Move annotation formats to dataset manager (#1256)

* Move formats to dataset manager

* Unify datataset export and anno export implementations

* Add track_id to TrackedShape, export tracked shapes

* Replace MOT format

* Replace LabelMe format

* Add new formats to dm

* Add dm tests

* Extend TrackedShape

* Enable dm test in CI

* Fix tests

* Add import

* Fix tests

* Fix mot track ids

* Fix mot format

* Update attribute logic in labelme tests

* Use common code in yolo

* Put datumaro in path in settings

* Expect labels file in MOT next to annotations file

* Add MOT format description

* Add import

* Add labelme format description

* Linter fix

* Linter fix2

* Compare attributes ordered

* Update docs

* Update tests

.travis.yml

@@ -13,5 +13,6 @@ before_script:
 
 script:
  - docker-compose -f docker-compose.yml -f docker-compose.ci.yml run cvat_ci /bin/bash -c 'python3 manage.py test cvat/apps utils/cli'
+ - docker-compose -f docker-compose.yml -f docker-compose.ci.yml run cvat_ci /bin/bash -c 'python3 manage.py test --pattern="_tests.py" cvat/apps/dataset_manager'
  - docker-compose -f docker-compose.yml -f docker-compose.ci.yml run cvat_ci /bin/bash -c 'python3 manage.py test datumaro/'
  - docker-compose -f docker-compose.yml -f docker-compose.ci.yml run cvat_ci /bin/bash -c 'cd cvat-data && npm install && cd ../cvat-core && npm install && npm run test && npm run coveralls'

cvat/apps/annotation/README.md

@@ -1,3 +1,5 @@
+<!--lint disable list-item-indent-->
+<!--lint disable no-duplicate-headings-->
 ## Description
 
 The purpose of this application is to add support for multiple annotation formats for CVAT.
@@ -525,10 +527,10 @@ python create_pascal_tf_record.py --data_dir <path to VOCdevkit> --set train --y
  │   └── Segmentation/
  │   └── default.txt # list of image names without extension
  ├── SegmentationClass/ # merged class masks
- │   └── image1.png
+ │   ├── image1.png
  │   └── image2.png
  └── SegmentationObject/ # merged instance masks
- └── image1.png
+ ├── image1.png
  └── image2.png
  ```
  Mask is a png image with several (RGB) channels where each pixel has own color which corresponds to a label.
@@ -557,11 +559,70 @@ python create_pascal_tf_record.py --data_dir <path to VOCdevkit> --set train --y
  │   └── Segmentation/
  │   └── <any_subset_name>.txt
  ├── SegmentationClass/
- │   └── image1.png
+ │   ├── image1.png
  │   └── image2.png
  └── SegmentationObject/
- └── image.png
+ ├── image1.png
  └── image2.png
  ```
 - supported shapes: Polygons
-- additional comments: the CVAT task should be created with the full label set that may be in the annotation files
+- additional comments: the CVAT task should be created with the full label set that may be in the annotation files
+
+### [MOT sequence](https://arxiv.org/pdf/1906.04567.pdf)
+#### Dumper
+- downloaded file: a zip archive of the following structure:
+ ```bash
+ taskname.zip/
+ ├── img1/
+ | ├── imgage1.jpg
+ | └── imgage2.jpg
+ └── gt/
+ ├── labels.txt
+ └── gt.txt
+
+ # labels.txt
+ cat
+ dog
+ person
+ ...
+
+ # gt.txt
+ # frame_id, track_id, x, y, w, h, "not ignored", class_id, visibility, <skipped>
+ 1,1,1363,569,103,241,1,1,0.86014
+ ...
+
+ ```
+- supported annotations: Rectangle shapes and tracks
+- supported attributes: `visibility` (number), `ignored` (checkbox)
+
+#### Loader
+- uploaded file: a zip archive of the structure above or:
+ ```bash
+ taskname.zip/
+ ├── labels.txt # optional, mandatory for non-official labels
+ └── gt.txt
+ ```
+- supported annotations: Rectangle tracks
+
+### [LabelMe](http://labelme.csail.mit.edu/Release3.0)
+#### Dumper
+- downloaded file: a zip archive of the following structure:
+ ```bash
+ taskname.zip/
+ ├── img1.jpg
+ └── img1.xml
+ ```
+- supported annotations: Rectangles, Polygons (with attributes)
+
+#### Loader
+- uploaded file: a zip archive of the following structure:
+ ```bash
+ taskname.zip/
+ ├── Masks/
+ | ├── img1_mask1.png
+ | └── img1_mask2.png
+ ├── img1.xml
+ ├── img2.xml
+ └── img3.xml
+ ```
+- supported annotations: Rectangles, Polygons, Masks (as polygons)

cvat/apps/annotation/annotation.py

@@ -104,8 +104,8 @@ class Annotation:
  Attribute = namedtuple('Attribute', 'name, value')
  LabeledShape = namedtuple('LabeledShape', 'type, frame, label, points, occluded, attributes, group, z_order')
  LabeledShape.__new__.__defaults__ = (0, 0)
- TrackedShape = namedtuple('TrackedShape', 'type, points, occluded, frame, attributes, outside, keyframe, z_order')
- TrackedShape.__new__.__defaults__ = (0, )
+ TrackedShape = namedtuple('TrackedShape', 'type, frame, points, occluded, outside, keyframe, attributes, group, z_order, label, track_id')
+ TrackedShape.__new__.__defaults__ = (0, 0, None, 0)
  Track = namedtuple('Track', 'label, group, shapes')
  Tag = namedtuple('Tag', 'frame, label, attributes, group')
  Tag.__new__.__defaults__ = (0, )
@@ -272,11 +272,14 @@ def _export_tracked_shape(self, shape):
  return Annotation.TrackedShape(
  type=shape["type"],
  frame=self._db_task.data.start_frame + shape["frame"] * self._frame_step,
+ label=self._get_label_name(shape["label_id"]),
  points=shape["points"],
  occluded=shape["occluded"],
+ z_order=shape.get("z_order", 0),
+ group=shape.get("group", 0),
  outside=shape.get("outside", False),
  keyframe=shape.get("keyframe", True),
- z_order=shape["z_order"],
+ track_id=shape["track_id"],
  attributes=self._export_attributes(shape["attributes"]),
  )
 
@@ -318,7 +321,11 @@ def _get_frame(annotations, shape):
  annotations = {}
  data_manager = DataManager(self._annotation_ir)
  for shape in sorted(data_manager.to_shapes(self._db_task.data.size), key=lambda shape: shape.get("z_order", 0)):
- _get_frame(annotations, shape).labeled_shapes.append(self._export_labeled_shape(shape))
+ if 'track_id' in shape:
+ exported_shape = self._export_tracked_shape(shape)
+ else:
+ exported_shape = self._export_labeled_shape(shape)
+ _get_frame(annotations, shape).labeled_shapes.append(exported_shape)
 
  for tag in self._annotation_ir.tags:
  _get_frame(annotations, tag).tags.append(self._export_tag(tag))
@@ -332,14 +339,17 @@ def shapes(self):
 
  @property
  def tracks(self):
- for track in self._annotation_ir.tracks:
+ for idx, track in enumerate(self._annotation_ir.tracks):
  tracked_shapes = TrackManager.get_interpolated_shapes(track, 0, self._db_task.data.size)
  for tracked_shape in tracked_shapes:
  tracked_shape["attributes"] += track["attributes"]
+ tracked_shape["track_id"] = idx
+ tracked_shape["group"] = track["group"]
+ tracked_shape["label_id"] = track["label_id"]
 
  yield Annotation.Track(
  label=self._get_label_name(track["label_id"]),
- group=track['group'],
+ group=track["group"],
  shapes=[self._export_tracked_shape(shape) for shape in tracked_shapes],
  )
 

cvat/apps/annotation/format.py

@@ -11,12 +11,10 @@
 
 def register_format(format_file):
  source_code = open(format_file, 'r').read()
- global_vars = {
- "__builtins__": {},
- }
+ global_vars = {}
  exec(source_code, global_vars)
  if "format_spec" not in global_vars or not isinstance(global_vars["format_spec"], dict):
- raise Exception("Could not find \'format_spec\' definition in format file specification")
+ raise Exception("Could not find 'format_spec' definition in format file specification")
 
  format_spec = deepcopy(global_vars["format_spec"])
  format_spec["handler_file"] = File(open(format_file))