Fix spelling errors

CHANGELOG.md

@@ -8,7 +8,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 ### Added
-- Support for escaping in attribiute values in LabelMe format (<https://github.com/openvinotoolkit/datumaro/issues/49>)
+- Support for escaping in attribute values in LabelMe format (<https://github.com/openvinotoolkit/datumaro/issues/49>)
 - Support for Segmentation Splitting (<https://github.com/openvinotoolkit/datumaro/pull/223>)
 - Support for CIFAR-10/100 dataset format (<https://github.com/openvinotoolkit/datumaro/pull/225>, <https://github.com/openvinotoolkit/datumaro/pull/243>)
 - Support for COCO panoptic and stuff format (<https://github.com/openvinotoolkit/datumaro/pull/210>)
@@ -175,7 +175,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 ### Added
 - `CamVid` dataset format (<https://github.com/openvinotoolkit/datumaro/pull/57>)
 - Ability to install `opencv-python-headless` dependency with `DATUMARO_HEADLESS=1`
-  enviroment variable instead of `opencv-python` (<https://github.com/openvinotoolkit/datumaro/pull/62>)
+  environment variable instead of `opencv-python` (<https://github.com/openvinotoolkit/datumaro/pull/62>)
 
 ### Changed
 - Allow empty supercategory in COCO (<https://github.com/openvinotoolkit/datumaro/pull/54>)

README.md

@@ -152,7 +152,7 @@ CVAT annotations                             ---> Publication, statistics etc.
     - keep only vertically-oriented images
     - remove small area bounding boxes from annotations
   - Annotation conversions, for instance:
-    - polygons to instance masks and vise-versa
+    - polygons to instance masks and vice-versa
     - apply a custom colormap for mask annotations
     - rename or remove dataset labels
   - Splitting a dataset into multiple subsets like `train`, `val`, and `test`:
@@ -170,7 +170,7 @@ CVAT annotations                             ---> Publication, statistics etc.
       - sampling with Entropy based algorithm
 - Dataset quality checking
   - Simple checking for errors
-  - Comparison with model infernece
+  - Comparison with model inference
   - Merging and comparison of multiple datasets
   - Annotation validation based on the task type(classification, etc)
 - Dataset comparison

datumaro/components/extractor.py

@@ -1,5 +1,5 @@
 
-# Copyright (C) 2019-2020 Intel Corporation
+# Copyright (C) 2019-2021 Intel Corporation
 #
 # SPDX-License-Identifier: MIT
 
@@ -69,7 +69,7 @@ def from_iterable(cls, iterable):
             iterable ([type]): This iterable object can be:
             1)simple str - will generate one Category with str as name
             2)list of str - will interpreted as list of Category names
-            3)list of positional argumetns - will generate Categories
+            3)list of positional arguments - will generate Categories
             with this arguments
 
 
@@ -448,7 +448,7 @@ def from_iterable(cls, iterable):
 
         Args:
             iterable ([type]): This iterable object can be:
-            1) list of positional argumetns - will generate Categories
+            1) list of positional arguments - will generate Categories
                 with these arguments
 
         Returns:

datumaro/components/operations.py

@@ -1,4 +1,4 @@
-# Copyright (C) 2020 Intel Corporation
+# Copyright (C) 2020-2021 Intel Corporation
 #
 # SPDX-License-Identifier: MIT
 
@@ -153,7 +153,7 @@ class Conf:
         quorum = attrib(converter=int, default=0)
         ignored_attributes = attrib(converter=set, factory=set)
 
-        def _groups_conveter(value):
+        def _groups_converter(value):
             result = []
             for group in value:
                 rg = set()
@@ -163,7 +163,7 @@ def _groups_conveter(value):
                     rg.add((name, optional))
                 result.append(rg)
             return result
-        groups = attrib(converter=_groups_conveter, factory=list)
+        groups = attrib(converter=_groups_converter, factory=list)
         close_distance = attrib(converter=float, default=0.75)
     conf = attrib(converter=ensure_cls(Conf), factory=Conf)
 

datumaro/plugins/accuracy_checker_plugin/details/ac.py

@@ -1,10 +1,10 @@
 
-# Copyright (C) 2020 Intel Corporation
+# Copyright (C) 2020-2021 Intel Corporation
 #
 # SPDX-License-Identifier: MIT
 
 from datumaro.util.tf_util import import_tf
-import_tf() # prevent TF loading and potential interpeter crash
+import_tf() # prevent TF loading and potential interpreter crash
 
 from itertools import groupby
 

datumaro/plugins/accuracy_checker_plugin/details/representation.py

@@ -1,10 +1,10 @@
 
-# Copyright (C) 2020 Intel Corporation
+# Copyright (C) 2020-2021 Intel Corporation
 #
 # SPDX-License-Identifier: MIT
 
 from datumaro.util.tf_util import import_tf
-import_tf() # prevent TF loading and potential interpeter crash
+import_tf() # prevent TF loading and potential interpreter crash
 
 import accuracy_checker.representation as ac
 

datumaro/plugins/cifar_format.py

@@ -1,4 +1,4 @@
-# Copyright (C) 2020 Intel Corporation
+# Copyright (C) 2020-2021 Intel Corporation
 #
 # SPDX-License-Identifier: MIT
 
@@ -161,7 +161,7 @@ def apply(self):
             annotation_dict['data'] = np.array(data)
             if len(image_sizes):
                 size = (CifarPath.IMAGE_SIZE, CifarPath.IMAGE_SIZE)
-                # 'image_sizes' isn't included in the standart format,
+                # 'image_sizes' isn't included in the standard format,
                 # needed for different image sizes
                 annotation_dict['image_sizes'] = [image_sizes.get(p, size)
                     for p in range(len(data))]

datumaro/plugins/ndr.py

@@ -1,4 +1,4 @@
-# Copyright (C) 2020 Intel Corporation
+# Copyright (C) 2020-2021 Intel Corporation
 #
 # SPDX-License-Identifier: MIT
 
@@ -173,7 +173,7 @@ def _remove(self):
                             (item.id, len(img.shape)))
 
                 if self.algorithm == Algorithm.gradient:
-                    # Caculate gradient
+                    # Calculate gradient
                     img = self._cgrad_feature(img)
                 else :
                     raise NotImplementedError()
@@ -267,7 +267,7 @@ def _keep_cut(self, num_cut, all_key, fidx,
                 # of the collision(number of same hash key)
                 # [x1, x2, y1, y2, y3, y4, z1, z2, z3]. x, y and z for hash key
                 # i.e. there are 4 elements which have hash key y.
-                # then the occurence will be [2, 4, 3] and reverse of them
+                # then the occurrence will be [2, 4, 3] and reverse of them
                 # will be [1/2, 1/4, 1/3]
                 # Normalizing them by dividing with sum, we get [6/13, 3/13, 4/13]
                 # Then the key x will be sampled with probability 6/13

datumaro/plugins/splitter.py

@@ -1,4 +1,4 @@
-# Copyright (C) 2020 Intel Corporation
+# Copyright (C) 2020-2021 Intel Corporation
 #
 # SPDX-License-Identifier: MIT
 
@@ -31,7 +31,7 @@ class Split(Transform, CliPlugin):
     Each image can have multiple object annotations -
     (bbox, mask, polygon). Since an image shouldn't be included
     in multiple subsets at the same time, and image annotations
-    shoudln't be split, in general, dataset annotations are unlikely
+    shouldn't be split, in general, dataset annotations are unlikely
     to be split exactly in the specified ratio. |n
     This split tries to split dataset images as close as possible
     to the specified ratio, keeping the initial class distribution.|n
@@ -684,7 +684,7 @@ class _InstanceSpecificSplit(_TaskSpecificSplit):
     each image can have multiple object annotations -
     (instance bounding boxes, masks, polygons). Since an image shouldn't be included
     in multiple subsets at the same time, and image annotations
-    shoudln't be split, in general, dataset annotations are unlikely to be split
+    shouldn't be split, in general, dataset annotations are unlikely to be split
     exactly in the specified ratio. |n
     This split tries to split dataset images as close as possible
     to the specified ratio, keeping the initial class distribution.|n

docs/cli_design.mm

@@ -9,7 +9,7 @@
 <node CREATED="1562592677270" ID="ID_1205701076" MODIFIED="1574330175510" TEXT="Generates a project from other project or dataset in a specific format"/>
 </node>
 <node CREATED="1562592764462" ID="ID_724395644" MODIFIED="1579775533832" TEXT="export">
-<node CREATED="1562592918908" ID="ID_44929477" MODIFIED="1574330221398" TEXT="Saves dataset in a specfic format"/>
+<node CREATED="1562592918908" ID="ID_44929477" MODIFIED="1574330221398" TEXT="Saves dataset in a specific format"/>
 </node>
 <node CREATED="1562593914751" ID="ID_378739335" MODIFIED="1579775533832" TEXT="extract">
 <node CREATED="1562593918968" ID="ID_424607257" MODIFIED="1569929409897" TEXT="Extracts subproject by filter"/>

docs/developer_guide.md

@@ -72,7 +72,7 @@ class colors for masks, class attributes.
 This information is stored in `dataset.categories`, which is a mapping from
 `AnnotationType` to a corresponding `...Categories` class. Each annotation type
 can have its `Categories`. Typically, there will be a `LabelCategories` object.
-Annotations and other categories adress dataset labels
+Annotations and other categories address dataset labels
 by their indices in this object.
 
 The main operation for a dataset is iteration over its elements.

docs/formats/cityscapes_user_manual.md

@@ -133,7 +133,7 @@ to get more information about these operations.
 There are few examples of using Datumaro operations to solve
 particular problems with Cityscapes dataset:
 
-### Example 1. How to load an original Cityscapes dataset ans convert to Pascal VOC
+### Example 1. How to load an original Cityscapes dataset and convert to Pascal VOC
 
 ```bash
 datum create -o project

docs/formats/coco_user_manual.md

@@ -181,7 +181,7 @@ to get more information about these operations.
 There are few examples of using Datumaro operations to solve
 particular problems with COCO dataset:
 
-### Example 1. How to load an original panoptic COCO dataset ans convert to Pascal VOC
+### Example 1. How to load an original panoptic COCO dataset and convert to Pascal VOC
 
 ```bash
 datum create -o project

docs/user_manual.md

@@ -1348,7 +1348,7 @@ pip install 'git+https://github.com/openvinotoolkit/open_model_zoo.git#subdirect
 #### OpenVINO™
 
 This plugin provides support for model inference with [OpenVINO™](https://01.org/openvinotoolkit).
-The plugin depends on the OpenVINO™ Tookit, which can be installed by
+The plugin depends on the OpenVINO™ Toolkit, which can be installed by
 following [these instructions](https://docs.openvinotoolkit.org/latest/index.html#packaging_and_deployment)
 
 ### Dataset Formats

tests/cli/test_voc_format.py

@@ -68,13 +68,13 @@ def test_preparing_dataset_for_train_model(self):
             run(self, 'filter', '-p', test_dir, '-m', 'i+a',
                 '-e', "/item/annotation[occluded='False']", '-o', result_path)
 
-            splitted_path = osp.join(test_dir, 'splitted')
-            run(self, 'transform', '-p', result_path, '-o', splitted_path,
+            split_path = osp.join(test_dir, 'split')
+            run(self, 'transform', '-p', result_path, '-o', split_path,
                 '-t', 'random_split', '--', '-s', 'test:.5',
                 '-s', 'train:.5', '--seed', '1')
 
             export_path = osp.join(test_dir, 'dataset')
-            run(self, 'export', '-p', splitted_path, '-f', 'voc',
+            run(self, 'export', '-p', split_path, '-f', 'voc',
                 '-o', export_path, '--', '--label-map', 'voc')
 
             parsed_dataset = Dataset.import_from(export_path, format='voc')

tests/test_dataset.py

@@ -458,7 +458,7 @@ def __iter__(self):
 
         self.assertTrue(iter_called)
 
-    def test_can_chain_lazy_tranforms(self):
+    def test_can_chain_lazy_transforms(self):
         iter_called = False
         class TestExtractor(Extractor):
             def __iter__(self):