def convert_to_coco_json(dataset_name, output_folder="", allow_cached=True):
"""
Converts dataset into COCO format and saves it to a json file.
dataset_name must be registered in DatastCatalog and in detectron2's standard format.
Args:
dataset_name:
reference from the config file to the catalogs
must be registered in DatastCatalog and in detectron2's standard format
output_folder: where json file will be saved and loaded from
allow_cached: if json file is already present then skip conversion
Returns:
cache_path: path to the COCO-format json file
"""
# TODO: The dataset or the conversion script *may* change,
# a checksum would be useful for validating the cached data
cache_path = os.path.join(output_folder, f"{dataset_name}_coco_format.json")
PathManager.mkdirs(output_folder)
if os.path.exists(cache_path) and allow_cached:
logger.info(f"Reading cached annotations in COCO format from:{cache_path} ...")
else:
logger.info(f"Converting dataset annotations in '{dataset_name}' to COCO format ...)")
coco_dict = convert_to_coco_dict(dataset_name)
with PathManager.open(cache_path, "w") as json_file:
logger.info(f"Caching annotations in COCO format: {cache_path}")
json.dump(coco_dict, json_file)
return cache_path
def _load_file(self, filename):
if filename.endswith(".pkl"):
with PathManager.open(filename, "rb") as f:
data = pickle.load(f, encoding="latin1")
if "model" in data and "__author__" in data:
# file is in dl_lib model zoo format
self.logger.info("Reading a file from '{}'".format(
data["__author__"]))
return data
else:
# assume file is from Caffe2 / Detectron1 model zoo
if "blobs" in data:
# Detection models have "blobs", but ImageNet models don't
data = data["blobs"]
data = {
k: v
for k, v in data.items() if not k.endswith("_momentum")
}
return {
"model": data,
"__author__": "Caffe2",
"matching_heuristics": True
}
loaded = super()._load_file(filename) # load native pth checkpoint
if "model" not in loaded:
loaded = {"model": loaded}
return loaded
def __init__(self, json_file, window_size=20):
"""
Args:
json_file (str): path to the json file. New data will be appended if the file exists.
window_size (int): the window size of median smoothing for the scalars whose
`smoothing_hint` are True.
"""
self._file_handle = PathManager.open(json_file, "a")
self._window_size = window_size
def load_voc_instances(dirname: str, split: str):
"""
Load Pascal VOC detection annotations to dl_lib format.
Args:
dirname: Contain "Annotations", "ImageSets", "JPEGImages"
split (str): one of "train", "test", "val", "trainval"
"""
with PathManager.open(
os.path.join(dirname, "ImageSets", "Main", split + ".txt")) as f:
fileids = np.loadtxt(f, dtype=np.str)
dicts = []
for fileid in fileids:
anno_file = os.path.join(dirname, "Annotations", fileid + ".xml")
jpeg_file = os.path.join(dirname, "JPEGImages", fileid + ".jpg")
tree = ET.parse(anno_file)
r = {
"file_name": jpeg_file,
"image_id": fileid,
"height": int(tree.findall("./size/height")[0].text),
"width": int(tree.findall("./size/width")[0].text),
}
instances = []
for obj in tree.findall("object"):
cls = obj.find("name").text
# We include "difficult" samples in training.
# Based on limited experiments, they don't hurt accuracy.
# difficult = int(obj.find("difficult").text)
# if difficult == 1:
# continue
bbox = obj.find("bndbox")
bbox = [
float(bbox.find(x).text)
for x in ["xmin", "ymin", "xmax", "ymax"]
]
# Original annotations are integers in the range [1, W or H]
# Assuming they mean 1-based pixel indices (inclusive),
# a box with annotation (xmin=1, xmax=W) covers the whole image.
# In coordinate space this is represented by (xmin=0, xmax=W)
bbox[0] -= 1.0
bbox[1] -= 1.0
instances.append({
"category_id": CLASS_NAMES.index(cls),
"bbox": bbox,
"bbox_mode": BoxMode.XYXY_ABS
})
r["annotations"] = instances
dicts.append(r)
return dicts
def after_step(self):
if self._profiler is None:
return
self._profiler.__exit__(None, None, None)
out_file = os.path.join(
self._output_dir,
"profiler-trace-iter{}.json".format(self.trainer.iter))
if "://" not in out_file:
self._profiler.export_chrome_trace(out_file)
else:
# Support non-posix filesystems
with tempfile.TemporaryDirectory(prefix="dl_lib_profiler") as d:
tmp_file = os.path.join(d, "tmp.json")
self._profiler.export_chrome_trace(tmp_file)
with open(tmp_file) as f:
content = f.read()
with PathManager.open(out_file, "w") as f:
f.write(content)
def load_coco_json(json_file, image_root, dataset_name=None, extra_annotation_keys=None):
"""
Load a json file with COCO's instances annotation format.
Currently supports instance detection, instance segmentation,
and person keypoints annotations.
Args:
json_file (str): full path to the json file in COCO instances annotation format.
image_root (str): the directory where the images in this json file exists.
dataset_name (str): the name of the dataset (e.g., coco_2017_train).
If provided, this function will also 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 "iscrowd", "bbox", "keypoints",
"category_id", "segmentation"). The values for these keys will be returned as-is.
For example, the densepose annotations are loaded in this way.
Returns:
list[dict]: a list of dicts in dl_lib 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 pycocotools.coco import COCO
timer = Timer()
json_file = PathManager.get_local_path(json_file)
with contextlib.redirect_stdout(io.StringIO()):
coco_api = COCO(json_file)
if timer.seconds() > 1:
logger.info("Loading {} takes {:.2f} seconds.".format(json_file, timer.seconds()))
id_map = None
if dataset_name is not None:
meta = MetadataCatalog.get(dataset_name)
cat_ids = sorted(coco_api.getCatIds())
cats = coco_api.loadCats(cat_ids)
# The categories in a custom json file may not be sorted.
thing_classes = [c["name"] for c in sorted(cats, key=lambda x: x["id"])]
meta.thing_classes = thing_classes
# In COCO, certain category ids are artificially removed,
# and by convention they are always ignored.
# We deal with COCO's id issue and translate
# the category ids to contiguous ids in [0, 80).
# It works by looking at the "categories" field in the json, therefore
# if users' own json also have incontiguous ids, we'll
# apply this mapping as well but print a warning.
if not (min(cat_ids) == 1 and max(cat_ids) == len(cat_ids)):
if "coco" not in dataset_name:
logger.warning(
"""
Category ids in annotations are not in [1, #categories]! We'll apply a mapping for you.
"""
)
id_map = {v: i for i, v in enumerate(cat_ids)}
meta.thing_dataset_id_to_contiguous_id = id_map
# sort indices for reproducible results
img_ids = sorted(list(coco_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 = coco_api.loadImgs(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,
# 'iscrowd': 0,
# 'image_id': 1268,
# 'bbox': [192.81, 224.8, 74.73, 33.43],
# 'category_id': 16,
# 'id': 42986},
# ...]
anns = [coco_api.imgToAnns[img_id] for img_id in img_ids]
if "minival" not in json_file:
# The popular valminusminival & minival annotations for COCO2014 contain this bug.
# However the ratio of buggy annotations there is tiny and does not affect accuracy.
# Therefore we explicitly white-list them.
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 COCO format from {}".format(len(imgs_anns), json_file))
dataset_dicts = []
ann_keys = ["iscrowd", "bbox", "keypoints", "category_id"] + (extra_annotation_keys or [])
num_instances_without_valid_segmentation = 0
for (img_dict, anno_dict_list) in imgs_anns:
record = {}
record["file_name"] = os.path.join(image_root, img_dict["file_name"])
record["height"] = img_dict["height"]
record["width"] = img_dict["width"]
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.
# The original COCO valminusminival2014 & minival2014 annotation files
# actually contains bugs that, together with certain ways of using COCO API,
# can trigger this assertion.
assert anno["image_id"] == image_id
assert anno.get("ignore", 0) == 0
obj = {key: anno[key] for key in ann_keys if key in anno}
segm = anno.get("segmentation", None)
if segm: # either list[list[float]] or dict(RLE)
if not isinstance(segm, dict):
# filter out invalid polygons (< 3 points)
segm = [poly for poly in segm if len(poly) % 2 == 0 and len(poly) >= 6]
if len(segm) == 0:
num_instances_without_valid_segmentation += 1
continue # ignore this instance
obj["segmentation"] = segm
keypts = anno.get("keypoints", None)
if keypts: # list[int]
for idx, v in enumerate(keypts):
if idx % 3 != 2:
# COCO's segmentation coordinates are floating points in [0, H or W],
# but keypoint coordinates are integers in [0, H-1 or W-1]
# Therefore we assume the coordinates are "pixel indices" and
# add 0.5 to convert to floating point coordinates.
keypts[idx] = v + 0.5
obj["keypoints"] = keypts
obj["bbox_mode"] = BoxMode.XYWH_ABS
if id_map:
obj["category_id"] = id_map[obj["category_id"]]
objs.append(obj)
record["annotations"] = objs
dataset_dicts.append(record)
if num_instances_without_valid_segmentation > 0:
logger.warn(
"Filtered out {} instances without valid segmentation. "
"There might be issues in your dataset generation process.".format(
num_instances_without_valid_segmentation
)
)
return dataset_dicts
def load_sem_seg(gt_root, image_root, gt_ext="png", image_ext="jpg"):
"""
Load semantic segmentation datasets. All files under "gt_root" with "gt_ext" extension are
treated as ground truth annotations and all files under "image_root" with "image_ext" extension
as input images. Ground truth and input images are matched using file paths relative to
"gt_root" and "image_root" respectively without taking into account file extensions.
This works for COCO as well as some other datasets.
Args:
gt_root (str): full path to ground truth semantic segmentation files. Semantic segmentation
annotations are stored as images with integer values in pixels that represent
corresponding semantic labels.
image_root (str): the directory where the input images are.
gt_ext (str): file extension for ground truth annotations.
image_ext (str): file extension for input images.
Returns:
list[dict]:
a list of dicts in dl_lib standard format without instance-level
annotation.
Notes:
1. This function does not read the image and ground truth files.
The results do not have the "image" and "sem_seg" fields.
"""
# We match input images with ground truth based on their relative filepaths (without file
# extensions) starting from 'image_root' and 'gt_root' respectively.
def file2id(folder_path, file_path):
# extract relative path starting from `folder_path`
image_id = os.path.normpath(os.path.relpath(file_path, start=folder_path))
# remove file extension
image_id = os.path.splitext(image_id)[0]
return image_id
input_files = sorted(
(os.path.join(image_root, f) for f in PathManager.ls(image_root) if f.endswith(image_ext)),
key=lambda file_path: file2id(image_root, file_path),
)
gt_files = sorted(
(os.path.join(gt_root, f) for f in PathManager.ls(gt_root) if f.endswith(gt_ext)),
key=lambda file_path: file2id(gt_root, file_path),
)
assert len(gt_files) > 0, "No annotations found in {}.".format(gt_root)
# Use the intersection, so that val2017_100 annotations can run smoothly with val2017 images
if len(input_files) != len(gt_files):
logger.warn(
"Directory {} and {} has {} and {} files, respectively.".format(
image_root, gt_root, len(input_files), len(gt_files)
)
)
input_basenames = [os.path.basename(f)[: -len(image_ext)] for f in input_files]
gt_basenames = [os.path.basename(f)[: -len(gt_ext)] for f in gt_files]
intersect = list(set(input_basenames) & set(gt_basenames))
# sort, otherwise each worker may obtain a list[dict] in different order
intersect = sorted(intersect)
logger.warn("Will use their intersection of {} files.".format(len(intersect)))
input_files = [os.path.join(image_root, f + image_ext) for f in intersect]
gt_files = [os.path.join(gt_root, f + gt_ext) for f in intersect]
logger.info(
"Loaded {} images with semantic segmentation from {}".format(len(input_files), image_root)
)
dataset_dicts = []
for (img_path, gt_path) in zip(input_files, gt_files):
local_path = PathManager.get_local_path(gt_path)
w, h = imagesize.get(local_path)
record = {}
record["file_name"] = img_path
record["sem_seg_file_name"] = gt_path
record["height"] = h
record["width"] = w
dataset_dicts.append(record)
return dataset_dicts