def save_im_name_mapping(raw_dir, ori_to_new_im_name_file):
im_names = []
for dir_name in ['bounding_box_train', 'bounding_box_test', 'query']:
im_names_ = get_im_names(osp.join(raw_dir, dir_name), return_path=False, return_np=False)
im_names_.sort()
# Images in different original directories may have same names,
# so here we use relative paths as original image names.
im_names_ = [osp.join(dir_name, n) for n in im_names_]
im_names += im_names_
new_im_names = map_im_names(im_names, parse_original_im_name, new_im_name_tmpl)
ori_to_new_im_name = dict(zip(im_names, new_im_names))
save_pickle(ori_to_new_im_name, ori_to_new_im_name_file)
print('File saved to {}'.format(ori_to_new_im_name_file))
##################
# Just Some Info #
##################
print('len(im_names)', len(im_names))
print('len(set(im_names))', len(set(im_names)))
print('len(set(new_im_names))', len(set(new_im_names)))
print('len(ori_to_new_im_name)', len(ori_to_new_im_name))
bounding_box_train_im_names = get_im_names(osp.join(raw_dir, 'bounding_box_train'), return_path=False, return_np=False)
bounding_box_test_im_names = get_im_names(osp.join(raw_dir, 'bounding_box_test'), return_path=False, return_np=False)
query_im_names = get_im_names(osp.join(raw_dir, 'query'), return_path=False, return_np=False)
print('set(bounding_box_train_im_names).isdisjoint(set(bounding_box_test_im_names))',
set(bounding_box_train_im_names).isdisjoint(set(bounding_box_test_im_names)))
print('set(bounding_box_train_im_names).isdisjoint(set(query_im_names))',
set(bounding_box_train_im_names).isdisjoint(set(query_im_names)))
print('set(bounding_box_test_im_names).isdisjoint(set(query_im_names))',
set(bounding_box_test_im_names).isdisjoint(set(query_im_names)))
def save_im_name_mapping(raw_dir, ori_to_new_im_name_file):
im_names = []
for dir_name in ['bounding_box_train', 'bounding_box_test', 'query', 'gt_bbox']:
im_names_ = get_im_names(osp.join(raw_dir, dir_name), return_path=False, return_np=False)
im_names_.sort()
# Filter out id -1
if dir_name == 'bounding_box_test':
im_names_ = [n for n in im_names_ if not n.startswith('-1')]
# Get (id, cam) in query set
if dir_name == 'query':
q_ids_cams = set([(parse_original_im_name(n, 'id'), parse_original_im_name(n, 'cam')) for n in im_names_])
# Filter out images that are not corresponding to query (id, cam)
if dir_name == 'gt_bbox':
im_names_ = [n for n in im_names_ if (parse_original_im_name(n, 'id'), parse_original_im_name(n, 'cam')) in q_ids_cams]
# Images in different original directories may have same names,
# so here we use relative paths as original image names.
im_names_ = [osp.join(dir_name, n) for n in im_names_]
im_names += im_names_
new_im_names = map_im_names(im_names, parse_original_im_name, new_im_name_tmpl)
ori_to_new_im_name = dict(zip(im_names, new_im_names))
save_pickle(ori_to_new_im_name, ori_to_new_im_name_file)
print('File saved to {}'.format(ori_to_new_im_name_file))
##################
# Just Some Info #
##################
print('len(im_names)', len(im_names))
print('len(set(im_names))', len(set(im_names)))
print('len(set(new_im_names))', len(set(new_im_names)))
print('len(ori_to_new_im_name)', len(ori_to_new_im_name))
bounding_box_train_im_names = get_im_names(osp.join(raw_dir, 'bounding_box_train'), return_path=False, return_np=False)
bounding_box_test_im_names = get_im_names(osp.join(raw_dir, 'bounding_box_test'), return_path=False, return_np=False)
query_im_names = get_im_names(osp.join(raw_dir, 'query'), return_path=False, return_np=False)
gt_bbox_im_names = get_im_names(osp.join(raw_dir, 'gt_bbox'), return_path=False, return_np=False)
print('set(bounding_box_train_im_names).isdisjoint(set(bounding_box_test_im_names))',
set(bounding_box_train_im_names).isdisjoint(set(bounding_box_test_im_names)))
print('set(bounding_box_train_im_names).isdisjoint(set(query_im_names))',
set(bounding_box_train_im_names).isdisjoint(set(query_im_names)))
print('set(bounding_box_train_im_names).isdisjoint(set(gt_bbox_im_names))',
set(bounding_box_train_im_names).isdisjoint(set(gt_bbox_im_names)))
print('set(bounding_box_test_im_names).isdisjoint(set(query_im_names))',
set(bounding_box_test_im_names).isdisjoint(set(query_im_names)))
print('set(bounding_box_test_im_names).isdisjoint(set(gt_bbox_im_names))',
set(bounding_box_test_im_names).isdisjoint(set(gt_bbox_im_names)))
print('set(query_im_names).isdisjoint(set(gt_bbox_im_names))',
set(query_im_names).isdisjoint(set(gt_bbox_im_names)))
print('len(query_im_names)', len(query_im_names))
print('len(gt_bbox_im_names)', len(gt_bbox_im_names))
print('len(set(query_im_names) & set(gt_bbox_im_names))', len(set(query_im_names) & set(gt_bbox_im_names)))
print('len(set(query_im_names) | set(gt_bbox_im_names))', len(set(query_im_names) | set(gt_bbox_im_names)))
def save_im_name_mapping(raw_dir, ori_to_new_im_name_file):
im_names = []
for dir_name in ['bounding_box_train', 'bounding_box_test', 'query']:
im_names_ = get_im_names(osp.join(raw_dir, dir_name),
return_path=False,
return_np=False)
im_names_.sort()
# Images in different original directories may have same names,
# so here we use relative paths as original image names.
im_names_ = [osp.join(dir_name, n) for n in im_names_]
im_names += im_names_
new_im_names = map_im_names(im_names, parse_original_im_name,
new_im_name_tmpl)
ori_to_new_im_name = dict(zip(im_names, new_im_names))
save_pickle(ori_to_new_im_name, ori_to_new_im_name_file)
print('File saved to {}'.format(ori_to_new_im_name_file))
##################
# Just Some Info #
##################
print('len(im_names)', len(im_names))
print('len(set(im_names))', len(set(im_names)))
print('len(set(new_im_names))', len(set(new_im_names)))
print('len(ori_to_new_im_name)', len(ori_to_new_im_name))
bounding_box_train_im_names = get_im_names(osp.join(
raw_dir, 'bounding_box_train'),
return_path=False,
return_np=False)
bounding_box_test_im_names = get_im_names(osp.join(raw_dir,
'bounding_box_test'),
return_path=False,
return_np=False)
query_im_names = get_im_names(osp.join(raw_dir, 'query'),
return_path=False,
return_np=False)
print(
'set(bounding_box_train_im_names).isdisjoint(set(bounding_box_test_im_names))',
set(bounding_box_train_im_names).isdisjoint(
set(bounding_box_test_im_names)))
print('set(bounding_box_train_im_names).isdisjoint(set(query_im_names))',
set(bounding_box_train_im_names).isdisjoint(set(query_im_names)))
print('set(bounding_box_test_im_names).isdisjoint(set(query_im_names))',
set(bounding_box_test_im_names).isdisjoint(set(query_im_names)))
def save_images(zip_file, save_dir=None, train_test_split_file=None):
"""Rename and move all used images to a directory."""
print("Extracting zip file")
root = osp.dirname(osp.abspath(zip_file))
if save_dir is None:
save_dir = root
may_make_dir(save_dir)
with ZipFile(zip_file) as z:
z.extractall(path=save_dir)
print("Extracting zip file done")
new_im_dir = osp.join(save_dir, 'images')
may_make_dir(new_im_dir)
raw_dir = osp.join(save_dir, osp.basename(zip_file)[:-4])
im_paths = []
nums = []
for dir_name in ['bounding_box_train', 'bounding_box_test', 'query']:
im_paths_ = get_im_names(osp.join(raw_dir, dir_name),
return_path=True,
return_np=False)
im_paths_.sort()
im_paths += list(im_paths_)
nums.append(len(im_paths_))
im_names = move_ims(im_paths, new_im_dir, parse_original_im_name,
new_im_name_tmpl)
split = dict()
keys = ['trainval_im_names', 'gallery_im_names', 'q_im_names']
inds = [0] + nums
inds = np.cumsum(inds)
for i, k in enumerate(keys):
split[k] = im_names[inds[i]:inds[i + 1]]
save_pickle(split, train_test_split_file)
print('Saving images done.')
return split
def save_images(zip_file, save_dir=None, train_test_split_file=None):
"""Rename and move all used images to a directory."""
print("Extracting zip file")
root = osp.dirname(osp.abspath(zip_file))
if save_dir is None:
save_dir = root
may_make_dir(save_dir)
with ZipFile(zip_file) as z:
z.extractall(path=save_dir)
print("Extracting zip file done")
new_im_dir = osp.join(save_dir, 'images')
may_make_dir(new_im_dir)
raw_dir = osp.join(save_dir, osp.basename(zip_file)[:-4])
im_paths = []
nums = []
for dir_name in ['bounding_box_train', 'bounding_box_test', 'query']:
im_paths_ = get_im_names(osp.join(raw_dir, dir_name),
return_path=True, return_np=False)
im_paths_.sort()
im_paths += list(im_paths_)
nums.append(len(im_paths_))
im_names = move_ims(
im_paths, new_im_dir, parse_original_im_name, new_im_name_tmpl)
split = dict()
keys = ['trainval_im_names', 'gallery_im_names', 'q_im_names']
inds = [0] + nums
inds = np.cumsum(inds)
for i, k in enumerate(keys):
split[k] = im_names[inds[i]:inds[i + 1]]
save_pickle(split, train_test_split_file)
print('Saving images done.')
return split
def save_images(zip_file, save_dir=None, train_test_split_file=None):
"""Rename and move all used images to a directory."""
print("Extracting zip file")
root = osp.dirname(osp.abspath(zip_file))
if save_dir is None:
save_dir = root
may_make_dir(osp.abspath(save_dir))
with ZipFile(zip_file) as z:
z.extractall(path=save_dir)
print("Extracting zip file done")
new_im_dir = osp.join(save_dir, 'images')
may_make_dir(osp.abspath(new_im_dir))
raw_dir = osp.join(save_dir, osp.basename(zip_file)[:-4])
im_paths = []
nums = []
im_paths_ = get_im_names(osp.join(raw_dir, 'bounding_box_train'),
return_path=True,
return_np=False)
im_paths_.sort()
im_paths += list(im_paths_)
nums.append(len(im_paths_))
im_paths_ = get_im_names(osp.join(raw_dir, 'bounding_box_test'),
return_path=True,
return_np=False)
im_paths_.sort()
im_paths_ = [p for p in im_paths_ if not osp.basename(p).startswith('-1')]
im_paths += list(im_paths_)
nums.append(len(im_paths_))
im_paths_ = get_im_names(osp.join(raw_dir, 'query'),
return_path=True,
return_np=False)
im_paths_.sort()
im_paths += list(im_paths_)
nums.append(len(im_paths_))
q_ids_cams = set([(parse_original_im_name(osp.basename(p), 'id'),
parse_original_im_name(osp.basename(p), 'cam'))
for p in im_paths_])
im_paths_ = get_im_names(osp.join(raw_dir, 'gt_bbox'),
return_path=True,
return_np=False)
im_paths_.sort()
# Only gather images for those ids and cams used in testing.
im_paths_ = [
p for p in im_paths_
if (parse_original_im_name(osp.basename(p), 'id'),
parse_original_im_name(osp.basename(p), 'cam')) in q_ids_cams
]
im_paths += list(im_paths_)
nums.append(len(im_paths_))
im_names = move_ims(im_paths, new_im_dir, parse_original_im_name,
new_im_name_tmpl)
split = dict()
keys = [
'trainval_im_names', 'gallery_im_names', 'q_im_names', 'mq_im_names'
]
inds = [0] + nums
inds = np.cumsum(np.array(inds))
for i, k in enumerate(keys):
split[k] = im_names[inds[i]:inds[i + 1]]
save_pickle(split, train_test_split_file)
print('Saving images done.')
return split
def save_images(original_file, save_dir=None, train_test_split_file=None):
"""Rename and move all used images to a directory."""
# print("Extracting zip file")
root = osp.dirname(osp.abspath(original_file))
if save_dir is None:
save_dir = root
may_make_dir(osp.abspath(save_dir))
# with ZipFile(original_file) as z:
# z.extractall(path=save_dir)
# print("Extracting zip file done")
new_im_dir = osp.join(save_dir, 'images')
may_make_dir(osp.abspath(new_im_dir))
raw_dir = osp.abspath(original_file)
print('raw_dir: ', raw_dir)
im_paths = []
nums = []
im_paths_ = get_im_names(osp.join(raw_dir, 'bounding_box_train'),
pattern='*.png',
return_path=True,
return_np=False)
im_paths_.sort()
im_paths += list(im_paths_)
nums.append(len(im_paths_))
print('dir_name: bounding_box_train')
print('nums: ', nums)
# Create (anchor, positive, negative)
anchor_positive_negative_2(im_paths, parse_original_im_name, save_dir)
im_paths_ = get_im_names(osp.join(raw_dir, 'bounding_box_test'),
pattern='*.png',
return_path=True,
return_np=False)
im_paths_.sort()
im_paths_ = [p for p in im_paths_ if not osp.basename(p).startswith('-1')]
im_paths += list(im_paths_)
nums.append(len(im_paths_))
print('dir_name: bounding_box_test')
print('nums: ', nums)
im_paths_ = get_im_names(osp.join(raw_dir, 'query'),
pattern='*.png',
return_path=True,
return_np=False)
im_paths_.sort()
im_paths += list(im_paths_)
nums.append(len(im_paths_))
q_ids_cams = set([(parse_original_im_name(osp.basename(p), 'id'),
parse_original_im_name(osp.basename(p), 'cam'))
for p in im_paths_])
print('dir_name: query')
print('nums: ', nums)
im_paths_ = get_im_names(osp.join(raw_dir, 'gt_bbox'),
pattern='*.png',
return_path=True,
return_np=False)
im_paths_.sort()
#print('len of im_paths:'+str(len(im_paths)))
# Only gather images for those ids and cams used in testing.
im_paths_ = [
p for p in im_paths_
if (parse_original_im_name(osp.basename(p), 'id'),
parse_original_im_name(osp.basename(p), 'cam')) in q_ids_cams
]
im_paths += list(im_paths_)
nums.append(len(im_paths_))
print('dir_name: gt_bbox')
print('nums: ', nums)
im_names = move_ims_2(im_paths, parse_original_im_name, new_im_name_tmpl)
split = dict()
keys = [
'trainval_im_names', 'gallery_im_names', 'q_im_names', 'mq_im_names'
]
inds = [0] + nums
print('inds: ', inds)
inds = np.cumsum(np.array(inds))
print('inds: ', inds)
print('enumerate(keys): ', enumerate(keys))
for i, k in enumerate(keys):
print('i,k: ', i, k)
split[k] = im_names[inds[i]:inds[i + 1]]
save_pickle(split, train_test_split_file)
print('Saving images done.')
return split
def save_images(zip_file, save_dir=None, train_test_split_file=None):
"""Rename and move all used images to a directory."""
print("Extracting zip file")
root = osp.dirname(osp.abspath(zip_file))
if save_dir is None:
save_dir = root
may_make_dir(osp.abspath(save_dir))
with ZipFile(zip_file) as z:
z.extractall(path=save_dir)
print("Extracting zip file done")
new_im_dir = osp.join(save_dir, 'images')
may_make_dir(osp.abspath(new_im_dir))
raw_dir = osp.join(save_dir, osp.basename(zip_file)[:-4])
im_paths = []
nums = []
im_paths_ = get_im_names(osp.join(raw_dir, 'bounding_box_train'),
return_path=True, return_np=False)
im_paths_.sort()
im_paths += list(im_paths_)
nums.append(len(im_paths_))
im_paths_ = get_im_names(osp.join(raw_dir, 'bounding_box_test'),
return_path=True, return_np=False)
im_paths_.sort()
im_paths_ = [p for p in im_paths_ if not osp.basename(p).startswith('-1')]
im_paths += list(im_paths_)
nums.append(len(im_paths_))
im_paths_ = get_im_names(osp.join(raw_dir, 'query'),
return_path=True, return_np=False)
im_paths_.sort()
im_paths += list(im_paths_)
nums.append(len(im_paths_))
q_ids_cams = set([(parse_original_im_name(osp.basename(p), 'id'),
parse_original_im_name(osp.basename(p), 'cam'))
for p in im_paths_])
im_paths_ = get_im_names(osp.join(raw_dir, 'gt_bbox'),
return_path=True, return_np=False)
im_paths_.sort()
# Only gather images for those ids and cams used in testing.
im_paths_ = [p for p in im_paths_
if (parse_original_im_name(osp.basename(p), 'id'),
parse_original_im_name(osp.basename(p), 'cam'))
in q_ids_cams]
im_paths += list(im_paths_)
nums.append(len(im_paths_))
im_names = move_ims(
im_paths, new_im_dir, parse_original_im_name, new_im_name_tmpl)
split = dict()
keys = ['trainval_im_names', 'gallery_im_names', 'q_im_names', 'mq_im_names']
inds = [0] + nums
inds = np.cumsum(np.array(inds))
for i, k in enumerate(keys):
split[k] = im_names[inds[i]:inds[i + 1]]
save_pickle(split, train_test_split_file)
print('Saving images done.')
return split
def save_im_name_mapping(raw_dir, ori_to_new_im_name_file):
im_names = []
for dir_name in [
'bounding_box_train', 'bounding_box_test', 'query', 'gt_bbox'
]:
im_names_ = get_im_names(osp.join(raw_dir, dir_name),
return_path=False,
return_np=False)
im_names_.sort()
# Filter out id -1
if dir_name == 'bounding_box_test':
im_names_ = [n for n in im_names_ if not n.startswith('-1')]
# Get (id, cam) in query set
if dir_name == 'query':
q_ids_cams = set([(parse_original_im_name(n, 'id'),
parse_original_im_name(n, 'cam'))
for n in im_names_])
# Filter out images that are not corresponding to query (id, cam)
if dir_name == 'gt_bbox':
im_names_ = [
n for n in im_names_
if (parse_original_im_name(n, 'id'),
parse_original_im_name(n, 'cam')) in q_ids_cams
]
# Images in different original directories may have same names,
# so here we use relative paths as original image names.
im_names_ = [osp.join(dir_name, n) for n in im_names_]
im_names += im_names_
new_im_names = map_im_names(im_names, parse_original_im_name,
new_im_name_tmpl)
ori_to_new_im_name = dict(zip(im_names, new_im_names))
save_pickle(ori_to_new_im_name, ori_to_new_im_name_file)
print('File saved to {}'.format(ori_to_new_im_name_file))
##################
# Just Some Info #
##################
print('len(im_names)', len(im_names))
print('len(set(im_names))', len(set(im_names)))
print('len(set(new_im_names))', len(set(new_im_names)))
print('len(ori_to_new_im_name)', len(ori_to_new_im_name))
bounding_box_train_im_names = get_im_names(osp.join(
raw_dir, 'bounding_box_train'),
return_path=False,
return_np=False)
bounding_box_test_im_names = get_im_names(osp.join(raw_dir,
'bounding_box_test'),
return_path=False,
return_np=False)
query_im_names = get_im_names(osp.join(raw_dir, 'query'),
return_path=False,
return_np=False)
gt_bbox_im_names = get_im_names(osp.join(raw_dir, 'gt_bbox'),
return_path=False,
return_np=False)
print(
'set(bounding_box_train_im_names).isdisjoint(set(bounding_box_test_im_names))',
set(bounding_box_train_im_names).isdisjoint(
set(bounding_box_test_im_names)))
print('set(bounding_box_train_im_names).isdisjoint(set(query_im_names))',
set(bounding_box_train_im_names).isdisjoint(set(query_im_names)))
print('set(bounding_box_train_im_names).isdisjoint(set(gt_bbox_im_names))',
set(bounding_box_train_im_names).isdisjoint(set(gt_bbox_im_names)))
print('set(bounding_box_test_im_names).isdisjoint(set(query_im_names))',
set(bounding_box_test_im_names).isdisjoint(set(query_im_names)))
print('set(bounding_box_test_im_names).isdisjoint(set(gt_bbox_im_names))',
set(bounding_box_test_im_names).isdisjoint(set(gt_bbox_im_names)))
print('set(query_im_names).isdisjoint(set(gt_bbox_im_names))',
set(query_im_names).isdisjoint(set(gt_bbox_im_names)))
print('len(query_im_names)', len(query_im_names))
print('len(gt_bbox_im_names)', len(gt_bbox_im_names))
print('len(set(query_im_names) & set(gt_bbox_im_names))',
len(set(query_im_names) & set(gt_bbox_im_names)))
print('len(set(query_im_names) | set(gt_bbox_im_names))',
len(set(query_im_names) | set(gt_bbox_im_names)))
def save_images(data_dir, save_dir=None, train_test_split_file=None):
"""Rename and move all used images to a directory."""
# print("Extracting zip file")
# root = osp.dirname(osp.abspath(zip_file))
# if save_dir is None:
# save_dir = root
# may_make_dir(osp.abspath(save_dir))
# with ZipFile(zip_file) as z:
# z.extractall(path=save_dir)
# print("Extracting zip file done")
#get the images and origin name of path
new_im_dir = osp.join(save_dir, 'images')
may_make_dir(osp.abspath(new_im_dir))
# define paths of all images and number of files in four folders
im_paths = []
bb_test = []
bb_test_num = 0
bb_train_num = 0
bb_train = []
query = []
query_num = 0
gt_bb_num = 0
gt_bb = []
nums = []
for data in dataset:
raw_dir = osp.join(data_dir, data)
im_paths_ = get_im_names(osp.join(raw_dir, 'bounding_box_train'),
return_path=True,
return_np=False)
im_paths_.sort()
bb_train += list(im_paths_)
bb_train_num += len(im_paths_)
im_paths_ = get_im_names(osp.join(raw_dir, 'bounding_box_test'),
return_path=True,
return_np=False)
im_paths_.sort()
im_paths_ = [
p for p in im_paths_ if not osp.basename(p).startswith('-1')
]
bb_test += list(im_paths_)
bb_test_num += len(im_paths_)
im_paths_ = get_im_names(osp.join(raw_dir, 'query'),
return_path=True,
return_np=False)
im_paths_.sort()
query += list(im_paths_)
query_num += len(im_paths_)
q_ids_cams = set([(parse_original_im_name(osp.basename(p), 'id'),
parse_original_im_name(osp.basename(p), 'cam'))
for p in im_paths_])
im_paths_ = get_im_names(osp.join(raw_dir, 'gt_bbox'),
return_path=True,
return_np=False)
im_paths_.sort()
# Only gather images for those ids and cams used in testing.
im_paths_ = [
p for p in im_paths_
if (parse_original_im_name(osp.basename(p), 'id'),
parse_original_im_name(osp.basename(p), 'cam')) in q_ids_cams
]
gt_bb += list(im_paths_)
gt_bb_num += len(im_paths_)
im_paths = bb_train + bb_test + query + gt_bb
nums = [bb_train_num] + [bb_test_num] + [query_num] + [gt_bb_num]
im_names = move_ims(im_paths, new_im_dir, parse_original_im_name,
new_im_name_tmpl)
split = dict()
keys = [
'trainval_im_names', 'gallery_im_names', 'q_im_names', 'mq_im_names'
]
inds = [0] + nums
inds = np.cumsum(np.array(inds))
for i, k in enumerate(keys):
split[k] = im_names[inds[i]:inds[i + 1]]
save_pickle(split, train_test_split_file)
print('Saving images done.')
return split