|
|
--- |
|
|
library_name: transformers |
|
|
--- |
|
|
|
|
|
This is the HF transformers implementation for D-FINE |
|
|
|
|
|
Model: D-FINE-L-COCO |
|
|
D-FINE, a powerful real-time object detector that achieves outstanding localization precision by redefining the bounding box regression task in DETR models. D-FINE comprises two key components: Fine-grained Distribution Refinement (FDR) and Global Optimal Localization Self-Distillation (GO-LSD). |
|
|
|
|
|
Usage: |
|
|
|
|
|
```python |
|
|
import torch |
|
|
import requests |
|
|
|
|
|
from PIL import Image |
|
|
from transformers import DFineForObjectDetection, AutoImageProcessor |
|
|
|
|
|
url = 'http://images.cocodataset.org/val2017/000000039769.jpg' |
|
|
image = Image.open(requests.get(url, stream=True).raw) |
|
|
|
|
|
image_processor = AutoImageProcessor.from_pretrained("vladislavbro/dfine_l_coco") |
|
|
model = DFineForObjectDetection.from_pretrained("vladislavbro/dfine_l_coco") |
|
|
|
|
|
inputs = image_processor(images=image, return_tensors="pt") |
|
|
|
|
|
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}") |
