def transform(zip_file, save_dir=None):
"""Refactor file directories, rename images and partition the train/val/test
set.
"""
train_test_split_file = osp.join(save_dir, 'train_test_split.pkl')
train_test_split = save_images(zip_file, save_dir, train_test_split_file)
# train_test_split = load_pickle(train_test_split_file)
# partition train/val/test set
trainval_ids = list(
set([
parse_new_im_name(n, 'id')
for n in train_test_split['trainval_im_names']
]))
# Sort ids, so that id-to-label mapping remains the same when running
# the code on different machines.
trainval_ids.sort()
trainval_ids2labels = dict(zip(trainval_ids, range(len(trainval_ids))))
partitions = partition_train_val_set(train_test_split['trainval_im_names'],
parse_new_im_name,
num_val_ids=100)
train_im_names = partitions['train_im_names']
train_ids = list(
set([parse_new_im_name(n, 'id')
for n in partitions['train_im_names']]))
# Sort ids, so that id-to-label mapping remains the same when running
# the code on different machines.
train_ids.sort()
train_ids2labels = dict(zip(train_ids, range(len(train_ids))))
# A mark is used to denote whether the image is from
# query (mark == 0), or
# gallery (mark == 1), or
# multi query (mark == 2) set
val_marks = [0, ] * len(partitions['val_query_im_names']) \
+ [1, ] * len(partitions['val_gallery_im_names'])
val_im_names = list(partitions['val_query_im_names']) \
+ list(partitions['val_gallery_im_names'])
test_im_names = list(train_test_split['q_im_names']) \
+ list(train_test_split['gallery_im_names'])
test_marks = [0, ] * len(train_test_split['q_im_names']) \
+ [1, ] * len(train_test_split['gallery_im_names'])
partitions = {
'trainval_im_names': train_test_split['trainval_im_names'],
'trainval_ids2labels': trainval_ids2labels,
'train_im_names': train_im_names,
'train_ids2labels': train_ids2labels,
'val_im_names': val_im_names,
'val_marks': val_marks,
'test_im_names': test_im_names,
'test_marks': test_marks
}
partition_file = osp.join(save_dir, 'partitions.pkl')
save_pickle(partitions, partition_file)
print('Partition file saved to {}'.format(partition_file))
def transform(zip_file, save_dir=None):
"""Refactor file directories, rename images and partition the train/val/test
set.
"""
train_test_split_file = osp.join(save_dir, 'train_test_split.pkl')
train_test_split = save_images(zip_file, save_dir, train_test_split_file)
# train_test_split = load_pickle(train_test_split_file)
# partition train/val/test set
trainval_ids = list(set([parse_new_im_name(n, 'id')
for n in train_test_split['trainval_im_names']]))
# Sort ids, so that id-to-label mapping remains the same when running
# the code on different machines.
trainval_ids.sort()
trainval_ids2labels = dict(zip(trainval_ids, range(len(trainval_ids))))
partitions = partition_train_val_set(
train_test_split['trainval_im_names'], parse_new_im_name, num_val_ids=100)
train_im_names = partitions['train_im_names']
train_ids = list(set([parse_new_im_name(n, 'id')
for n in partitions['train_im_names']]))
# Sort ids, so that id-to-label mapping remains the same when running
# the code on different machines.
train_ids.sort()
train_ids2labels = dict(zip(train_ids, range(len(train_ids))))
# A mark is used to denote whether the image is from
# query (mark == 0), or
# gallery (mark == 1), or
# multi query (mark == 2) set
val_marks = [0, ] * len(partitions['val_query_im_names']) \
+ [1, ] * len(partitions['val_gallery_im_names'])
val_im_names = list(partitions['val_query_im_names']) \
+ list(partitions['val_gallery_im_names'])
test_im_names = list(train_test_split['q_im_names']) \
+ list(train_test_split['mq_im_names']) \
+ list(train_test_split['gallery_im_names'])
test_marks = [0, ] * len(train_test_split['q_im_names']) \
+ [2, ] * len(train_test_split['mq_im_names']) \
+ [1, ] * len(train_test_split['gallery_im_names'])
partitions = {'trainval_im_names': train_test_split['trainval_im_names'],
'trainval_ids2labels': trainval_ids2labels,
'train_im_names': train_im_names,
'train_ids2labels': train_ids2labels,
'val_im_names': val_im_names,
'val_marks': val_marks,
'test_im_names': test_im_names,
'test_marks': test_marks}
partition_file = osp.join(save_dir, 'partitions.pkl')
save_pickle(partitions, partition_file)
print('Partition file saved to {}'.format(partition_file))
def _updatePartition(self, img_fnames):
specific_dir = self.dataset_nm
## Old
pkl_fpath_old = osp.join(self.update_trainingset_path, specific_dir, \
'original')
pkl_fname = osp.join(pkl_fpath_old, 'partitions.pkl')
old_partitions = load_pickle(pkl_fname)
trainval_im_names = old_partitions['trainval_im_names']
## Update
# Train Val
trainval_im_names = trainval_im_names + list(img_fnames)
trainval_im_names.sort()
trainval_ids = list(set([parse_new_im_name(n, 'id')
for n in trainval_im_names]))
trainval_ids.sort()
trainval_ids2labels = dict(zip(trainval_ids, range(len(trainval_ids))))
partitions = partition_train_val_set(
trainval_im_names, parse_new_im_name, num_val_ids=100)
# Train
train_im_names = partitions['train_im_names']
train_ids = list(set([parse_new_im_name(n, 'id')
for n in partitions['train_im_names']]))
train_ids.sort()
train_ids2labels = dict(zip(train_ids, range(len(train_ids))))
# Val
val_marks = [0, ] * len(partitions['val_query_im_names']) \
+ [1, ] * len(partitions['val_gallery_im_names'])
val_im_names = list(partitions['val_query_im_names']) \
+ list(partitions['val_gallery_im_names'])
## Save
new_partitions = {'trainval_im_names': trainval_im_names,
'trainval_ids2labels': trainval_ids2labels,
'train_im_names': train_im_names,
'train_ids2labels': train_ids2labels,
'val_im_names': val_im_names,
'val_marks': val_marks,
'test_im_names': old_partitions['test_im_names'],
'test_marks': old_partitions['test_marks']}
pkl_fpath_new = osp.join(self.update_trainingset_path, specific_dir, \
'new')
pkl_fname = osp.join(pkl_fpath_new, 'partitions.pkl')
save_pickle(new_partitions, pkl_fname)
return pkl_fname
def transform(zip_file, train_test_partition_file, save_dir=None):
"""Save images and partition the train/val/test set.
"""
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")
mat_file = osp.join(save_dir, osp.basename(zip_file)[:-4], 'cuhk-03.mat')
save_images(mat_file, save_dir, new_im_name_tmpl)
if osp.exists(train_test_partition_file):
train_test_partition = load_pickle(train_test_partition_file)
else:
raise RuntimeError('Train/test partition file should be provided.')
for im_type in ['detected', 'labeled']:
trainval_im_names = train_test_partition[im_type]['train_im_names']
trainval_ids = list(set([parse_im_name(n, 'id')
for n in trainval_im_names]))
# Sort ids, so that id-to-label mapping remains the same when running
# the code on different machines.
trainval_ids.sort()
trainval_ids2labels = dict(zip(trainval_ids, range(len(trainval_ids))))
train_val_partition = \
partition_train_val_set(trainval_im_names, parse_im_name, num_val_ids=100)
train_im_names = train_val_partition['train_im_names']
train_ids = list(set([parse_im_name(n, 'id')
for n in train_val_partition['train_im_names']]))
# Sort ids, so that id-to-label mapping remains the same when running
# the code on different machines.
train_ids.sort()
train_ids2labels = dict(zip(train_ids, range(len(train_ids))))
# A mark is used to denote whether the image is from
# query (mark == 0), or
# gallery (mark == 1), or
# multi query (mark == 2) set
val_marks = [0, ] * len(train_val_partition['val_query_im_names']) \
+ [1, ] * len(train_val_partition['val_gallery_im_names'])
val_im_names = list(train_val_partition['val_query_im_names']) \
+ list(train_val_partition['val_gallery_im_names'])
test_im_names = list(train_test_partition[im_type]['query_im_names']) \
+ list(train_test_partition[im_type]['gallery_im_names'])
test_marks = [0, ] * len(train_test_partition[im_type]['query_im_names']) \
+ [1, ] * len(
train_test_partition[im_type]['gallery_im_names'])
partitions = {'trainval_im_names': trainval_im_names,
'trainval_ids2labels': trainval_ids2labels,
'train_im_names': train_im_names,
'train_ids2labels': train_ids2labels,
'val_im_names': val_im_names,
'val_marks': val_marks,
'test_im_names': test_im_names,
'test_marks': test_marks}
partition_file = osp.join(save_dir, im_type, 'partitions.pkl')
save_pickle(partitions, partition_file)
print('Partition file for "{}" saved to {}'.format(im_type, partition_file))
def transform(zip_file, train_test_partition_file, save_dir=None):
"""Save images and partition the train/val/test set.
"""
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")
mat_file = osp.join(save_dir, osp.basename(zip_file)[:-4], 'cuhk-03.mat')
save_images(mat_file, save_dir, new_im_name_tmpl)
if osp.exists(train_test_partition_file):
train_test_partition = load_pickle(train_test_partition_file)
else:
raise RuntimeError('Train/test partition file should be provided.')
for im_type in ['detected', 'labeled']:
trainval_im_names = train_test_partition[im_type]['train_im_names']
trainval_ids = list(
set([parse_im_name(n, 'id') for n in trainval_im_names]))
# Sort ids, so that id-to-label mapping remains the same when running
# the code on different machines.
trainval_ids.sort()
trainval_ids2labels = dict(zip(trainval_ids, range(len(trainval_ids))))
train_val_partition = \
partition_train_val_set(trainval_im_names, parse_im_name, num_val_ids=100)
train_im_names = train_val_partition['train_im_names']
train_ids = list(
set([
parse_im_name(n, 'id')
for n in train_val_partition['train_im_names']
]))
# Sort ids, so that id-to-label mapping remains the same when running
# the code on different machines.
train_ids.sort()
train_ids2labels = dict(zip(train_ids, range(len(train_ids))))
# A mark is used to denote whether the image is from
# query (mark == 0), or
# gallery (mark == 1), or
# multi query (mark == 2) set
val_marks = [0, ] * len(train_val_partition['val_query_im_names']) \
+ [1, ] * len(train_val_partition['val_gallery_im_names'])
val_im_names = list(train_val_partition['val_query_im_names']) \
+ list(train_val_partition['val_gallery_im_names'])
test_im_names = list(train_test_partition[im_type]['query_im_names']) \
+ list(train_test_partition[im_type]['gallery_im_names'])
test_marks = [0, ] * len(train_test_partition[im_type]['query_im_names']) \
+ [1, ] * len(
train_test_partition[im_type]['gallery_im_names'])
partitions = {
'trainval_im_names': trainval_im_names,
'trainval_ids2labels': trainval_ids2labels,
'train_im_names': train_im_names,
'train_ids2labels': train_ids2labels,
'val_im_names': val_im_names,
'val_marks': val_marks,
'test_im_names': test_im_names,
'test_marks': test_marks
}
partition_file = osp.join(save_dir, im_type, 'partitions.pkl')
save_pickle(partitions, partition_file)
print('Partition file for "{}" saved to {}'.format(
im_type, partition_file))
def transform(original_file, save_dir=None):
"""Refactor file directories, rename images and partition the train/val/test
set.
"""
train_test_split_file = osp.join(save_dir, 'train_split.pkl')
train_test_split = save_images(original_file, save_dir,
train_test_split_file)
# train_test_split = load_pickle(train_test_split_file)
# partition train/val/test set
trainval_ids = list(
set([
parse_new_im_name(n, 'id')
for n in train_test_split['trainval_im_names']
]))
# Sort ids, so that id-to-label mapping remains the same when running
# the code on different machines.
trainval_ids.sort()
trainval_ids2labels = dict(zip(trainval_ids, range(len(trainval_ids))))
partitions = partition_train_val_set(train_test_split['trainval_im_names'],
parse_new_im_name,
num_val_ids=100)
train_im_names = partitions['train_im_names']
train_ids = list(
set([parse_new_im_name(n, 'id')
for n in partitions['train_im_names']]))
# Sort ids, so that id-to-label mapping remains the same when running
# the code on different machines.
train_ids.sort()
train_ids2labels = dict(zip(train_ids, range(len(train_ids))))
# change anchor_positive_negative to new names
apn_pkl_file = osp.join(save_dir, 'anchor_positive_negative_split_2.pkl')
apn_pkl = load_pickle(apn_pkl_file)
anchor_list = apn_pkl['anchor']
positive_list = apn_pkl['positive']
negative_list = apn_pkl['negative']
anchor_array = np.array(anchor_list)
# mess up the order of anchor_positive_negative (trainval)
new_tv_anchor_names, new_tv_positive_names, new_tv_negative_names = mess_up_apn(
anchor_list, positive_list, negative_list)
# select the train anchor_positive_negative
train_anchor_names = []
train_positive_names = []
train_negative_names = []
for i in range(train_im_names.shape[0]):
k = np.where(anchor_array == train_im_names[i])
ind = k[0][0]
ta = anchor_list[ind]
tp = positive_list[ind]
tn = negative_list[ind]
train_anchor_names.append(ta)
train_positive_names.append(tp)
train_negative_names.append(tn)
# A mark is used to denote whether the image is from
# query (mark == 0), or
# gallery (mark == 1), or
# multi query (mark == 2) set
val_marks = [0, ] * len(partitions['val_query_im_names']) \
+ [1, ] * len(partitions['val_gallery_im_names'])
val_im_names = list(partitions['val_query_im_names']) \
+ list(partitions['val_gallery_im_names'])
test_im_names = list(train_test_split['q_im_names']) \
+ list(train_test_split['mq_im_names']) \
+ list(train_test_split['gallery_im_names'])
test_marks = [0, ] * len(train_test_split['q_im_names']) \
+ [2, ] * len(train_test_split['mq_im_names']) \
+ [1, ] * len(train_test_split['gallery_im_names'])
partitions = {
'trainval_anchor_im_names': new_tv_anchor_names,
'trainval_positive_im_names': new_tv_positive_names,
'trainval_negative_im_names': new_tv_negative_names,
'trainval_ids2labels': trainval_ids2labels,
'train_anchor_im_names': train_anchor_names,
'train_positive_im_names': train_positive_names,
'train_negative_im_names': train_negative_names,
'train_ids2labels': train_ids2labels,
'val_im_names': val_im_names,
'val_marks': val_marks,
'test_im_names': test_im_names,
'test_marks': test_marks
}
partition_file = osp.join(save_dir, 'new_shuffle_apn_partitions_2.pkl')
save_pickle(partitions, partition_file)
print('Partition file saved to {}'.format(partition_file))
