Update README.md
Browse files
README.md
CHANGED
|
@@ -42,4 +42,11 @@ The copy of this dataset on hugging face is available [here](https://huggingface
|
|
| 42 |
* **Batch size**: use 8 as train batch sizes
|
| 43 |
* **Training strategy**: Direct fine-tuning of DETR with minimal modifications
|
| 44 |
|
| 45 |
-
## Results & Example Predictions
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 42 |
* **Batch size**: use 8 as train batch sizes
|
| 43 |
* **Training strategy**: Direct fine-tuning of DETR with minimal modifications
|
| 44 |
|
| 45 |
+
## Results & Example Predictions
|
| 46 |
+
|
| 47 |
+
Since its a fine-tuned model, the accuracy is really high, and also classification accuracy can reach about 100%.
|
| 48 |
+
|
| 49 |
+
The predicted bounding box and masks are also very accurate :
|
| 50 |
+
|
| 51 |
+
|
| 52 |
+
|