Add ImageNet format

cvat/apps/dataset_manager/formats/README.md

@@ -18,6 +18,7 @@
   - [PASCAL VOC and mask](#voc)
   - [YOLO](#yolo)
   - [TF detection API](#tfrecord)
+  - [ImageNet](#imagenet)
 
 ## How to add a new annotation format support<a id="how-to-add"></a>
 
@@ -802,3 +803,35 @@ taskname.zip/
 ```
 
 - supported annotations: Rectangles, Polygons, Masks (as polygons)
+
+### [ImageNet](http://www.image-net.org)<a id="imagenet" />
+
+#### ImageNet Dumper
+
+Downloaded file: a zip archive of the following structure:
+
+```bash
+# if we save images:
+taskname.zip/
+└── label1/
+    ├── label1_image1.jpg
+    └── label1_image2.jpg
+└── label2/
+    ├── label2_image1.jpg
+    ├── label2_image3.jpg
+    └── label2_image4.jpg
+
+# if we keep only annotation:
+taskname.zip/
+└── <any_subset_name>.txt
+└── synsets.txt
+
+```
+
+- supported annotations: Labels
+
+#### ImageNet Loader
+
+Uploaded file: a zip archive of the structure above
+
+- supported annotations: Labels

cvat/apps/dataset_manager/formats/imagenet.py

@@ -0,0 +1,41 @@
+# Copyright (C) 2020 Intel Corporation
+#
+# SPDX-License-Identifier: MIT
+
+import os.path as osp
+from glob import glob
+
+import zipfile
+from tempfile import TemporaryDirectory
+
+from datumaro.components.project 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='ImageNet', ext='ZIP', version='1.0')
+def _export(dst_file, task_data, save_images=False):
+    extractor = CvatTaskDataExtractor(task_data, include_images=save_images)
+    extractor = Dataset.from_extractors(extractor) # apply lazy transform
+    with TemporaryDirectory() as temp_dir:
+        if save_images:
+            dm_env.converters.get('imagenet').convert(extractor,
+                save_dir=temp_dir, save_images=save_images)
+        else:
+            dm_env.converters.get('imagenet_txt').convert(extractor,
+                save_dir=temp_dir, save_images=save_images)
+
+        make_zip_archive(temp_dir, dst_file)
+
+@importer(name='ImageNet', ext='ZIP', version='1.0')
+def _import(src_file, task_data):
+    with TemporaryDirectory() as tmp_dir:
+        zipfile.ZipFile(src_file).extractall(tmp_dir)
+        if glob(osp.join(tmp_dir, '*.txt')):
+            dataset = dm_env.make_importer('imagenet_txt')(tmp_dir).make_dataset()
+        else:
+            dataset = dm_env.make_importer('imagenet')(tmp_dir).make_dataset()
+        import_dm_annotations(dataset, task_data)

cvat/apps/dataset_manager/formats/registry.py

@@ -90,4 +90,5 @@ def make_exporter(name):
 import cvat.apps.dataset_manager.formats.mots
 import cvat.apps.dataset_manager.formats.pascal_voc
 import cvat.apps.dataset_manager.formats.tfrecord
-import cvat.apps.dataset_manager.formats.yolo
+import cvat.apps.dataset_manager.formats.yolo
+import cvat.apps.dataset_manager.formats.imagenet

cvat/apps/dataset_manager/tests/test_formats.py

@@ -271,6 +271,7 @@ def test_export_formats_query(self):
             'Segmentation mask 1.1',
             'TFRecord 1.0',
             'YOLO 1.1',
+            'ImageNet 1.0',
         })
 
     def test_import_formats_query(self):
@@ -287,6 +288,7 @@ def test_import_formats_query(self):
             'Segmentation mask 1.1',
             'TFRecord 1.0',
             'YOLO 1.1',
+            'ImageNet 1.0',
         })
 
     def test_exports(self):
@@ -322,6 +324,7 @@ def test_empty_images_are_exported(self):
             ('Segmentation mask 1.1', 'voc'),
             ('TFRecord 1.0', 'tf_detection_api'),
             ('YOLO 1.1', 'yolo'),
+            ('ImageNet 1.0', 'imagenet_txt'),
         ]:
             with self.subTest(format=format_name):
                 if not dm.formats.registry.EXPORT_FORMATS[format_name].ENABLED:

cvat/apps/engine/tests/test_rest_api.py

@@ -3355,6 +3355,9 @@ def _get_initial_annotation(annotation_format):
                                       + polygon_shapes_with_attrs
                 annotations["tags"] = tags_with_attrs + tags_wo_attrs
 
+            elif annotation_format == "ImageNet 1.0":
+                annotations["tags"] = tags_wo_attrs
+
             else:
                 raise Exception("Unknown format {}".format(annotation_format))