apple
/

coreml-detr-semantic-segmentation

Image Segmentation

Core ML

Model card Files Files and versions Community

reach-vb HF staff commited on Jun 12, 2024

Commit

9c9c0ef

verified ·

1 Parent(s): 5e24d79

Update README.md (#3)

Browse files

- Update README.md (e3ac35c50a39524a04d13706157c4ac8b03f9d52)

Files changed (1) hide show

README.md +2 -6

README.md CHANGED Viewed

@@ -18,17 +18,13 @@ The model is trained using a "bipartite matching loss": one compares the predict
 ![model image](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/model_doc/detr_architecture.png)
-## Intended uses & limitations
-You can use the raw model for object detection. See the [model hub](https://huggingface.co/models?search=facebook/detr) to look for all available DETR models.
 ## Evaluation - Variants
 | Variant                                                                                               | Parameters | Size (MB) | Weight Precision | Act. Precision | IoU   | Pixel accuracy |
 |-------------------------------------------------------------------------------------------------------|-----------:|----------:|------------------|----------------|------:|---------------:|
 | [facebook/detr-resnet-50-panoptic (PyTorch)](https://huggingface.co/facebook/detr-resnet-50-panoptic) | 43M        | 172       | Float32          | Float32        | 0.393 | 0.746          |
-| [DETRResnet50SemanticSegmentationF32](DETRResnet50SemanticSegmentationF32.mlpackage)                                                                   | 43M        | 171       | Float32          | Float32        | 0.393 | 0.746          |
-| [DETRResnet50SemanticSegmentationF16](DETRResnet50SemanticSegmentationF16.mlpackage)                                                                   | 43M        | 86        | Float16          | Float16        | 0.395 | 0.746          |
 IoU and Pixel accuracy measured on 512 images from the COCO dataset. The ground truth labels were extracted from the panoptic segmentation annotations, transformed to semantic segmentation masks. Input images were resized so that the smaller edge equals 448, then center-cropped.

 ![model image](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/model_doc/detr_architecture.png)
 ## Evaluation - Variants
 | Variant                                                                                               | Parameters | Size (MB) | Weight Precision | Act. Precision | IoU   | Pixel accuracy |
 |-------------------------------------------------------------------------------------------------------|-----------:|----------:|------------------|----------------|------:|---------------:|
 | [facebook/detr-resnet-50-panoptic (PyTorch)](https://huggingface.co/facebook/detr-resnet-50-panoptic) | 43M        | 172       | Float32          | Float32        | 0.393 | 0.746          |
+| [DETRResnet50SemanticSegmentationF32](DETRResnet50SemanticSegmentationF32.mlpackage)                  | 43M        | 171       | Float32          | Float32        | 0.393 | 0.746          |
+| [DETRResnet50SemanticSegmentationF16](DETRResnet50SemanticSegmentationF16.mlpackage)                  | 43M        | 86        | Float16          | Float16        | 0.395 | 0.746          |
 IoU and Pixel accuracy measured on 512 images from the COCO dataset. The ground truth labels were extracted from the panoptic segmentation annotations, transformed to semantic segmentation masks. Input images were resized so that the smaller edge equals 448, then center-cropped.