torch==2.5.1 torchvision==0.20.1 --index-url https://download.pytorch.org/whl/cu121
  1. Install other needed packages
pip install -r requirements.txt
  1. Compiling CUDA operators
cd models/dino/ops
python setup.py build install
# unit test (should see all checking is True)
python test.py
cd ../../..

We use the environment same to DAB-DETR and DN-DETR to run DINO. If you have run DN-DETR or DAB-DETR, you can skip this step.

Onnx-File Export

To export an onnx file using the saved checkpoint.pth file run

python export.py --checkpoint /path-to-checkpoint/checkpoint.pth --output /output_dir/name.onnx

About

No description, website, or topics provided.

Resources

Stars

0 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages