# 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 demo.py that is able to run builtin standard models. Run it with:
python demo/demo.py --config-file configs/COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x.yaml \
--input input1.jpg input2.jpg \
[--other-options]


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 demo.py -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_}train_net.py”, 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 “train_net.py”, first setup the corresponding datasets following datasets/README.md, then run:

python tools/train_net.py --num-gpus 8 \


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

python tools/train_net.py \
SOLVER.IMS_PER_BATCH 2 SOLVER.BASE_LR 0.0025


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/train_net.py \

For more options, see python tools/train_net.py -h.