Merge pull request #98549 from tgokal/tgokal-hyp-automl-images

clarify tile_grid_size for instance seg

Author: Jak-MS

articles/machine-learning/reference-automl-images-hyperparameters.md

@@ -110,7 +110,7 @@ The following hyperparameters are for object detection and instance segmentation
 | `box_score_threshold` | During inference, only return proposals with a classification score greater than `box_score_threshold`. <br> Must be a float in the range [0, 1].| 0.3 |
 | `nms_iou_threshold` | IOU (intersection over union) threshold used in non-maximum suppression (NMS) for the prediction head. Used during inference.  <br>Must be a float in the range [0, 1]. | 0.5 |
 | `box_detections_per_image` | Maximum number of detections per image, for all classes. <br> Must be a positive integer.| 100 |
-| `tile_grid_size` | The grid size to use for tiling each image. <br>*Note: tile_grid_size must not be None to enable [small object detection](how-to-use-automl-small-object-detect.md) logic*<br> Should be passed as a string in '3x2' format. Example: --tile_grid_size '3x2' | No Default |
+| `tile_grid_size` | The grid size to use for tiling each image. <br>*- `tile_grid_size` must not be None to enable [small object detection](how-to-use-automl-small-object-detect.md) logic.*<br>*- `tile_grid_size` is not supported for instance segmentation tasks.*<br> Should be passed as a string in '3x2' format. Example: --tile_grid_size '3x2' | No Default |
 | `tile_overlap_ratio` | Overlap ratio between adjacent tiles in each dimension. <br> Must be float in the range of [0, 1) | 0.25 |
 | `tile_predictions_nms_threshold` | The IOU threshold to use to perform NMS while merging predictions from tiles and image. Used in validation/ inference. <br> Must be float in the range of [0, 1] | 0.25 |