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')
python类DATA_DIR的实例源码
def cache_path(self):
cache_path = osp.abspath(osp.join(cfg.DATA_DIR, 'cache'))
if not os.path.exists(cache_path):
os.makedirs(cache_path)
return cache_path
def _get_default_path(self):
"""
Return the default path where PASCAL VOC is expected to be installed.
"""
return os.path.join(cfg.DATA_DIR, 'VOCdevkit' + self._year)
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 cache_path(self):
cache_path = osp.abspath(osp.join(cfg.DATA_DIR, 'cache'))
if not os.path.exists(cache_path):
os.makedirs(cache_path)
return cache_path
def _get_default_path(self):
"""
Return the default path where PASCAL VOC is expected to be installed.
"""
return os.path.join(cfg.DATA_DIR, 'VOCdevkit' + self._year)
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 _get_default_path(self):
"""
Return the default path where PASCAL VOC is expected to be installed.
"""
return os.path.join(cfg.DATA_DIR, 'ImageNet' + self._year)
def cache_path(self):
cache_path = osp.abspath(osp.join(cfg.DATA_DIR, 'cache'))
if not os.path.exists(cache_path):
os.makedirs(cache_path)
return cache_path
def demo(net, image_name):
"""Detect object classes in an image using pre-computed object proposals."""
# Load the demo image
im_file = os.path.join(cfg.DATA_DIR, 'demo', image_name)
im = cv2.imread(im_file)
# Detect all object classes and regress object bounds
timer = Timer()
timer.tic()
scores, boxes = im_detect(net, im)
timer.toc()
print ('Detection took {:.3f}s for '
'{:d} object proposals').format(timer.total_time, boxes.shape[0])
# Visualize detections for each class
CONF_THRESH = 0.8
NMS_THRESH = 0.3
for cls_ind, cls in enumerate(CLASSES[1:]):
cls_ind += 1 # because we skipped background
cls_boxes = boxes[:, 4*cls_ind:4*(cls_ind + 1)]
cls_scores = scores[:, cls_ind]
dets = np.hstack((cls_boxes,
cls_scores[:, np.newaxis])).astype(np.float32)
keep = nms(dets, NMS_THRESH)
dets = dets[keep, :]
vis_detections(im, cls, dets, thresh=CONF_THRESH)
def _get_default_path(self):
"""
Return the default path where PASCAL VOC is expected to be installed.
"""
return os.path.join(cfg.DATA_DIR, 'VOCdevkit' + self._year)
def cache_path(self):
cache_path = osp.abspath(osp.join(cfg.DATA_DIR, 'cache'))
if not os.path.exists(cache_path):
os.makedirs(cache_path)
return cache_path
def _get_default_path(self):
"""
Return the default path where PASCAL VOC is expected to be installed.
"""
return os.path.join(cfg.DATA_DIR, 'VOCdevkit' + self._year)
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 cache_path(self):
cache_path = osp.abspath(osp.join(cfg.DATA_DIR, 'cache'))
if not os.path.exists(cache_path):
os.makedirs(cache_path)
return cache_path
pascal_voc.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 21
收藏 0
点赞 0
评论 0
def _get_default_path(self):
"""
Return the default path where PASCAL VOC is expected to be installed.
"""
return os.path.join(cfg.DATA_DIR, 'VOCdevkit' + self._year)
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 29
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')
imdb.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 cache_path(self):
cache_path = osp.abspath(osp.join(cfg.DATA_DIR, 'cache'))
if not os.path.exists(cache_path):
os.makedirs(cache_path)
return cache_path
test_yl.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 21
收藏 0
点赞 0
评论 0
def demo(sess, net, image_name):
"""Detect object classes in an image using pre-computed object proposals."""
# Load the demo image
im_file = os.path.join(cfg.DATA_DIR, 'demo', image_name)
#im_file = os.path.join('/home/corgi/Lab/label/pos_frame/ACCV/training/000001/',image_name)
im = cv2.imread(im_file)
# Detect all object classes and regress object bounds
timer = Timer()
timer.tic()
scores, boxes = im_detect(sess, net, im)
timer.toc()
print ('Detection took {:.3f}s for '
'{:d} object proposals').format(timer.total_time, boxes.shape[0])
# Visualize detections for each class
im = im[:, :, (2, 1, 0)]
fig, ax = plt.subplots(figsize=(12, 12))
ax.imshow(im, aspect='equal')
CONF_THRESH = 0.9
NMS_THRESH = 0.3
for cls_ind, cls in enumerate(CLASSES[1:]):
cls_ind += 1 # because we skipped background
cls_boxes = boxes[:, 4*cls_ind:4*(cls_ind + 1)]
cls_scores = scores[:, cls_ind]
dets = np.hstack((cls_boxes,
cls_scores[:, np.newaxis])).astype(np.float32)
keep = nms(dets, NMS_THRESH)
dets = dets[keep, :]
vis_detections(im, cls, dets, ax, thresh=CONF_THRESH)
demo.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 27
收藏 0
点赞 0
评论 0
def demo(sess, net, image_name):
"""Detect object classes in an image using pre-computed object proposals."""
# Load the demo image
im_file = os.path.join(cfg.DATA_DIR, 'demo', image_name)
#im_file = os.path.join('/home/corgi/Lab/label/pos_frame/ACCV/training/000001/',image_name)
im = cv2.imread(im_file)
# Detect all object classes and regress object bounds
timer = Timer()
timer.tic()
# scores, boxes = im_detect(sess, net, im)
scores, boxes, eyes, smiles = im_detect_ori(sess, net, im)
timer.toc()
print ('Detection took {:.3f}s for '
'{:d} object proposals').format(timer.total_time, boxes.shape[0])
# Visualize detections for each class
im = im[:, :, (2, 1, 0)]
fig, ax = plt.subplots(figsize=(8, 8))
ax.imshow(im, aspect='equal')
CONF_THRESH = 0.9
NMS_THRESH = 0.3
for cls_ind, cls in enumerate(CLASSES[20:]):
cls_ind += 20 # because we skipped everything except face
cls_boxes = boxes[:, 4*cls_ind:4*(cls_ind + 1)]
cls_scores = scores[:, cls_ind]
dets = np.hstack((cls_boxes,
cls_scores[:, np.newaxis])).astype(np.float32)
keep = nms(dets, NMS_THRESH)
dets = dets[keep, :]
eye = eyes[keep, :]
smile= smiles[keep, :]
vis_detections(im, cls, dets, eye, smile, ax, thresh=CONF_THRESH)
