Add files with duplicate annotations across files

files-registry.txt

@@ -1,4 +1,4 @@
-DATA_DESCRIPTION.md 7898e104bac65573ccd96129404e57d05e5b3850fd288f78f707b790bfa1826c
+DATA_DESCRIPTION.md 8e25497ac0a5f3afe70cd92df84c1d9eba4d5a45172b73c7e78830c30c098db6
 test_annotations/medium_bboxes_dataset_COCO/COCO_JSON_sample_1.json 8bdea1ed408aaf6ad5eb8deed2f47c16fcff35697ad4983f59afb7462de9c5df
 test_annotations/medium_bboxes_dataset_COCO/COCO_JSON_sample_2.json 7ea3d6d152921294e0ab71740249c87eb5aecbb95a2b6554ab3e89a1d4e59b82
 test_annotations/medium_bboxes_dataset_VIA/VIA_JSON_sample_1.json 3d197d8fbd6121a32d729486c7511eb6d8451371a67fbae791a2309f27c8fb19
@@ -11,3 +11,7 @@ test_annotations/small_bboxes_dataset_errors/small_bboxes_non_unique_img_id_COCO
 test_annotations/small_bboxes_dataset_no_categories/small_bboxes_no_cat_COCO.json 56bb5934e3552a76dd512948d6e4b0ff93037d92b67549a571f10b1b597c2b7d
 test_annotations/small_bboxes_dataset_no_categories/small_bboxes_no_cat_VIA.json 4187c3a265aecd42010b77f6d09db68ea2369c20e2ab336877c079de990b0e14
 test_annotations/small_bboxes_dataset_no_categories/small_bboxes_null_catID_COCO.json 3e34ba1cfd6e176f96aeffe2d3dbe44ee4326c2368fb1c8beb7e1cdd069c7386
+test_annotations/small_bboxes_dataset_subset/small_bboxes_COCO_subset.json 63a5b2cbdf5929dfdf69b50b89635b7198904591c4b69a8d3aa48cfad7227de2
+test_annotations/small_bboxes_dataset_subset/small_bboxes_COCO_subset_plus.json 7dad577c1b0dac454ec6071994715a320286f5128fd5ef8816dacea4a73b6c75
+test_annotations/small_bboxes_dataset_subset/small_bboxes_VIA_subset.json 29b776000d4cd66d860a18cb6f983d8db2095e15cc23df0bde37bd24bec4937b
+test_annotations/small_bboxes_dataset_subset/small_bboxes_VIA_subset_plus.json a1bf2139a98cb1a9ff7fd10b2ce7746396e34c474af4ccf219f4350bf08c6e21

test_data/DATA_DESCRIPTION.md

@@ -54,4 +54,15 @@ Small size bounding boxes datasets with errors to catch.
 
 | File name | Type | Format | N annotations | N images | Comments |
 | --- | --- | --- | --- | --- | --- |
-| `small_bboxes_non_unique_img_id_COCO.json` | bboxes | COCO | 4 | 4 | Two images have the same filename and image ID. This happens if two images have the same number-based filename, because the imageID is extracted using [`parseInt`](https://developer.mozilla.org/en-US/docs/Web/JavaScript/Reference/Global_Objects/parseInt) when exporting as COCO in the VIA tool.|
+| `small_bboxes_non_unique_img_id_COCO.json` | bboxes | COCO | 4 | 4 | Two images have the same filename and image ID. This happens if two images have the same number-based filename, because the imageID is extracted using [`parseInt`](https://developer.mozilla.org/en-US/docs/Web/JavaScript/Reference/Global_Objects/parseInt) when exporting as COCO in the VIA tool.|
+
+
+#### `small_bboxes_dataset_subset`
+A subset of the corresponding small bounding boxes datasets. If prefixed with `_plus` it contains some additional annotations. See description of the corresponding dataset for more details. The files with the same name except for the format identifier contain the exact same annotations.
+
+| File name | Type | Format | N annotations | N images | Comments |
+| --- | --- | --- | --- | --- | --- |
+| `small_bboxes_VIA_subset.json` | bboxes | VIA | 2 | 3 | Same as `small_bboxes_VIA.json` but the last annotation in the last frame has been removed. |
+| `small_bboxes_VIA_subset_plus.json` | bboxes | VIA | 3 | 3 | Same as `small_bboxes_VIA_subset.json` but with one additional annotation, different from any of the annotations in `small_bboxes_VIA.json`.|
+| `small_bboxes_COCO_subset.json` | bboxes | VIA | 2 | 3 | Same as `small_bboxes_COCO.json` but the last annotation in the last frame has been removed. |
+| `small_bboxes_COCO_subset_plus.json` | bboxes | VIA | 3 | 3 | Same as `small_bboxes_COCO_subset.json` but with one additional annotation, different from any of the annotations in `small_bboxes_COCO.json`.|

test_data/test_annotations/small_bboxes_dataset_subset/small_bboxes_COCO_subset.json

@@ -0,0 +1 @@
+{"info":{"year":2025,"version":"1.0","description":"VIA project exported to COCO format using VGG Image Annotator (http://www.robots.ox.ac.uk/~vgg/software/via/)","contributor":"","url":"http://www.robots.ox.ac.uk/~vgg/software/via/","date_created":"Mon Feb 10 2025 20:54:55 GMT+0000 (Greenwich Mean Time)"},"images":[{"id":0,"width":1280,"height":720,"file_name":"00000.jpg","license":0,"date_captured":""},{"id":83,"width":1280,"height":720,"file_name":"00083.jpg","license":0,"date_captured":""},{"id":166,"width":1280,"height":720,"file_name":"00166.jpg","license":0,"date_captured":""}],"annotations":[{"segmentation":[[963,283,1265,283,1265,455,963,455]],"area":51944,"bbox":[963,283,302,172],"iscrowd":0,"id":1,"image_id":0,"category_id":1},{"segmentation":[[376,314,677,314,677,437,376,437]],"area":37023,"bbox":[376,314,301,123],"iscrowd":0,"id":2,"image_id":83,"category_id":1}],"licenses":[{"id":0,"name":"Unknown License","url":""}],"categories":[{"supercategory":"animal","id":1,"name":"crab"}]}

test_data/test_annotations/small_bboxes_dataset_subset/small_bboxes_COCO_subset_plus.json

@@ -0,0 +1 @@
+{"info":{"year":2025,"version":"1.0","description":"VIA project exported to COCO format using VGG Image Annotator (http://www.robots.ox.ac.uk/~vgg/software/via/)","contributor":"","url":"http://www.robots.ox.ac.uk/~vgg/software/via/","date_created":"Mon Feb 10 2025 20:56:35 GMT+0000 (Greenwich Mean Time)"},"images":[{"id":0,"width":1280,"height":720,"file_name":"00000.jpg","license":0,"date_captured":""},{"id":83,"width":1280,"height":720,"file_name":"00083.jpg","license":0,"date_captured":""},{"id":166,"width":1280,"height":720,"file_name":"00166.jpg","license":0,"date_captured":""}],"annotations":[{"segmentation":[[963,283,1265,283,1265,455,963,455]],"area":51944,"bbox":[963,283,302,172],"iscrowd":0,"id":1,"image_id":0,"category_id":1},{"segmentation":[[376,314,677,314,677,437,376,437]],"area":37023,"bbox":[376,314,301,123],"iscrowd":0,"id":2,"image_id":83,"category_id":1},{"segmentation":[[587,334,656,334,656,383,587,383]],"area":3381,"bbox":[587,334,69,49],"iscrowd":0,"id":3,"image_id":166,"category_id":1}],"licenses":[{"id":0,"name":"Unknown License","url":""}],"categories":[{"supercategory":"animal","id":1,"name":"crab"}]}

test_data/test_annotations/small_bboxes_dataset_subset/small_bboxes_VIA_subset.json

@@ -0,0 +1 @@
+{"_via_settings":{"ui":{"annotation_editor_height":25,"annotation_editor_fontsize":0.8,"leftsidebar_width":18,"image_grid":{"img_height":80,"rshape_fill":"none","rshape_fill_opacity":0.3,"rshape_stroke":"yellow","rshape_stroke_width":2,"show_region_shape":true,"show_image_policy":"all"},"image":{"region_label":"__via_region_id__","region_color":"__via_default_region_color__","region_label_font":"10px Sans","on_image_annotation_editor_placement":"NEAR_REGION"}},"core":{"buffer_size":18,"filepath":{},"default_filepath":""},"project":{"name":"via_project_10Feb2025_20h53m"}},"_via_img_metadata":{"0":{"filename":"00000.jpg","size":322877,"regions":[{"shape_attributes":{"name":"rect","x":963,"y":283,"width":302,"height":172},"region_attributes":{"animal":"1"}}],"file_attributes":{"width":1280,"height":720}},"83":{"filename":"00083.jpg","size":311221,"regions":[{"shape_attributes":{"name":"rect","x":376,"y":314,"width":301,"height":123},"region_attributes":{"animal":"1"}}],"file_attributes":{"width":1280,"height":720}},"166":{"filename":"00166.jpg","size":324555,"regions":[],"file_attributes":{"width":1280,"height":720}}},"_via_attributes":{"region":{"animal":{"type":"radio","description":"coco[\"categories\"][0]={\"id\":1,\"name\":\"crab\",\"supercategory\":\"animal\"}","options":{"1":"crab"},"default_options":{}}},"file":{}},"_via_data_format_version":"2.0.10","_via_image_id_list":[0,83,166]}

test_data/test_annotations/small_bboxes_dataset_subset/small_bboxes_VIA_subset_plus.json

@@ -0,0 +1 @@
+{"_via_settings":{"ui":{"annotation_editor_height":25,"annotation_editor_fontsize":0.8,"leftsidebar_width":18,"image_grid":{"img_height":80,"rshape_fill":"none","rshape_fill_opacity":0.3,"rshape_stroke":"yellow","rshape_stroke_width":2,"show_region_shape":true,"show_image_policy":"all"},"image":{"region_label":"__via_region_id__","region_color":"__via_default_region_color__","region_label_font":"10px Sans","on_image_annotation_editor_placement":"NEAR_REGION"}},"core":{"buffer_size":18,"filepath":{},"default_filepath":""},"project":{"name":"via_project_10Feb2025_20h53m"}},"_via_img_metadata":{"0":{"filename":"00000.jpg","size":-1,"regions":[{"shape_attributes":{"name":"rect","x":963,"y":283,"width":302,"height":172},"region_attributes":{"animal":"1"}}],"file_attributes":{"width":1280,"height":720}},"83":{"filename":"00083.jpg","size":-1,"regions":[{"shape_attributes":{"name":"rect","x":376,"y":314,"width":301,"height":123},"region_attributes":{"animal":"1"}}],"file_attributes":{"width":1280,"height":720}},"166":{"filename":"00166.jpg","size":-1,"regions":[{"shape_attributes":{"name":"rect","x":587,"y":334,"width":69,"height":49},"region_attributes":{"animal":"1"}}],"file_attributes":{"width":1280,"height":720}}},"_via_attributes":{"region":{"animal":{"type":"radio","description":"coco[\"categories\"][0]={\"id\":1,\"name\":\"crab\",\"supercategory\":\"animal\"}","options":{"1":"crab"},"default_options":{}}},"file":{}},"_via_data_format_version":"2.0.10","_via_image_id_list":[0,83,166]}