---
license: apache-2.0
tags:
- object-detection
- vision
datasets:
- coco
widget:
- src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/savanna.jpg
  example_title: Savanna
- src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/football-match.jpg
  example_title: Football Match
- src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/airport.jpg
  example_title: Airport
---

# DETR (End-to-End Object Detection) model with ResNet-50 backbone trained on SKU110K Dataset with 400 num_queries

DEtection TRansformer (DETR) model trained end-to-end on SKU110K object detection (8k annotated images). It was introduced in the paper [End-to-End Object Detection with Transformers](https://arxiv.org/abs/2005.12872) by Carion et al. and first released in [this repository](https://github.com/facebookresearch/detr). 

### How to use

Here is how to use this model:

```python
from transformers import DetrImageProcessor, DetrForObjectDetection
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)

# you can specify the revision tag if you don't want the timm dependency
processor = DetrImageProcessor.from_pretrained("facebook/detr-resnet-50", revision="no_timm")
model = DetrForObjectDetection.from_pretrained("facebook/detr-resnet-50", revision="no_timm")

inputs = processor(images=image, return_tensors="pt")
outputs = model(**inputs)

# convert outputs (bounding boxes and class logits) to COCO API
# let's only keep detections with score > 0.9
target_sizes = torch.tensor([image.size[::-1]])
results = processor.post_process_object_detection(outputs, target_sizes=target_sizes, threshold=0.9)[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}"
    )
```
This should output:
```
Detected remote with confidence 0.998 at location [40.16, 70.81, 175.55, 117.98]
Detected remote with confidence 0.996 at location [333.24, 72.55, 368.33, 187.66]
Detected couch with confidence 0.995 at location [-0.02, 1.15, 639.73, 473.76]
Detected cat with confidence 0.999 at location [13.24, 52.05, 314.02, 470.93]
Detected cat with confidence 0.999 at location [345.4, 23.85, 640.37, 368.72]
```

Currently, both the feature extractor and model support PyTorch. 

## Training data

The DETR model was trained on [SKU110K Dataset](https://github.com/eg4000/SKU110K_CVPR19), a dataset consisting of 8219/588/2936 annotated images for training/validation/test respectively. 

## Training procedure
### Training

The model was trained for 140 epochs on 1 RTX 4060 Ti GPU(Finetuning decoder only) with batch size of 8 and 70 epochs(finetuning the whole network) with batch size of 3 and accumulating gradients for 3 steps.

## Evaluation results

This model achieves an AP (average precision) of **59.0** on SKU110k validation. Result was calculated with torchmetrics MeanAveragePrecision class.