Update README.md

README.md

@@ -22,6 +22,28 @@ The model is trained using a "bipartite matching loss": one compares the predict
 
 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.
+
+## Evaluation - Inference time
+
+The following results refer to DETRResnet50SemanticSegmentationF16. The compute units for MacBook Pro (M1 Max) were manually selected to "CPU and Neural Engine".
+
+| Device               | OS   | Inference time (ms) | Dominant compute unit |
+| -------------------- | ---- | ------------------: | --------------------- |
+| iPhone 14            | 17.5 |                     | Neural Engine         |
+| iPhone 14 Pro Max    | 17.5 |                     | Neural Engine         |
+| iPhone 15            | 17.0 |                     | Neural Engine         |
+| iPhone 15 Pro Max    | 17.5 |                  40 | Neural Engine         |
+| MacBook Pro (M1 Max) | 14.5 |                  43 | Neural Engine         |
+
 ## Download
 
 Install `huggingface-hub`