[Datumaro] MOT format (#1289)

* Add mot format base

* Add mot format

* Extract common code

datumaro/datumaro/plugins/coco_format/converter.py

@@ -17,23 +17,14 @@
     AnnotationType, Points
 )
 from datumaro.components.cli_plugin import CliPlugin
-from datumaro.util import find
+from datumaro.util import find, cast
 from datumaro.util.image import save_image
 import datumaro.util.mask_tools as mask_tools
 import datumaro.util.annotation_tools as anno_tools
 
 from .format import CocoTask, CocoPath
 
 
-def _cast(value, type_conv, default=None):
-    if value is None:
-        return default
-    try:
-        return type_conv(value)
-    except Exception:
-        return default
-
-
 SegmentationMode = Enum('SegmentationMode', ['guess', 'polygons', 'mask'])
 
 class _TaskConverter:
@@ -82,7 +73,7 @@ def save_image_info(self, item, filename):
             'id': self._get_image_id(item),
             'width': int(w),
             'height': int(h),
-            'file_name': _cast(filename, str, ''),
+            'file_name': cast(filename, str, ''),
             'license': 0,
             'flickr_url': '',
             'coco_url': '',
@@ -162,8 +153,8 @@ def save_categories(self, dataset):
         for idx, cat in enumerate(label_categories.items):
             self.categories.append({
                 'id': 1 + idx,
-                'name': _cast(cat.name, str, ''),
-                'supercategory': _cast(cat.parent, str, ''),
+                'name': cast(cat.name, str, ''),
+                'supercategory': cast(cat.parent, str, ''),
             })
 
     @classmethod
@@ -309,7 +300,7 @@ def convert_instance(self, instance, item):
         elem = {
             'id': self._get_ann_id(ann),
             'image_id': self._get_image_id(item),
-            'category_id': _cast(ann.label, int, -1) + 1,
+            'category_id': cast(ann.label, int, -1) + 1,
             'segmentation': segmentation,
             'area': float(area),
             'bbox': list(map(float, bbox)),
@@ -334,10 +325,11 @@ def save_categories(self, dataset):
         for idx, label_cat in enumerate(label_categories.items):
             cat = {
                 'id': 1 + idx,
-                'name': _cast(label_cat.name, str, ''),
-                'supercategory': _cast(label_cat.parent, str, ''),
+                'name': cast(label_cat.name, str, ''),
+                'supercategory': cast(label_cat.parent, str, ''),
                 'keypoints': [],
                 'skeleton': [],
+
             }
 
             if point_categories is not None:
@@ -416,8 +408,8 @@ def save_categories(self, dataset):
         for idx, cat in enumerate(label_categories.items):
             self.categories.append({
                 'id': 1 + idx,
-                'name': _cast(cat.name, str, ''),
-                'supercategory': _cast(cat.parent, str, ''),
+                'name': cast(cat.name, str, ''),
+                'supercategory': cast(cat.parent, str, ''),
             })
 
     def save_annotations(self, item):
@@ -504,7 +496,7 @@ def _make_task_converters(self):
     def _get_image_id(self, item):
         image_id = self._image_ids.get(item.id)
         if image_id is None:
-            image_id = _cast(item.id, int, len(self._image_ids) + 1)
+            image_id = cast(item.id, int, len(self._image_ids) + 1)
             self._image_ids[item.id] = image_id
         return image_id
 

datumaro/datumaro/plugins/cvat_format/converter.py

@@ -12,19 +12,12 @@
 from datumaro.components.cli_plugin import CliPlugin
 from datumaro.components.converter import Converter
 from datumaro.components.extractor import DEFAULT_SUBSET_NAME, AnnotationType
+from datumaro.util import cast
 from datumaro.util.image import save_image
 
 from .format import CvatPath
 
 
-def _cast(value, type_conv, default=None):
-    if value is None:
-        return default
-    try:
-        return type_conv(value)
-    except Exception:
-        return default
-
 def pairwise(iterable):
     a = iter(iterable)
     return zip(a, a)
@@ -188,7 +181,7 @@ def _save_image(self, item):
 
     def _write_item(self, item, index):
         image_info = OrderedDict([
-            ("id", str(_cast(item.id, int, index))),
+            ("id", str(cast(item.id, int, index))),
         ])
         if item.has_image:
             size = item.image.size

datumaro/datumaro/plugins/datumaro_format/converter.py

@@ -16,21 +16,14 @@
     Label, Mask, RleMask, Points, Polygon, PolyLine, Bbox, Caption,
     LabelCategories, MaskCategories, PointsCategories
 )
+from datumaro.util import cast
 from datumaro.util.image import save_image
 import pycocotools.mask as mask_utils
 from datumaro.components.cli_plugin import CliPlugin
 
 from .format import DatumaroPath
 
 
-def _cast(value, type_conv, default=None):
-    if value is None:
-        return default
-    try:
-        return type_conv(value)
-    except Exception:
-        return default
-
 class _SubsetWriter:
     def __init__(self, name, context):
         self._name = name
@@ -108,18 +101,18 @@ def _convert_annotation(self, obj):
         assert isinstance(obj, Annotation)
 
         ann_json = {
-            'id': _cast(obj.id, int),
-            'type': _cast(obj.type.name, str),
+            'id': cast(obj.id, int),
+            'type': cast(obj.type.name, str),
             'attributes': obj.attributes,
-            'group': _cast(obj.group, int, 0),
+            'group': cast(obj.group, int, 0),
         }
         return ann_json
 
     def _convert_label_object(self, obj):
         converted = self._convert_annotation(obj)
 
         converted.update({
-            'label_id': _cast(obj.label, int),
+            'label_id': cast(obj.label, int),
         })
         return converted
 
@@ -133,7 +126,7 @@ def _convert_mask_object(self, obj):
                 np.require(obj.image, dtype=np.uint8, requirements='F'))
 
         converted.update({
-            'label_id': _cast(obj.label, int),
+            'label_id': cast(obj.label, int),
             'rle': {
                 # serialize as compressed COCO mask
                 'counts': rle['counts'].decode('ascii'),
@@ -146,7 +139,7 @@ def _convert_polyline_object(self, obj):
         converted = self._convert_annotation(obj)
 
         converted.update({
-            'label_id': _cast(obj.label, int),
+            'label_id': cast(obj.label, int),
             'points': [float(p) for p in obj.points],
         })
         return converted
@@ -155,7 +148,7 @@ def _convert_polygon_object(self, obj):
         converted = self._convert_annotation(obj)
 
         converted.update({
-            'label_id': _cast(obj.label, int),
+            'label_id': cast(obj.label, int),
             'points': [float(p) for p in obj.points],
         })
         return converted
@@ -164,7 +157,7 @@ def _convert_bbox_object(self, obj):
         converted = self._convert_annotation(obj)
 
         converted.update({
-            'label_id': _cast(obj.label, int),
+            'label_id': cast(obj.label, int),
             'bbox': [float(p) for p in obj.get_bbox()],
         })
         return converted
@@ -173,7 +166,7 @@ def _convert_points_object(self, obj):
         converted = self._convert_annotation(obj)
 
         converted.update({
-            'label_id': _cast(obj.label, int),
+            'label_id': cast(obj.label, int),
             'points': [float(p) for p in obj.points],
             'visibility': [int(v.value) for v in obj.visibility],
         })
@@ -183,7 +176,7 @@ def _convert_caption_object(self, obj):
         converted = self._convert_annotation(obj)
 
         converted.update({
-            'caption': _cast(obj.caption, str),
+            'caption': cast(obj.caption, str),
         })
         return converted
 
@@ -193,8 +186,8 @@ def _convert_label_categories(self, obj):
         }
         for label in obj.items:
             converted['labels'].append({
-                'name': _cast(label.name, str),
-                'parent': _cast(label.parent, str),
+                'name': cast(label.name, str),
+                'parent': cast(label.parent, str),
             })
         return converted
 
@@ -218,7 +211,7 @@ def _convert_points_categories(self, obj):
         for label_id, item in obj.items.items():
             converted['items'].append({
                 'label_id': int(label_id),
-                'labels': [_cast(label, str) for label in item.labels],
+                'labels': [cast(label, str) for label in item.labels],
                 'adjacent': [int(v) for v in item.adjacent],
             })
         return converted