def __init__(self, root, annFile, transform=None, target_transform=None):
from pycocotools.coco import COCO
self.root = root
self.coco = COCO(annFile)
self.ids = list(self.coco.imgs.keys())
self.transform = transform
self.target_transform = target_transform
python类COCO的实例源码
def __init__(self, split, memoization=False):
assert not memoization
self.dataset = 'coco'
self.coco_ids_to_internal = {k: self.cats_to_ids[v] for k, v in coco_ids_to_cats.items()}
self.ids_to_coco_ids = dict(map(reversed, self.coco_ids_to_internal.items()))
self.split = split
assert self.split in ['train2014', 'val2014', 'test2014', 'test2015', 'minival2014', 'valminusminival2014', 'test-dev2015']
self.root = DATASETS_ROOT + 'coco/'
self.included_coco_ids = list(coco_ids.values())
if 'test' in self.split:
json = '%s/annotations/image_info_%s.json'
else:
json = '%s/annotations/instances_%s.json'
self.coco = COCO(json % (self.root, self.split))
self.filenames = self.coco.getImgIds()
self.num_classes = COCOLoader.num_classes
self.real_split = self.split
if self.real_split in ['minival2014', 'valminusminival2014']:
self.real_split = 'val2014'
self.coco = COCO('%s/annotations/instances_%s.json' % (self.root, self.real_split))
if 'test' in self.real_split:
self.real_split = 'test2015'
log.info("Created a COCO loader %s with %i images" % (split, len(self.coco.getImgIds())))
def get_loader(root, json, vocab, transform, batch_size, shuffle, num_workers):
"""Returns torch.utils.data.DataLoader for custom coco dataset."""
# COCO caption dataset
coco = CocoDataset(root=root,
json=json,
vocab=vocab,
transform=transform)
# Data loader for COCO dataset
# This will return (images, captions, lengths) for every iteration.
# images: tensor of shape (batch_size, 3, 224, 224).
# captions: tensor of shape (batch_size, padded_length).
# lengths: list indicating valid length for each caption. length is (batch_size).
data_loader = torch.utils.data.DataLoader(dataset=coco,
batch_size=batch_size,
shuffle=shuffle,
num_workers=num_workers,
collate_fn=collate_fn)
return data_loader
def __init__(self, annotations_path, class_names='all'):
self.coco = COCO(annotations_path)
self.class_names = class_names
if self.class_names == 'all':
class_data = self.coco.loadCats(self.coco.getCatIds())
self.class_names = [class_['name'] for class_ in class_data]
coco_ids = [class_['id'] for class_ in class_data]
one_hot_ids = list(range(1, len(coco_ids) + 1))
self.coco_id_to_class_arg = dict(zip(coco_ids, one_hot_ids))
self.class_names = ['background'] + self.class_names
self.num_classes = len(self.class_names)
else:
"""
https://github.com/cocodataset/cocoapi/blob/master/PythonAPI/pycocoDemo.ipynb
catIds = self.coco.getCatIds(catNms=self.class_names)
imgIds = self.coco.getImgIds(catIds=catIds)
imgIds = self.coco.getImgIds(imgIds=[324158])
"""
def get_loader_single(data_name, split, root, json, vocab, transform,
batch_size=100, shuffle=True,
num_workers=2, ids=None, collate_fn=collate_fn):
"""Returns torch.utils.data.DataLoader for custom coco dataset."""
if 'coco' in data_name:
# COCO custom dataset
dataset = CocoDataset(root=root,
json=json,
vocab=vocab,
transform=transform, ids=ids)
elif 'f8k' in data_name or 'f30k' in data_name:
dataset = FlickrDataset(root=root,
split=split,
json=json,
vocab=vocab,
transform=transform)
# Data loader
data_loader = torch.utils.data.DataLoader(dataset=dataset,
batch_size=batch_size,
shuffle=shuffle,
pin_memory=True,
num_workers=num_workers,
collate_fn=collate_fn)
return data_loader
def __init__(self,
which_set='train',
warn_grayscale=False,
*args,
**kwargs):
sys.path.append(os.path.join(os.path.dirname(
os.path.abspath(__file__)), 'coco', 'PythonAPI'))
self.which_set = 'val' if which_set == 'valid' else which_set
self.warn_grayscale = warn_grayscale
# constructing the ThreadedDataset
# it also creates/copies the dataset in self.path if not already there
super(MSCocoDataset, self).__init__(*args, **kwargs)
self.set_has_GT = self.which_set != 'test'
if self.seq_length != 1 or self.seq_per_subset != 0:
raise NotImplementedError('Images in COCO are not sequential. '
'It does not make sense to request a '
'sequence. seq_length {} '
'seq_per_subset {}'.format(
self.seq_length,
self.seq_per_subset))
def setUp(self):
self.annotations_file = "data/coco/annotations/instances_minival2014.json"
if getattr(self, 'coco', None) is None:
self.coco = COCO(self.annotations_file)
image_name = config.IMAGE_NAME_FORMAT % ('val2014', self.coco.getImgIds()[0])
image_path = config.IMAGE_PATH_FORMAT % ('val2014', image_name)
self.image = load_image(image_path)
def __init__(self, annotation_file, ign_null_img=False):
BaseDataset.__init__(self)
self.annotation_file = annotation_file
coco.COCO.__init__(self, annotation_file)
for i in self.getImgIds():
image_file_name = config.IMAGE_NAME_FORMAT % (config.IMAGE_SET, i)
image_file_path = config.IMAGE_PATH_FORMAT % (config.IMAGE_SET, image_file_name)
try:
if len(self.imgToAnns[i]) == 0:
raise KeyError
self.append(COCOItem(image_file_path, self.imgToAnns[i]))
except KeyError:
if ign_null_img is False:
self.append(COCOItem(image_file_path, []))
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',
}
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 _do_detection_eval(self, res_file, output_dir):
ann_type = 'bbox'
coco_dt = self._COCO.loadRes(res_file)
coco_eval = COCOeval(self._COCO, coco_dt)
coco_eval.params.useSegm = (ann_type == 'segm')
coco_eval.evaluate()
coco_eval.accumulate()
self._print_detection_eval_metrics(coco_eval)
eval_file = osp.join(output_dir, 'detection_results.pkl')
with open(eval_file, 'wb') as fid:
pickle.dump(coco_eval, fid, pickle.HIGHEST_PROTOCOL)
print('Wrote COCO eval results to: {}'.format(eval_file))
def __init__(self, image_set, year):
imdb.__init__(self, 'coco_' + year + '_' + image_set)
# COCO specific config options
self.config = {'top_k' : 2000,
'use_salt' : True,
'cleanup' : True,
'crowd_thresh' : 0.7,
'min_size' : 2}
# 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(zip(self.classes, xrange(self.num_classes)))
self._class_to_coco_cat_id = dict(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('selective_search')
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
}
coco_name = image_set + year # e.g., "val2014"
self._data_name = (self._view_map[coco_name]
if self._view_map.has_key(coco_name)
else coco_name)
# Dataset splits that have ground-truth annotations (test splits
# do not have gt annotations)
self._gt_splits = ('train', 'val', 'minival')
def _do_detection_eval(self, res_file, output_dir):
ann_type = 'bbox'
coco_dt = self._COCO.loadRes(res_file)
coco_eval = COCOeval(self._COCO, coco_dt)
coco_eval.params.useSegm = (ann_type == 'segm')
coco_eval.evaluate()
coco_eval.accumulate()
self._print_detection_eval_metrics(coco_eval)
eval_file = osp.join(output_dir, 'detection_results.pkl')
with open(eval_file, 'wb') as fid:
cPickle.dump(coco_eval, fid, cPickle.HIGHEST_PROTOCOL)
print 'Wrote COCO eval results to: {}'.format(eval_file)
def __init__(self, image_set, year):
imdb.__init__(self, 'coco_' + year + '_' + image_set)
# COCO specific config options
self.config = {'top_k' : 2000,
'use_salt' : True,
'cleanup' : True,
'crowd_thresh' : 0.7,
'min_size' : 2}
# 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(zip(self.classes, xrange(self.num_classes)))
self._class_to_coco_cat_id = dict(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('selective_search')
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
}
coco_name = image_set + year # e.g., "val2014"
self._data_name = (self._view_map[coco_name]
if self._view_map.has_key(coco_name)
else coco_name)
# Dataset splits that have ground-truth annotations (test splits
# do not have gt annotations)
self._gt_splits = ('train', 'val', 'minival')
def _do_detection_eval(self, res_file, output_dir):
ann_type = 'bbox'
coco_dt = self._COCO.loadRes(res_file)
coco_eval = COCOeval(self._COCO, coco_dt)
coco_eval.params.useSegm = (ann_type == 'segm')
coco_eval.evaluate()
coco_eval.accumulate()
self._print_detection_eval_metrics(coco_eval)
eval_file = osp.join(output_dir, 'detection_results.pkl')
with open(eval_file, 'wb') as fid:
cPickle.dump(coco_eval, fid, cPickle.HIGHEST_PROTOCOL)
print 'Wrote COCO eval results to: {}'.format(eval_file)
def __init__(self, root, json, vocab, transform=None):
"""Set the path for images, captions and vocabulary wrapper.
Args:
root: image directory.
json: coco annotation file path.
vocab: vocabulary wrapper.
transform: image transformer.
"""
self.root = root
self.coco = COCO(json)
self.ids = list(self.coco.anns.keys())
self.vocab = vocab
self.transform = transform
def build_vocab(json, threshold):
"""Build a simple vocabulary wrapper."""
coco = COCO(json)
counter = Counter()
ids = coco.anns.keys()
for i, id in enumerate(ids):
caption = str(coco.anns[id]['caption'])
tokens = nltk.tokenize.word_tokenize(caption.lower())
counter.update(tokens)
if i % 1000 == 0:
print("[%d/%d] Tokenized the captions." %(i, len(ids)))
# If the word frequency is less than 'threshold', then the word is discarded.
words = [word for word, cnt in counter.items() if cnt >= threshold]
# Creates a vocab wrapper and add some special tokens.
vocab = Vocabulary()
vocab.add_word('<pad>')
vocab.add_word('<start>')
vocab.add_word('<end>')
vocab.add_word('<unk>')
# Adds the words to the vocabulary.
for i, word in enumerate(words):
vocab.add_word(word)
return vocab
def __init__(self, image_set, year):
imdb.__init__(self, 'coco_' + year + '_' + image_set)
# COCO specific config options
self.config = {'top_k' : 2000,
'use_salt' : True,
'cleanup' : True,
'crowd_thresh' : 0.7,
'min_size' : 2}
# 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(zip(self.classes, xrange(self.num_classes)))
self._class_to_coco_cat_id = dict(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('selective_search')
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
}
coco_name = image_set + year # e.g., "val2014"
self._data_name = (self._view_map[coco_name]
if self._view_map.has_key(coco_name)
else coco_name)
# Dataset splits that have ground-truth annotations (test splits
# do not have gt annotations)
self._gt_splits = ('train', 'val', 'minival')
def _do_detection_eval(self, res_file, output_dir):
ann_type = 'bbox'
coco_dt = self._COCO.loadRes(res_file)
coco_eval = COCOeval(self._COCO, coco_dt)
coco_eval.params.useSegm = (ann_type == 'segm')
coco_eval.evaluate()
coco_eval.accumulate()
self._print_detection_eval_metrics(coco_eval)
eval_file = osp.join(output_dir, 'detection_results.pkl')
with open(eval_file, 'wb') as fid:
cPickle.dump(coco_eval, fid, cPickle.HIGHEST_PROTOCOL)
print 'Wrote COCO eval results to: {}'.format(eval_file)
def __init__(self, image_set, year, devkit_path=None):
datasets.imdb.__init__(self, 'coco_' + year + '_' + image_set)
# COCO specific config options
self.config = {'top_k' : 2000,
'use_salt' : True,
'cleanup' : True,
'crowd_thresh' : 0.7,
'min_size' : 2}
# name, paths
self._year = year
self._image_set = image_set
self._data_path = self._get_default_path() if devkit_path is None \
else devkit_path
# 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(zip(self.classes, xrange(self.num_classes)))
self._class_to_coco_cat_id = dict(zip([c['name'] for c in cats],
self._COCO.getCatIds()))
self._image_index = self._load_image_set_index()
# Default to roidb handler
self._roidb_handler = self.gt_roidb
self.competition_mode(False)
self._data_name = image_set + year # e.g., "val2014"
if self._data_name == 'test-dev2015':
self._data_name_path = 'test2015'
else:
self._data_name_path = self._data_name
def _do_detection_eval(self, res_file, output_dir):
ann_type = 'bbox'
coco_dt = self._COCO.loadRes(res_file)
coco_eval = COCOeval(self._COCO, coco_dt)
coco_eval.params.useSegm = (ann_type == 'segm')
coco_eval.evaluate()
coco_eval.accumulate()
self._print_detection_eval_metrics(coco_eval)
eval_file = osp.join(output_dir, 'detection_results.pkl')
with open(eval_file, 'wb') as fid:
cPickle.dump(coco_eval, fid, cPickle.HIGHEST_PROTOCOL)
print 'Wrote COCO eval results to: {}'.format(eval_file)
def __init__(self, data_dir, set_name, image_data_generator, *args, **kwargs):
self.data_dir = data_dir
self.set_name = set_name
self.coco = COCO(os.path.join(data_dir, 'annotations', 'instances_' + set_name + '.json'))
self.image_ids = self.coco.getImgIds()
self.load_classes()
super(CocoGenerator, self).__init__(image_data_generator, **kwargs)
def __init__(self, image_set, year):
imdb.__init__(self, 'coco_' + year + '_' + image_set)
# COCO specific config options
self.config = {'top_k' : 2000,
'use_salt' : True,
'cleanup' : True,
'crowd_thresh' : 0.7,
'min_size' : 2}
# 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(zip(self.classes, xrange(self.num_classes)))
self._class_to_coco_cat_id = dict(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('selective_search')
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
}
coco_name = image_set + year # e.g., "val2014"
self._data_name = (self._view_map[coco_name]
if self._view_map.has_key(coco_name)
else coco_name)
# Dataset splits that have ground-truth annotations (test splits
# do not have gt annotations)
self._gt_splits = ('train', 'val', 'minival')
def _do_detection_eval(self, res_file, output_dir):
ann_type = 'bbox'
coco_dt = self._COCO.loadRes(res_file)
coco_eval = COCOeval(self._COCO, coco_dt)
coco_eval.params.useSegm = (ann_type == 'segm')
coco_eval.evaluate()
coco_eval.accumulate()
self._print_detection_eval_metrics(coco_eval)
eval_file = osp.join(output_dir, 'detection_results.pkl')
with open(eval_file, 'wb') as fid:
cPickle.dump(coco_eval, fid, cPickle.HIGHEST_PROTOCOL)
print 'Wrote COCO eval results to: {}'.format(eval_file)
coco.py 文件源码
项目：Automatic_Group_Photography_Enhancement
作者: Yuliang-Zou
项目源码
文件源码
阅读 24
收藏 0
点赞 0
评论 0
def __init__(self, image_set, year):
imdb.__init__(self, 'coco_' + year + '_' + image_set)
# COCO specific config options
self.config = {'top_k' : 2000,
'use_salt' : True,
'cleanup' : True,
'crowd_thresh' : 0.7,
'min_size' : 2}
# 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(zip(self.classes, xrange(self.num_classes)))
self._class_to_coco_cat_id = dict(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('selective_search')
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
}
coco_name = image_set + year # e.g., "val2014"
self._data_name = (self._view_map[coco_name]
if self._view_map.has_key(coco_name)
else coco_name)
# Dataset splits that have ground-truth annotations (test splits
# do not have gt annotations)
self._gt_splits = ('train', 'val', 'minival')
coco.py 文件源码
项目：Automatic_Group_Photography_Enhancement
作者: Yuliang-Zou
项目源码
文件源码
阅读 32
收藏 0
点赞 0
评论 0
def _do_detection_eval(self, res_file, output_dir):
ann_type = 'bbox'
coco_dt = self._COCO.loadRes(res_file)
coco_eval = COCOeval(self._COCO, coco_dt)
coco_eval.params.useSegm = (ann_type == 'segm')
coco_eval.evaluate()
coco_eval.accumulate()
self._print_detection_eval_metrics(coco_eval)
eval_file = osp.join(output_dir, 'detection_results.pkl')
with open(eval_file, 'wb') as fid:
cPickle.dump(coco_eval, fid, cPickle.HIGHEST_PROTOCOL)
print 'Wrote COCO eval results to: {}'.format(eval_file)
def __init__(self, image_set, year):
imdb.__init__(self, 'coco_' + year + '_' + image_set)
# COCO specific config options
self.config = {'top_k' : 2000,
'use_salt' : True,
'cleanup' : True,
'crowd_thresh' : 0.7,
'min_size' : 2}
# 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(zip(self.classes, xrange(self.num_classes)))
self._class_to_coco_cat_id = dict(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('selective_search')
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
}
coco_name = image_set + year # e.g., "val2014"
self._data_name = (self._view_map[coco_name]
if self._view_map.has_key(coco_name)
else coco_name)
# Dataset splits that have ground-truth annotations (test splits
# do not have gt annotations)
self._gt_splits = ('train', 'val', 'minival')
def _do_detection_eval(self, res_file, output_dir):
ann_type = 'bbox'
coco_dt = self._COCO.loadRes(res_file)
coco_eval = COCOeval(self._COCO, coco_dt)
coco_eval.params.useSegm = (ann_type == 'segm')
coco_eval.evaluate()
coco_eval.accumulate()
self._print_detection_eval_metrics(coco_eval)
eval_file = osp.join(output_dir, 'detection_results.pkl')
with open(eval_file, 'wb') as fid:
cPickle.dump(coco_eval, fid, cPickle.HIGHEST_PROTOCOL)
print 'Wrote COCO eval results to: {}'.format(eval_file)
def __init__(self, image_set, year):
imdb.__init__(self, 'coco_' + year + '_' + image_set)
# COCO specific config options
self.config = {'top_k' : 2000,
'use_salt' : True,
'cleanup' : True,
'crowd_thresh' : 0.7,
'min_size' : 2}
# 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(zip(self.classes, xrange(self.num_classes)))
self._class_to_coco_cat_id = dict(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('selective_search')
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
}
coco_name = image_set + year # e.g., "val2014"
self._data_name = (self._view_map[coco_name]
if self._view_map.has_key(coco_name)
else coco_name)
# Dataset splits that have ground-truth annotations (test splits
# do not have gt annotations)
self._gt_splits = ('train', 'val', 'minival')
def _do_detection_eval(self, res_file, output_dir):
ann_type = 'bbox'
coco_dt = self._COCO.loadRes(res_file)
coco_eval = COCOeval(self._COCO, coco_dt)
coco_eval.params.useSegm = (ann_type == 'segm')
coco_eval.evaluate()
coco_eval.accumulate()
self._print_detection_eval_metrics(coco_eval)
eval_file = osp.join(output_dir, 'detection_results.pkl')
with open(eval_file, 'wb') as fid:
cPickle.dump(coco_eval, fid, cPickle.HIGHEST_PROTOCOL)
print 'Wrote COCO eval results to: {}'.format(eval_file)
def __init__(self, image_set, year):
imdb.__init__(self, 'coco_' + year + '_' + image_set)
# COCO specific config options
self.config = {'top_k' : 2000,
'use_salt' : True,
'cleanup' : True,
'crowd_thresh' : 0.7,
'min_size' : 2}
# 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(zip(self.classes, xrange(self.num_classes)))
self._class_to_coco_cat_id = dict(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('selective_search')
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
}
coco_name = image_set + year # e.g., "val2014"
self._data_name = (self._view_map[coco_name]
if self._view_map.has_key(coco_name)
else coco_name)
# Dataset splits that have ground-truth annotations (test splits
# do not have gt annotations)
self._gt_splits = ('train', 'val', 'minival')
