Instructions to use stevenbucaille/rf-detr-small with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use stevenbucaille/rf-detr-small with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("object-detection", model="stevenbucaille/rf-detr-small")# pip install -U transformers accelerate # Load model directly from transformers import AutoImageProcessor, AutoModelForObjectDetection processor = AutoImageProcessor.from_pretrained("stevenbucaille/rf-detr-small") model = AutoModelForObjectDetection.from_pretrained("stevenbucaille/rf-detr-small", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit ·
c2b27de
1
Parent(s): 453d5ce
feat: refresh RF-DETR Hub model cards
Browse filesAlign READMEs with LW-DETR layout and PR 36895 snippets.
Regenerate demo output from local checkpoints.
README.md
CHANGED
|
@@ -74,8 +74,6 @@ Detected remote with confidence 0.241 at location [334.29, 77.9, 370.72, 187.68]
|
|
| 74 |
Detected remote with confidence 0.177 at location [340.43, 77.33, 371.02, 119.32]
|
| 75 |
```
|
| 76 |
|
| 77 |
-
Currently, both the feature extractor and model support PyTorch.
|
| 78 |
-
|
| 79 |
## Training data
|
| 80 |
|
| 81 |
These checkpoints are trained on the standard [COCO 2017 object detection dataset](https://cocodataset.org/#home) label space (80 categories) as reflected in `config.id2label`.
|
|
|
|
| 74 |
Detected remote with confidence 0.177 at location [340.43, 77.33, 371.02, 119.32]
|
| 75 |
```
|
| 76 |
|
|
|
|
|
|
|
| 77 |
## Training data
|
| 78 |
|
| 79 |
These checkpoints are trained on the standard [COCO 2017 object detection dataset](https://cocodataset.org/#home) label space (80 categories) as reflected in `config.id2label`.
|