File size: 9,930 Bytes
938e515
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
# Copyright (c) Facebook, Inc. and its affiliates.
import logging
import os

from detectron2.data import DatasetCatalog, MetadataCatalog
from detectron2.structures import BoxMode
from detectron2.utils.file_io import PathManager
from fvcore.common.timer import Timer

from .builtin_meta import _get_coco_instances_meta
from .lvis_v0_5_categories import LVIS_CATEGORIES as LVIS_V0_5_CATEGORIES
from .lvis_v1_categories import LVIS_CATEGORIES as LVIS_V1_CATEGORIES
from .lvis_v1_category_image_count import (
    LVIS_CATEGORY_IMAGE_COUNT as LVIS_V1_CATEGORY_IMAGE_COUNT,
)

"""
This file contains functions to parse LVIS-format annotations into dicts in the
"Detectron2 format".
"""

logger = logging.getLogger(__name__)

__all__ = ["load_lvis_json", "register_lvis_instances", "get_lvis_instances_meta"]


def register_lvis_instances(name, metadata, json_file, image_root):
    """
    Register a dataset in LVIS's json annotation format for instance detection and segmentation.

    Args:
        name (str): a name that identifies the dataset, e.g. "lvis_v0.5_train".
        metadata (dict): extra metadata associated with this dataset. It can be an empty dict.
        json_file (str): path to the json instance annotation file.
        image_root (str or path-like): directory which contains all the images.
    """
    DatasetCatalog.register(name, lambda: load_lvis_json(json_file, image_root, name))
    MetadataCatalog.get(name).set(
        json_file=json_file, image_root=image_root, evaluator_type="lvis", **metadata
    )


def load_lvis_json(
    json_file, image_root, dataset_name=None, extra_annotation_keys=None
):
    """
    Load a json file in LVIS's annotation format.

    Args:
        json_file (str): full path to the LVIS json annotation file.
        image_root (str): the directory where the images in this json file exists.
        dataset_name (str): the name of the dataset (e.g., "lvis_v0.5_train").
            If provided, this function will put "thing_classes" into the metadata
            associated with this dataset.
        extra_annotation_keys (list[str]): list of per-annotation keys that should also be
            loaded into the dataset dict (besides "bbox", "bbox_mode", "category_id",
            "segmentation"). The values for these keys will be returned as-is.

    Returns:
        list[dict]: a list of dicts in Detectron2 standard format. (See
        `Using Custom Datasets </tutorials/datasets.html>`_ )

    Notes:
        1. This function does not read the image files.
           The results do not have the "image" field.
    """
    from lvis import LVIS

    json_file = PathManager.get_local_path(json_file)

    timer = Timer()
    lvis_api = LVIS(json_file)
    if timer.seconds() > 1:
        logger.info(
            "Loading {} takes {:.2f} seconds.".format(json_file, timer.seconds())
        )

    if dataset_name is not None:
        meta = get_lvis_instances_meta(dataset_name)
        MetadataCatalog.get(dataset_name).set(**meta)

    # sort indices for reproducible results
    img_ids = sorted(lvis_api.imgs.keys())
    # imgs is a list of dicts, each looks something like:
    # {'license': 4,
    #  'url': 'http://farm6.staticflickr.com/5454/9413846304_881d5e5c3b_z.jpg',
    #  'file_name': 'COCO_val2014_000000001268.jpg',
    #  'height': 427,
    #  'width': 640,
    #  'date_captured': '2013-11-17 05:57:24',
    #  'id': 1268}
    imgs = lvis_api.load_imgs(img_ids)
    # anns is a list[list[dict]], where each dict is an annotation
    # record for an object. The inner list enumerates the objects in an image
    # and the outer list enumerates over images. Example of anns[0]:
    # [{'segmentation': [[192.81,
    #     247.09,
    #     ...
    #     219.03,
    #     249.06]],
    #   'area': 1035.749,
    #   'image_id': 1268,
    #   'bbox': [192.81, 224.8, 74.73, 33.43],
    #   'category_id': 16,
    #   'id': 42986},
    #  ...]
    anns = [lvis_api.img_ann_map[img_id] for img_id in img_ids]

    # Sanity check that each annotation has a unique id
    ann_ids = [ann["id"] for anns_per_image in anns for ann in anns_per_image]
    assert len(set(ann_ids)) == len(
        ann_ids
    ), "Annotation ids in '{}' are not unique".format(json_file)

    imgs_anns = list(zip(imgs, anns))

    logger.info(
        "Loaded {} images in the LVIS format from {}".format(len(imgs_anns), json_file)
    )

    if extra_annotation_keys:
        logger.info(
            "The following extra annotation keys will be loaded: {} ".format(
                extra_annotation_keys
            )
        )
    else:
        extra_annotation_keys = []

    def get_file_name(img_root, img_dict):
        # Determine the path including the split folder ("train2017", "val2017", "test2017") from
        # the coco_url field. Example:
        #   'coco_url': 'http://images.cocodataset.org/train2017/000000155379.jpg'
        split_folder, file_name = img_dict["coco_url"].split("/")[-2:]
        return os.path.join(img_root + split_folder, file_name)

    dataset_dicts = []

    for (img_dict, anno_dict_list) in imgs_anns:
        record = {}
        record["file_name"] = get_file_name(image_root, img_dict)
        record["height"] = img_dict["height"]
        record["width"] = img_dict["width"]
        record["not_exhaustive_category_ids"] = img_dict.get(
            "not_exhaustive_category_ids", []
        )
        record["neg_category_ids"] = img_dict.get("neg_category_ids", [])
        image_id = record["image_id"] = img_dict["id"]

        objs = []
        for anno in anno_dict_list:
            # Check that the image_id in this annotation is the same as
            # the image_id we're looking at.
            # This fails only when the data parsing logic or the annotation file is buggy.
            assert anno["image_id"] == image_id
            obj = {"bbox": anno["bbox"], "bbox_mode": BoxMode.XYWH_ABS}
            # LVIS data loader can be used to load COCO dataset categories. In this case `meta`
            # variable will have a field with COCO-specific category mapping.
            if dataset_name is not None and "thing_dataset_id_to_contiguous_id" in meta:
                obj["category_id"] = meta["thing_dataset_id_to_contiguous_id"][
                    anno["category_id"]
                ]
            else:
                obj["category_id"] = (
                    anno["category_id"] - 1
                )  # Convert 1-indexed to 0-indexed
            segm = anno["segmentation"]  # list[list[float]]
            # filter out invalid polygons (< 3 points)
            valid_segm = [
                poly for poly in segm if len(poly) % 2 == 0 and len(poly) >= 6
            ]
            assert len(segm) == len(
                valid_segm
            ), "Annotation contains an invalid polygon with < 3 points"
            assert len(segm) > 0
            obj["segmentation"] = segm
            for extra_ann_key in extra_annotation_keys:
                obj[extra_ann_key] = anno[extra_ann_key]
            objs.append(obj)
        record["annotations"] = objs
        dataset_dicts.append(record)

    return dataset_dicts


def get_lvis_instances_meta(dataset_name):
    """
    Load LVIS metadata.

    Args:
        dataset_name (str): LVIS dataset name without the split name (e.g., "lvis_v0.5").

    Returns:
        dict: LVIS metadata with keys: thing_classes
    """
    if "cocofied" in dataset_name:
        return _get_coco_instances_meta()
    if "v0.5" in dataset_name:
        return _get_lvis_instances_meta_v0_5()
    elif "v1" in dataset_name:
        return _get_lvis_instances_meta_v1()
    raise ValueError("No built-in metadata for dataset {}".format(dataset_name))


def _get_lvis_instances_meta_v0_5():
    assert len(LVIS_V0_5_CATEGORIES) == 1230
    cat_ids = [k["id"] for k in LVIS_V0_5_CATEGORIES]
    assert min(cat_ids) == 1 and max(cat_ids) == len(
        cat_ids
    ), "Category ids are not in [1, #categories], as expected"
    # Ensure that the category list is sorted by id
    lvis_categories = sorted(LVIS_V0_5_CATEGORIES, key=lambda x: x["id"])
    thing_classes = [k["synonyms"][0] for k in lvis_categories]
    meta = {"thing_classes": thing_classes}
    return meta


def _get_lvis_instances_meta_v1():
    assert len(LVIS_V1_CATEGORIES) == 1203
    cat_ids = [k["id"] for k in LVIS_V1_CATEGORIES]
    assert min(cat_ids) == 1 and max(cat_ids) == len(
        cat_ids
    ), "Category ids are not in [1, #categories], as expected"
    # Ensure that the category list is sorted by id
    lvis_categories = sorted(LVIS_V1_CATEGORIES, key=lambda x: x["id"])
    thing_classes = [k["synonyms"][0] for k in lvis_categories]
    meta = {
        "thing_classes": thing_classes,
        "class_image_count": LVIS_V1_CATEGORY_IMAGE_COUNT,
    }
    return meta


def main() -> None:
    global logger
    """
    Test the LVIS json dataset loader.

    Usage:
        python -m detectron2.data.datasets.lvis \
            path/to/json path/to/image_root dataset_name vis_limit
    """
    import sys

    import detectron2.data.datasets  # noqa  # add pre-defined metadata
    import numpy as np
    from detectron2.utils.logger import setup_logger
    from detectron2.utils.visualizer import Visualizer
    from PIL import Image

    logger = setup_logger(name=__name__)
    meta = MetadataCatalog.get(sys.argv[3])

    dicts = load_lvis_json(sys.argv[1], sys.argv[2], sys.argv[3])
    logger.info("Done loading {} samples.".format(len(dicts)))

    dirname = "lvis-data-vis"
    os.makedirs(dirname, exist_ok=True)
    for d in dicts[: int(sys.argv[4])]:
        img = np.array(Image.open(d["file_name"]))
        visualizer = Visualizer(img, metadata=meta)
        vis = visualizer.draw_dataset_dict(d)
        fpath = os.path.join(dirname, os.path.basename(d["file_name"]))
        vis.save(fpath)


if __name__ == "__main__":
    main()  # pragma: no cover