Instructions to use ustc-community/dfine-medium-obj365 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ustc-community/dfine-medium-obj365 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("object-detection", model="ustc-community/dfine-medium-obj365")# Load model directly from transformers import AutoTokenizer, AutoModelForObjectDetection tokenizer = AutoTokenizer.from_pretrained("ustc-community/dfine-medium-obj365") model = AutoModelForObjectDetection.from_pretrained("ustc-community/dfine-medium-obj365", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -21,6 +21,9 @@ Yansong Peng, Hebei Li, Peixi Wu, Yueyi Zhang, Xiaoyan Sun, Feng Wu
|
|
| 21 |
This model was contributed by [VladOS95-cyber](https://github.com/VladOS95-cyber) with the help of [@qubvel-hf](https://huggingface.co/qubvel-hf)
|
| 22 |
|
| 23 |
This is the HF transformers implementation for D-FINE
|
|
|
|
|
|
|
|
|
|
| 24 |
|
| 25 |
### **Performance**
|
| 26 |
|
|
|
|
| 21 |
This model was contributed by [VladOS95-cyber](https://github.com/VladOS95-cyber) with the help of [@qubvel-hf](https://huggingface.co/qubvel-hf)
|
| 22 |
|
| 23 |
This is the HF transformers implementation for D-FINE
|
| 24 |
+
_coco -> model trained on COCO
|
| 25 |
+
_obj365 -> model trained on Object365
|
| 26 |
+
_obj2coco -> model trained on Object365 and then finetuned on COCO
|
| 27 |
|
| 28 |
### **Performance**
|
| 29 |
|