This model was released on 2020-10-08 and added to Hugging Face Transformers on 2022-09-14.

Deformable DETR

Deformable DETR improves on the original DETR by using a deformable attention module. This mechanism selectively attends to a small set of key sampling points around a reference. It improves training speed and improves accuracy.

<small> Deformable DETR architecture. Taken from the <a href="https://huggingface.co/papers/2010.04159">original paper</a>.</small>

You can find all the available Deformable DETR checkpoints under the SenseTime organization.

[!TIP] This model was contributed by nielsr.

Click on the Deformable DETR models in the right sidebar for more examples of how to apply Deformable DETR to different object detection and segmentation tasks.

The example below demonstrates how to perform object detection with the [Pipeline] and the [AutoModel] class.

from transformers import pipeline


pipeline = pipeline(
    "object-detection",
    model="SenseTime/deformable-detr",
    device_map=0
)

pipeline("http://images.cocodataset.org/val2017/000000039769.jpg")

import requests
import torch
from PIL import Image

from transformers import AutoImageProcessor, AutoModelForObjectDetection


url = "http://images.cocodataset.org/val2017/000000039769.jpg"
image = Image.open(requests.get(url, stream=True).raw)

image_processor = AutoImageProcessor.from_pretrained("SenseTime/deformable-detr")
model = AutoModelForObjectDetection.from_pretrained("SenseTime/deformable-detr", device_map="auto")

# prepare image for the model
inputs = image_processor(images=image, return_tensors="pt").to(model.device)

with torch.no_grad():
    outputs = model(**inputs)

results = image_processor.post_process_object_detection(outputs, target_sizes=torch.tensor([image.size[::-1]]), threshold=0.3)

for result in results:
    for score, label_id, box in zip(result["scores"], result["labels"], result["boxes"]):
        score, label = score.item(), label_id.item()
        box = [round(i, 2) for i in box.tolist()]
        print(f"{model.config.id2label[label]}: {score:.2f} {box}")

Resources

• Refer to this set of notebooks for inference and fine-tuning [DeformableDetrForObjectDetection] on a custom dataset.

DeformableDetrImageProcessor

[[autodoc]] DeformableDetrImageProcessor - preprocess - post_process_object_detection

DeformableDetrImageProcessorPil

[[autodoc]] DeformableDetrImageProcessorPil - preprocess - post_process_object_detection

DeformableDetrConfig

[[autodoc]] DeformableDetrConfig

DeformableDetrModel

[[autodoc]] DeformableDetrModel - forward

DeformableDetrForObjectDetection

[[autodoc]] DeformableDetrForObjectDetection - forward