Getting Started with Detectron2

This document provides a brief intro of the usage of builtin command-line tools in detectron2.

For a tutorial that involves actual coding with the API, see our Colab Notebook which covers how to run inference with an existing model, and how to train a builtin model on a custom dataset.

For more advanced tutorials, refer to our documentation.

Inference Demo with Pre-trained Models

  1. Pick a model and its config file from model zoo, for example, mask_rcnn_R_50_FPN_3x.yaml.
  2. We provide that is able to run builtin standard models. Run it with:
python demo/ --config-file configs/COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x.yaml \
  --input input1.jpg input2.jpg \
  --opts MODEL.WEIGHTS detectron2://COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x/137849600/model_final_f10217.pkl

The configs are made for training, therefore we need to specify MODEL.WEIGHTS to a model from model zoo for evaluation. This command will run the inference and show visualizations in an OpenCV window.

For details of the command line arguments, see -h. Some common ones are:

  • To run on your webcam, replace --input files with --webcam.
  • To run on a video, replace --input files with --video-input video.mp4.
  • To run on cpu, add MODEL.DEVICE cpu after --opts.
  • To save outputs to a directory (for images) or a file (for webcam or video), use --output.

Training & Evaluation in Command Line

We provide a script in “tools/{,plain_}”, that is made to train all the configs provided in detectron2. You may want to use it as a reference to write your own training script for a new research.

To train a model with “”, first setup the corresponding datasets following datasets/, then run:

python tools/ --num-gpus 8 \
    --config-file configs/COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_1x.yaml

The configs are made for 8-GPU training. To train on 1 GPU, change the batch size with:

python tools/ \
    --config-file configs/COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_1x.yaml \

For most models, CPU training is not supported.

(Note that we applied the linear learning rate scaling rule when changing the batch size.)

To evaluate a model’s performance, use

python tools/ \
    --config-file configs/COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_1x.yaml \
    --eval-only MODEL.WEIGHTS /path/to/checkpoint_file

For more options, see python tools/ -h.

Use Detectron2 APIs in Your Code

See our Colab Notebook to learn how to use detectron2 APIs to:

  1. run inference with an existing model
  2. train a builtin model on a custom dataset

See detectron2/projects for more ways to build your project on detectron2.