def __init__(self, mode):
"""
:param mode: train2014 or val2014
"""
self.mode = mode
self.root = os.path.join(COCO_PATH, mode)
self.ann_file = os.path.join(COCO_PATH, 'annotations',
'instances_{}.json'.format(mode))
self.coco = COCO(self.ann_file)
self.ids = [
k for k in self.coco.imgs.keys() if len(self.coco.imgToAnns[k]) > 0
]
tform = []
if self.is_train:
tform.append(
RandomOrder([
Grayscale(),
Brightness(),
Contrast(),
Sharpness(),
Hue(),
]))
tform += [
SquarePad(),
Resize(IM_SCALE),
ToTensor(),
Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),
]
self.transform_pipeline = Compose(tform)
self.ind_to_classes = ['__background__'] + [
v['name'] for k, v in self.coco.cats.items()
]
# COCO inds are weird (84 inds in total but a bunch of numbers are skipped)
self.id_to_ind = {
coco_id: (ind + 1)
for ind, coco_id in enumerate(self.coco.cats.keys())
}
self.id_to_ind[0] = 0
self.ind_to_id = {x: y for y, x in self.id_to_ind.items()}
def coco(self):
"""
:return: a Coco-like object that we can use to evaluate detection!
"""
anns = []
for i, (cls_array,
box_array) in enumerate(zip(self.gt_classes, self.gt_boxes)):
for cls, box in zip(cls_array.tolist(), box_array.tolist()):
anns.append({
'area': (box[3] - box[1] + 1) * (box[2] - box[0] + 1),
'bbox':
[box[0], box[1], box[2] - box[0] + 1, box[3] - box[1] + 1],
'category_id':
cls,
'id':
len(anns),
'image_id':
i,
'iscrowd':
0,
})
fauxcoco = COCO()
fauxcoco.dataset = {
'info': {
'description': 'ayy lmao'
},
'images': [{
'id': i
} for i in range(self.__len__())],
'categories': [{
'supercategory': 'person',
'id': i,
'name': name
} for i, name in enumerate(self.ind_to_classes)
if name != '__background__'],
'annotations':
anns,
}
fauxcoco.createIndex()
return fauxcoco
def __init__(self, image_set, year):
imdb.__init__(self, 'coco_' + year + '_' + image_set)
# COCO specific config options
self.config = {'use_salt': True,
'cleanup': True}
# name, paths
self._year = year
self._image_set = image_set
self._data_path = osp.join(cfg.DATA_DIR, 'coco')
# load COCO API, classes, class <-> id mappings
self._COCO = COCO(self._get_ann_file())
cats = self._COCO.loadCats(self._COCO.getCatIds())
self._classes = tuple(['__background__'] + [c['name'] for c in cats])
self._class_to_ind = dict(list(zip(self.classes, list(range(self.num_classes)))))
self._class_to_coco_cat_id = dict(list(zip([c['name'] for c in cats],
self._COCO.getCatIds())))
self._image_index = self._load_image_set_index()
# Default to roidb handler
self.set_proposal_method('gt')
self.competition_mode(False)
# Some image sets are "views" (i.e. subsets) into others.
# For example, minival2014 is a random 5000 image subset of val2014.
# This mapping tells us where the view's images and proposals come from.
self._view_map = {
'minival2014': 'val2014', # 5k val2014 subset
'valminusminival2014': 'val2014', # val2014 \setminus minival2014
'test-dev2015': 'test2015',
'valminuscapval2014': 'val2014',
'capval2014': 'val2014',
'captest2014': 'val2014'
}
coco_name = image_set + year # e.g., "val2014"
self._data_name = (self._view_map[coco_name]
if coco_name in self._view_map
else coco_name)
# Dataset splits that have ground-truth annotations (test splits
# do not have gt annotations)
self._gt_splits = ('train', 'val', 'minival')
def load_coco(self,
dataset_dir,
subsets,
class_ids=None,
class_map=None,
return_coco=False):
"""Load a subset of the COCO dataset.
dataset_dir: The root directory of the COCO dataset.
subset: What to load (train, val, minival, val35k)
class_ids: If provided, only loads images that have the given classes.
class_map: TODO: Not implemented yet. Supports maping classes from
different datasets to the same class ID.
return_coco: If True, returns the COCO object.
"""
# Path
self._view_map = {
'minival2014': 'val2014', # 5k val2014 subset
'valminusminival2014': 'val2014', # val2014 \setminus minival2014
'test-dev2015': 'test2015',
}
self.image_ids = []
for subset in subsets:
image_dir = os.path.join(
dataset_dir, 'images',
"train2014" if subset == "train" else "val2014")
# Create COCO object
json_path_dict = {
"train": "annotations/instances_train2014.json",
"val": "annotations/instances_val2014.json",
"minival": "annotations/instances_minival2014.json",
"val35k": "annotations/instances_valminusminival2014.json",
}
coco = COCO(os.path.join(dataset_dir, json_path_dict[subset]))
image_ids = []
# Load all classes or a subset?
if not class_ids:
# All classes
class_ids = sorted(coco.getCatIds())
# All images or a subset?
if class_ids:
for id in class_ids:
image_ids.extend(list(coco.getImgIds(catIds=[id])))
# Remove duplicates
image_ids = list(set(image_ids))
else:
# All images
image_ids = list(coco.imgs.keys())
# Add classes
for i in class_ids:
self.add_class("coco", i, coco.loadCats(i)[0]["name"])
# Add images
self.image_ids += image_ids
for i in image_ids:
self.add_image("coco",
image_id=i,
path=os.path.join(image_dir,
coco.imgs[i]['file_name']),
width=coco.imgs[i]["width"],
height=coco.imgs[i]["height"],
annotations=coco.loadAnns(
coco.getAnnIds(imgIds=[i],
catIds=class_ids,
iscrowd=None)))
print(subset)
print(len(self.image_info))
if return_coco:
return coco
def load_coco(self,
dataset_dir,
subset,
year=DEFAULT_DATASET_YEAR,
class_ids=None,
class_map=None,
return_coco=False,
auto_download=False):
"""Load a subset of the COCO dataset.
dataset_dir: The root directory of the COCO dataset.
subset: What to load (train, val, minival, valminusminival)
year: What dataset year to load (2014, 2017) as a string, not an integer
class_ids: If provided, only loads images that have the given classes.
class_map: TODO: Not implemented yet. Supports maping classes from
different datasets to the same class ID.
return_coco: If True, returns the COCO object.
auto_download: Automatically download and unzip MS-COCO images and annotations
"""
if auto_download is True:
self.auto_download(dataset_dir, subset, year)
coco = COCO("{}/annotations/instances_{}{}.json".format(
dataset_dir, subset, year))
if subset == "minival" or subset == "valminusminival":
subset = "val"
image_dir = "{}/{}{}".format(dataset_dir, subset, year)
# Load all classes or a subset?
if not class_ids:
# All classes
class_ids = sorted(coco.getCatIds())
# All images or a subset?
if class_ids:
image_ids = []
for id in class_ids:
image_ids.extend(list(coco.getImgIds(catIds=[id])))
# Remove duplicates
image_ids = list(set(image_ids))
else:
# All images
image_ids = list(coco.imgs.keys())
# Add classes
for i in class_ids:
self.add_class("coco", i, coco.loadCats(i)[0]["name"])
# Add images
for i in image_ids:
self.add_image("coco",
image_id=i,
path=os.path.join(image_dir,
coco.imgs[i]['file_name']),
width=coco.imgs[i]["width"],
height=coco.imgs[i]["height"],
annotations=coco.loadAnns(
coco.getAnnIds(imgIds=[i],
catIds=class_ids,
iscrowd=None)))
if return_coco:
return coco