đ Deformable DETR model with ResNet-50 backbone, with box refinement
This is a Deformable DETR model with a ResNet - 50 backbone and box refinement, trained end - to - end on COCO 2017 object detection dataset for detecting objects in images.
đ Quick Start
The Deformable DETR model can be used for object detection tasks. You can find all available Deformable DETR models on the model hub.
⨠Features
- End - to - End Training: Trained end - to - end on the COCO 2017 object detection dataset.
- Transformer - Based: Utilizes an encoder - decoder transformer architecture with a convolutional backbone.
- Object Queries: Uses object queries to detect objects in images.
đĻ Installation
No specific installation steps are provided in the original document.
đģ Usage Examples
Basic Usage
from transformers import AutoImageProcessor, DeformableDetrForObjectDetection
import torch
from PIL import Image
import requests
url = "http://images.cocodataset.org/val2017/000000039769.jpg"
image = Image.open(requests.get(url, stream=True).raw)
processor = AutoImageProcessor.from_pretrained("SenseTime/deformable-detr-with-box-refine")
model = DeformableDetrForObjectDetection.from_pretrained("SenseTime/deformable-detr-with-box-refine")
inputs = processor(images=image, return_tensors="pt")
outputs = model(**inputs)
target_sizes = torch.tensor([image.size[::-1]])
results = processor.post_process_object_detection(outputs, target_sizes=target_sizes, threshold=0.7)[0]
for score, label, box in zip(results["scores"], results["labels"], results["boxes"]):
box = [round(i, 2) for i in box.tolist()]
print(
f"Detected {model.config.id2label[label.item()]} with confidence "
f"{round(score.item(), 3)} at location {box}"
)
Currently, both the feature extractor and model support PyTorch.
đ Documentation
Model description
The DETR model is an encoder - decoder transformer with a convolutional backbone. Two heads are added on top of the decoder outputs in order to perform object detection: a linear layer for the class labels and a MLP (multi - layer perceptron) for the bounding boxes. The model uses so - called object queries to detect objects in an image. Each object query looks for a particular object in the image. For COCO, the number of object queries is set to 100.
The model is trained using a "bipartite matching loss": one compares the predicted classes + bounding boxes of each of the N = 100 object queries to the ground truth annotations, padded up to the same length N (so if an image only contains 4 objects, 96 annotations will just have a "no object" as class and "no bounding box" as bounding box). The Hungarian matching algorithm is used to create an optimal one - to - one mapping between each of the N queries and each of the N annotations. Next, standard cross - entropy (for the classes) and a linear combination of the L1 and generalized IoU loss (for the bounding boxes) are used to optimize the parameters of the model.

Intended uses & limitations
You can use the raw model for object detection.
Training data
The Deformable DETR model was trained on COCO 2017 object detection, a dataset consisting of 118k/5k annotated images for training/validation respectively.
BibTeX entry and citation info
@misc{https://doi.org/10.48550/arxiv.2010.04159,
doi = {10.48550/ARXIV.2010.04159},
url = {https://arxiv.org/abs/2010.04159},
author = {Zhu, Xizhou and Su, Weijie and Lu, Lewei and Li, Bin and Wang, Xiaogang and Dai, Jifeng},
keywords = {Computer Vision and Pattern Recognition (cs.CV), FOS: Computer and information sciences, FOS: Computer and information sciences},
title = {Deformable DETR: Deformable Transformers for End-to-End Object Detection},
publisher = {arXiv},
year = {2020},
copyright = {arXiv.org perpetual, non-exclusive license}
}
đ License
This model is licensed under the Apache - 2.0 license.