Support for WiderFace dataset format (cvat-ai#2864)

yasakova-anastasia · Maxim Zhiltsov · web-flow · commit 9f7d18150d76 · 2021-03-10T10:06:35.000+03:00
* Add support for WiderFace dataset format

* Add WiderFace to documentation

* update format docs

* Fix format descriptions

* Update Changelog

* Update Datumaro version

* Update Datumaro version to 0.1.6.1

* fix linter

* fix base.txt

* fix Changelog

* fix README

Co-authored-by: Maxim Zhiltsov &lt;maxim.zhiltsov@intel.com&gt;
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -20,6 +20,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - Pre-built [cvat_server](https://hub.docker.com/r/openvino/cvat_server) and
   [cvat_ui](https://hub.docker.com/r/openvino/cvat_ui) images were published on DockerHub (<https://github.com/openvinotoolkit/cvat/pull/2766>)
 - Project task subsets (<https://github.com/openvinotoolkit/cvat/pull/2774>)
+- [WiderFace](http://shuoyang1213.me/WIDERFACE/) format support (<https://github.com/openvinotoolkit/cvat/pull/2864>)
+- [VGGFace2](https://github.com/ox-vgg/vgg_face2) format support (<https://github.com/openvinotoolkit/cvat/pull/2865>)
 
 ### Changed
 
diff --git a/README.md b/README.md
@@ -62,6 +62,7 @@ For more information about supported formats look at the
 | [LabelMe 3.0](http://labelme.csail.mit.edu/Release3.0)                        | X      | X      |
 | [ImageNet](http://www.image-net.org)                                          | X      | X      |
 | [CamVid](http://mi.eng.cam.ac.uk/research/projects/VideoRec/CamVid/)          | X      | X      |
+| [WIDER Face](http://shuoyang1213.me/WIDERFACE/)                               | X      | X      |
 | [VGGFace2](https://github.com/ox-vgg/vgg_face2)                               | X      | X      |
 
 ## Deep learning serverless functions for automatic labeling
diff --git a/cvat/apps/dataset_manager/formats/README.md b/cvat/apps/dataset_manager/formats/README.md
@@ -20,6 +20,7 @@
   - [TF detection API](#tfrecord)
   - [ImageNet](#imagenet)
   - [CamVid](#camvid)
+  - [WIDER Face](#widerface)
   - [VGGFace2](#vggface2)
 
 ## How to add a new annotation format support<a id="how-to-add"></a>
@@ -876,6 +877,36 @@ Uploaded file: a zip archive of the structure above
 
 - supported annotations: Polygons
 
+### [WIDER Face](http://shuoyang1213.me/WIDERFACE/)<a id="widerface" />
+
+#### WIDER Face Dumper
+
+Downloaded file: a zip archive of the following structure:
+
+```bash
+taskname.zip/
+├── labels.txt # optional
+├── wider_face_split/
+│   └── wider_face_<any_subset_name>_bbx_gt.txt
+└── WIDER_<any_subset_name>/
+    └── images/
+        ├── 0--label0/
+        │   └── 0_label0_image1.jpg
+        └── 1--label1/
+            └── 1_label1_image2.jpg
+```
+
+- supported annotations: Rectangles (with attributes), Labels
+- supported attributes: `blur`, `expression`, `illumination`,
+  `occluded` (both the annotation property & an attribute), `pose`, `invalid`
+
+#### WIDER Face Loader
+
+Uploaded file: a zip archive of the structure above
+
+- supported annotations: Rectangles (with attributes), Labels
+- supported attributes: `blur`, `expression`, `illumination`, `occluded`, `pose`, `invalid`
+
 ### [VGGFace2](https://github.com/ox-vgg/vgg_face2)<a id="vggface2" />
 
 #### VGGFace2 Dumper
diff --git a/cvat/apps/dataset_manager/formats/registry.py b/cvat/apps/dataset_manager/formats/registry.py
@@ -95,4 +95,5 @@ def make_exporter(name):
 import cvat.apps.dataset_manager.formats.yolo
 import cvat.apps.dataset_manager.formats.imagenet
 import cvat.apps.dataset_manager.formats.camvid
+import cvat.apps.dataset_manager.formats.widerface
 import cvat.apps.dataset_manager.formats.vggface2
diff --git a/cvat/apps/dataset_manager/formats/widerface.py b/cvat/apps/dataset_manager/formats/widerface.py
@@ -0,0 +1,32 @@
+# Copyright (C) 2021 Intel Corporation
+#
+# SPDX-License-Identifier: MIT
+
+import zipfile
+from tempfile import TemporaryDirectory
+
+from datumaro.components.dataset import Dataset
+
+from cvat.apps.dataset_manager.bindings import CvatTaskDataExtractor, \
+    import_dm_annotations
+from cvat.apps.dataset_manager.util import make_zip_archive
+
+from .registry import dm_env, exporter, importer
+
+
+@exporter(name='WiderFace', ext='ZIP', version='1.0')
+def _export(dst_file, task_data, save_images=False):
+    dataset = Dataset.from_extractors(CvatTaskDataExtractor(
+        task_data, include_images=save_images), env=dm_env)
+    with TemporaryDirectory() as temp_dir:
+        dataset.export(temp_dir, 'wider_face', save_images=save_images)
+
+        make_zip_archive(temp_dir, dst_file)
+
+@importer(name='WiderFace', ext='ZIP', version='1.0')
+def _import(src_file, task_data):
+    with TemporaryDirectory() as tmp_dir:
+        zipfile.ZipFile(src_file).extractall(tmp_dir)
+
+        dataset = Dataset.import_from(tmp_dir, 'wider_face', env=dm_env)
+        import_dm_annotations(dataset, task_data)
diff --git a/cvat/apps/dataset_manager/tests/test_formats.py b/cvat/apps/dataset_manager/tests/test_formats.py
@@ -282,6 +282,7 @@ def test_export_formats_query(self):
             'YOLO 1.1',
             'ImageNet 1.0',
             'CamVid 1.0',
+            'WiderFace 1.0',
             'VGGFace2 1.0',
         })
 
@@ -301,6 +302,7 @@ def test_import_formats_query(self):
             'YOLO 1.1',
             'ImageNet 1.0',
             'CamVid 1.0',
+            'WiderFace 1.0',
             'VGGFace2 1.0',
         })
 
@@ -342,6 +344,7 @@ def test_empty_images_are_exported(self):
             ('YOLO 1.1', 'yolo'),
             ('ImageNet 1.0', 'imagenet_txt'),
             ('CamVid 1.0', 'camvid'),
+            ('WiderFace 1.0', 'wider_face'),
             ('VGGFace2 1.0', 'vgg_face2'),
         ]:
             with self.subTest(format=format_name):
diff --git a/cvat/apps/engine/tests/test_rest_api.py b/cvat/apps/engine/tests/test_rest_api.py
@@ -2595,6 +2595,32 @@ def _create_task(self, owner, assignee):
                     ]
                 },
                 {"name": "person"},
+                {
+                    "name": "widerface",
+                    "attributes": [
+                        {
+                            "name": "blur",
+                            "mutable": False,
+                            "input_type": "select",
+                            "default_value": "0",
+                            "values": ["0", "1", "2"]
+                        },
+                        {
+                            "name": "expression",
+                            "mutable": False,
+                            "input_type": "select",
+                            "default_value": "0",
+                            "values": ["0", "1"]
+                        },
+                        {
+                            "name": "illumination",
+                            "mutable": False,
+                            "input_type": "select",
+                            "default_value": "0",
+                            "values": ["0", "1"]
+                        },
+                    ]
+                },
             ]
         }
 
@@ -3716,6 +3742,30 @@ def _get_initial_annotation(annotation_format):
                 "occluded": False,
             }]
 
+            rectangle_shapes_with_wider_attrs = [{
+                    "frame": 0,
+                    "label_id": task["labels"][2]["id"],
+                    "group": 0,
+                    "source": "manual",
+                    "attributes": [
+                        {
+                            "spec_id": task["labels"][2]["attributes"][0]["id"],
+                            "value": task["labels"][2]["attributes"][0]["default_value"]
+                        },
+                        {
+                            "spec_id": task["labels"][2]["attributes"][1]["id"],
+                            "value": task["labels"][2]["attributes"][1]["values"][1]
+                        },
+                        {
+                            "spec_id": task["labels"][2]["attributes"][2]["id"],
+                            "value": task["labels"][2]["attributes"][2]["default_value"]
+                        }
+                    ],
+                    "points": [1.0, 2.1, 10.6, 53.22],
+                    "type": "rectangle",
+                    "occluded": False,
+                }]
+
             rectangle_shapes_wo_attrs = [{
                 "frame": 1,
                 "label_id": task["labels"][1]["id"],
@@ -3864,6 +3914,10 @@ def _get_initial_annotation(annotation_format):
                 annotations["shapes"] = rectangle_shapes_wo_attrs \
                                       + polygon_shapes_wo_attrs
 
+            elif annotation_format == "WiderFace 1.0":
+                annotations["tags"] = tags_wo_attrs
+                annotations["shapes"] = rectangle_shapes_with_wider_attrs
+
             elif annotation_format == "VGGFace2 1.0":
                 annotations["tags"] = tags_wo_attrs
                 annotations["shapes"] = points_wo_attrs \
