Update README.md
Browse files
README.md
CHANGED
|
@@ -21,6 +21,12 @@ This model was contributed by [VladOS95-cyber](https://github.com/VladOS95-cyber
|
|
| 21 |
|
| 22 |
This is the HF transformers implementation for D-FINE
|
| 23 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 24 |
### **Performance**
|
| 25 |
|
| 26 |
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).
|
|
|
|
| 21 |
|
| 22 |
This is the HF transformers implementation for D-FINE
|
| 23 |
|
| 24 |
+
_coco -> model trained on COCO
|
| 25 |
+
|
| 26 |
+
_obj365 -> model trained on Object365
|
| 27 |
+
|
| 28 |
+
_obj2coco -> model trained on Object365 and then finetuned on COCO
|
| 29 |
+
|
| 30 |
### **Performance**
|
| 31 |
|
| 32 |
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).
|