TopGit tracks facebookresearch/detr on GitHub. The project has 15.4k stars. End-to-End Object Detection with Transformers
Snapshot summary built from the project's own GitHub metadata — there's no written TopGit review yet. The page will update automatically when a full review is published.
WHY NO REVIEW YET
TopGit writes full reviews for the most-starred, most-requested repositories. This page is a snapshot until then — see the READ ME tab for the original README in full.
DE⫶TR: End-to-End Object Detection with Transformers
PyTorch training code and pretrained models for DETR (DEtection TRansformer).
We replace the full complex hand-crafted object detection pipeline with a Transformer, and match Faster R-CNN with a ResNet-50, obtaining 42 AP on COCO using half the computation power (FLOPs) and the same number of parameters. Inference in 50 lines of PyTorch.
What it is. Unlike traditional computer vision techniques, DETR approaches object detection as a direct set prediction problem. It consists of a set-based global loss, which forces unique predictions via bipartite matching, and a Transformer encoder-decoder architecture.
Given a fixed small set of learned object queries, DETR reasons about the relations of the objects and the global image context to directly output the final set of predictions in parallel. Due to this parallel nature, DETR is very fast and efficient.
About the code. We believe that object detection should not be more difficult than classification,
and should not require complex libraries for training and inference.
DETR is very simple to implement and experiment with, and we provide a
standalone Colab Notebook
showing how to do inference with DETR in only a few lines of PyTorch code.
Training code follows this idea - it is not a library,
but simply a main.py importing model and criterion
definitions with standard training loops.
Additionnally, we provide a Detectron2 wrapper in the d2/ folder. See the readme there for more information.
For details see End-to-End Object Detection with Transformers by Nicolas Carion, Francisco Massa, Gabriel Synnaeve, Nicolas Usunier, Alexander Kirillov, and Sergey Zagoruyko.
See our blog post to learn more about end to end object detection with transformers.
Model Zoo
We provide baseline DETR and DETR-DC5 models, and plan to include more in future.
AP is computed on COCO 2017 val5k, and inference time is over the first 100 val5k COCO images,
with torchscript transformer.
name
backbone
schedule
inf_time
box AP
url
size
0
DETR
R50
500
0.036
42.0
model | logs
159Mb
1
DETR-DC5
R50
500
0.083
43.3
model | logs
159Mb
2
DETR
R101
500
0.050
43.5
model | logs
232Mb
3
DETR-DC5
R101
500
0.097
44.9
model | logs
232Mb
COCO val5k evaluation results can be found in this gist.
The models are also available via torch hub,
to load DETR R50 with pretrained weights simply do:
model = torch.hub.load('facebookresearch/detr:main', 'detr_resnet50', pretrained=True)
COCO panoptic val5k models:
name
backbone
box AP
segm AP
PQ
url
size
0
DETR
R50
38.8
31.1
43.4
download
165Mb
1
DETR-DC5
R50
40.2
31.9
44.6
download
165Mb
2
DETR
R101
40.1
33
45.1
download
237Mb
Checkout our panoptic colab
to see how to use and visualize DETR's panoptic segmentation prediction.
Notebooks
We provide a few notebooks in colab to help you get a grasp on DETR:
DETR's hands on Colab Notebook: Shows how to load a model from hub, generate predictions, then visualize the attention of the model (similar to the figures of the paper)
Standalone Colab Notebook: In this notebook, we demonstrate how to implement a simplified version of DETR from the grounds up in 50 lines of Python, then visualize the predictions. It is a good starting point if you want to gain better understanding the architecture and poke around before diving in the codebase.
Panoptic Colab Notebook: Demonstrates how to use DETR for panoptic segmentation and plot the predictions.
Usage - Object detection
There are no extra compiled components in DETR and package dependencies are minimal,
so the code is very simple to use. We provide instructions how to install dependencies via conda.
First, clone the repository locally:
Download and extract COCO 2017 train and val images with annotations from
http://cocodataset.org.
We expect the directory structure to be the following:
A single epoch takes 28 minutes, so 300 epoch training
takes around 6 days on a single machine with 8 V100 cards.
To ease reproduction of our results we provide
results and training logs
for 150 epoch schedule (3 days on a single machine), achieving 39.5/60.3 AP/AP50.
We train DETR with AdamW setting learning rate in the transformer to 1e-4 and 1e-5 in the backbone.
Horizontal flips, scales and crops are used for augmentation.
Images are rescaled to have min size 800 and max size 1333.
The transformer is trained with dropout of 0.1, and the whole model is trained with grad clip of 0.1.
Evaluation
To evaluate DETR R50 on COCO val5k with a single GPU run:
We provide results for all DETR detection models in this
gist.
Note that numbers vary depending on batch size (number of images) per GPU.
Non-DC5 models were trained with batch size 2, and DC5 with 1,
so DC5 models show a significant drop in AP if evaluated with more
than 1 image per GPU.
Multinode training
Distributed training is available via Slurm and submitit:
pip install submitit
Train baseline DETR-6-6 model on 4 nodes for 300 epochs:
We show that it is relatively straightforward to extend DETR to predict segmentation masks. We mainly demonstrate strong panoptic segmentation results.
Data preparation
For panoptic segmentation, you need the panoptic annotations additionally to the coco dataset (see above for the coco dataset). You need to download and extract the annotations.
We expect the directory structure to be the following:
We recommend training segmentation in two stages: first train DETR to detect all the boxes, and then train the segmentation head.
For panoptic segmentation, DETR must learn to detect boxes for both stuff and things classes. You can train it on a single node with 8 gpus for 300 epochs with:
For instance segmentation, you can simply train a normal box model (or used a pre-trained one we provide).
Once you have a box model checkpoint, you need to freeze it, and train the segmentation head in isolation.
For panoptic segmentation you can train on a single node with 8 gpus for 25 epochs:
How active is development on facebookresearch/detr?
The most recent commit recorded on facebookresearch/detr was 2.7 years ago, based on the GitHub push timestamp. The repository has 2.7k forks — one of the better signals of community interest.
How many stars does facebookresearch/detr have?
facebookresearch/detr has 15.4k GitHub stars — refresh the page for the live number, or check github.com/facebookresearch/detr. TopGit mirrors GitHub's count but does not claim minute-by-minute accuracy.
Is facebookresearch/detr open source?
Yes — facebookresearch/detr ships under the Apache-2.0 license, which makes its source code freely readable (and, depending on license terms, forkable and reusable). Source: github.com/facebookresearch/detr.
What is facebookresearch/detr?
facebookresearch/detr (facebookresearch/detr) is a Python project on GitHub. From the project's own README: End-to-End Object Detection with Transformers
What language is facebookresearch/detr written in?
facebookresearch/detr is written primarily in Python. GitHub's language field is based on the largest share of bytes in the default branch.
What license does facebookresearch/detr use?
facebookresearch/detr is released under the Apache-2.0 license. Always verify the LICENSE file directly on GitHub for the authoritative terms — license strings can be edited out of sync with a project's actual stance.
Where do I read more about facebookresearch/detr?
This TopGit page is a snapshot — the READ ME tab shows the project's own README content (links stripped, images preserved). The GitHub repository at github.com/facebookresearch/detr is the definitive source.
Read full README in the tab above.
Want a second opinion on detr?
Ask an AI that can read this page — one click and you get its take on detr.