Update README.md
Browse files
README.md
CHANGED
|
@@ -12,7 +12,6 @@ This is a Model using `ResNet-50` backbone and customized Multi-task Head and l
|
|
| 12 |
|
| 13 |
Note that I only use processor and `resnet-50` backbone of `resnet-50-panotic` model, not use transformers. All the model, task heads and loss are self-defined.
|
| 14 |
|
| 15 |
-
|
| 16 |
Another model by directly fine-tuning DETR model can be found at https://huggingface.co/FriedParrot/fish-segmentation-simple
|
| 17 |
|
| 18 |
This model use kaggle dataset [A Large Scale Fish Dataset](https://www.kaggle.com/datasets/crowww/a-large-scale-fish-dataset) as dataset for training.
|
|
@@ -22,6 +21,12 @@ Tasks :
|
|
| 22 |
- BBoxes prediction, and
|
| 23 |
- Segmentation
|
| 24 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 25 |
### Model Sources
|
| 26 |
|
| 27 |
For source code : check [my github](https://github.com/FRIEDparrot/fish-segmentation)
|
|
|
|
| 12 |
|
| 13 |
Note that I only use processor and `resnet-50` backbone of `resnet-50-panotic` model, not use transformers. All the model, task heads and loss are self-defined.
|
| 14 |
|
|
|
|
| 15 |
Another model by directly fine-tuning DETR model can be found at https://huggingface.co/FriedParrot/fish-segmentation-simple
|
| 16 |
|
| 17 |
This model use kaggle dataset [A Large Scale Fish Dataset](https://www.kaggle.com/datasets/crowww/a-large-scale-fish-dataset) as dataset for training.
|
|
|
|
| 21 |
- BBoxes prediction, and
|
| 22 |
- Segmentation
|
| 23 |
|
| 24 |
+
> [!warning]
|
| 25 |
+
> Since this model include customized type, then `AutoModel()` and `AutoConfig()` may fail, but `AutoProcessor()` will work correctly (Since I use a DetrImageProcessor for this)
|
| 26 |
+
>
|
| 27 |
+
> If you want using this model, you can **go to my source code below** and look for `FishSegmentationModel` and `FishSegmentModelConfig` for load these models correctly.
|
| 28 |
+
>
|
| 29 |
+
|
| 30 |
### Model Sources
|
| 31 |
|
| 32 |
For source code : check [my github](https://github.com/FRIEDparrot/fish-segmentation)
|