Add support for evaluating masks and keypoints for custom dataset (#938)

Author: fmassa

references/detection/coco_utils.py

@@ -151,18 +151,26 @@ def convert_to_coco_api(ds):
     for img_idx in range(len(ds)):
         # find better way to get target
         # targets = ds.get_annotations(img_idx)
-        _, targets = ds[img_idx]
+        img, targets = ds[img_idx]
         image_id = targets["image_id"].item()
         img_dict = {}
         img_dict['id'] = image_id
+        img_dict['height'] = img.shape[-2]
+        img_dict['width'] = img.shape[-1]
         dataset['images'].append(img_dict)
         bboxes = targets["boxes"]
         bboxes[:, 2:] -= bboxes[:, :2]
         bboxes = bboxes.tolist()
         labels = targets['labels'].tolist()
         areas = targets['area'].tolist()
         iscrowd = targets['iscrowd'].tolist()
-        # TODO need to add masks as well
+        if 'masks' in targets:
+            masks = targets['masks']
+            # make masks Fortran contiguous for coco_mask
+            masks = masks.permute(0, 2, 1).contiguous().permute(0, 2, 1)
+        if 'keypoints' in targets:
+            keypoints = targets['keypoints']
+            keypoints = keypoints.reshape(keypoints.shape[0], -1).tolist()
         num_objs = len(bboxes)
         for i in range(num_objs):
             ann = {}
@@ -173,6 +181,11 @@ def convert_to_coco_api(ds):
             ann['area'] = areas[i]
             ann['iscrowd'] = iscrowd[i]
             ann['id'] = ann_id
+            if 'masks' in targets:
+                ann["segmentation"] = coco_mask.encode(masks[i].numpy())
+            if 'keypoints' in targets:
+                ann['keypoints'] = keypoints[i]
+                ann['num_keypoints'] = sum(k != 0 for k in keypoints[i][2::3])
             dataset['annotations'].append(ann)
             ann_id += 1
     dataset['categories'] = [{'id': i} for i in sorted(categories)]