def make_dataset(root_path, annotation_path, subset, n_samples_for_each_video,
sample_duration):
data = load_annotation_data(annotation_path)
# check if the subdirectory of the dataset is split into volumes
is_volumed = len(os.listdir(root_path)) <= (len(VOLUME_SPLITS) + 1)
video_names, annotations = get_video_names_and_annotations(
data, subset, is_volumed)
class_to_idx = get_class_labels(data)
idx_to_class = {}
for name, label in class_to_idx.items():
idx_to_class[label] = name
dataset = []
for i in range(len(video_names)):
if i % 1000 == 0:
print('dataset loading [{}/{}]'.format(i, len(video_names)))
video_path = os.path.join(root_path, video_names[i])
if not os.path.exists(video_path):
print("Path does not exist" + video_path)
continue
n_frames_file_path = os.path.join(video_path, 'n_frames')
n_frames = int(load_value_file(n_frames_file_path))
if n_frames <= 0:
continue
begin_t = 1
end_t = n_frames
sample = {
'video': video_path,
'segment': [begin_t, end_t],
'n_frames': n_frames,
#'video_id': video_names[i].split('/')[1]
'video_id': video_names[i]
}
if len(annotations) != 0:
sample['label'] = class_to_idx[annotations[i]['label']]
else:
sample['label'] = -1
if n_samples_for_each_video == 1:
sample['frame_indices'] = list(range(1, n_frames + 1))
dataset.append(sample)
else:
if n_samples_for_each_video > 1:
step = max(
1,
math.ceil((n_frames - 1 - sample_duration) /
(n_samples_for_each_video - 1)))
else:
step = sample_duration
for j in range(1, n_frames, step):
sample_j = copy.deepcopy(sample)
sample_j['frame_indices'] = list(
range(j, min(n_frames + 1, j + sample_duration)))
dataset.append(sample_j)
return dataset, idx_to_class
def make_dataset(dataset_path, subset, sample_duration, n_samples_for_each_video):
dataset_path = os.path.join(dataset_path, 'QUVA')
video_path = os.path.join(dataset_path, 'imgs')
video_names, annotations = get_video_names_and_annotations(dataset_path, subset)
dataset = []
max_n_frames = 0
for i in range(len(video_names)):
if (i+1) % 50 == 0 or i+1 == len(video_names):
print('{} dataset loading [{}/{}]'.format(subset, i+1, len(video_names)))
video_path_i = os.path.join(video_path, subset, video_names[i])
if not os.path.exists(video_path_i):
continue
n_frames_file_path = os.path.join(video_path_i, 'n_frames')
n_frames = int(load_value_file(n_frames_file_path))
max_n_frames = max(max_n_frames, n_frames)
if n_frames <= 0:
continue
begin_t = 1
end_t = n_frames
sample = {
'video': video_path_i,
'segment': [begin_t, end_t],
'n_frames': n_frames,
'video_id': video_names[i][0:3],
'label': annotations[i]
}
if n_samples_for_each_video == 1:
sample['frame_indices'] = list(range(1, n_frames + 1))
dataset.append(sample)
else:
if n_samples_for_each_video > 1:
step = max(1,
math.ceil((n_frames - 1 - sample_duration) /
(n_samples_for_each_video - 1)))
step = int(step)
else:
raise('error, n_samples_for_each_video should >=1\n')
# step = sample_duration
for j in range(1, n_frames-sample_duration, step):
sample_j = copy.deepcopy(sample)
sample_j['frame_indices'] = list(
range(j, min(n_frames + 1, j + sample_duration)))
dataset.append(sample_j)
return dataset, max_n_frames
def make_untrimmed_dataset(root_path, annotation_path, subset,
n_samples_for_each_video, sample_duration):
data = load_annotation_data(annotation_path)
video_names, _ = get_video_names_and_annotations(data, subset)
class_to_idx = get_class_labels(data)
idx_to_class = {}
for name, label in class_to_idx.items():
idx_to_class[label] = name
dataset = []
for i in range(len(video_names)):
if i % 1000 == 0:
print('dataset loading [{}/{}]'.format(i, len(video_names)))
video_path = os.path.join(root_path, video_names[i])
if not os.path.exists(video_path):
continue
fps_file_path = os.path.join(video_path, 'fps')
fps = load_value_file(fps_file_path)
begin_t = 1
end_t = get_end_t(video_path)
n_frames = end_t - begin_t
sample = {
'video': video_path,
'segment': [begin_t, end_t],
'fps': fps,
'video_id': video_names[i][2:]
}
if n_samples_for_each_video >= 1:
step = max(
1,
math.ceil((n_frames - 1 - sample_duration) /
(n_samples_for_each_video - 1)))
else:
step = sample_duration
for j in range(begin_t, end_t, step):
sample_j = copy.deepcopy(sample)
frame_indices = list(range(j, j + sample_duration))
frame_indices = modify_frame_indices(sample_j['video'],
frame_indices)
if len(frame_indices) < 16:
continue
sample_j['frame_indices'] = frame_indices
dataset.append(sample_j)
return dataset, idx_to_class
def make_dataset(root_path, annotation_path, subset, n_samples_for_each_video,
sample_duration):
data = load_annotation_data(annotation_path)
video_names, annotations = get_video_names_and_annotations(data, subset)
if not annotations:
raise ValueError('Unable to load annotations...')
class_to_idx = get_class_labels(data)
idx_to_class = {}
for name, label in class_to_idx.items():
idx_to_class[label] = name
dataset = []
for i in range(len(video_names)):
if i % 1000 == 0:
print('Loading UCF-101 videos [{}/{}]'.format(i, len(video_names)))
video_path = os.path.join(root_path, video_names[i])
if not os.path.exists(video_path):
continue
n_frames_file_path = os.path.join(video_path, 'n_frames')
if not os.path.exists(n_frames_file_path):
raise FileNotFoundError(
'n_frames_file_path does not exist: {}'.format(
n_frames_file_path))
n_frames = int(load_value_file(n_frames_file_path))
if n_frames <= 0:
continue
begin_t = 1
end_t = n_frames
sample = {
'video': video_path,
'segment': [begin_t, end_t],
'n_frames': n_frames,
'video_id': video_names[i].split('/')[1]
}
if len(annotations) != 0:
sample['label'] = class_to_idx[annotations[i]['label']]
else:
sample['label'] = -1
if n_samples_for_each_video == 1:
sample['frame_indices'] = list(range(1, n_frames + 1))
dataset.append(sample)
else:
if n_samples_for_each_video > 1:
step = max(
1,
math.ceil((n_frames - 1 - sample_duration) /
(n_samples_for_each_video - 1)))
else:
step = sample_duration
for j in range(1, n_frames, step):
sample_j = copy.deepcopy(sample)
sample_j['frame_indices'] = list(
range(j, min(n_frames + 1, j + sample_duration)))
dataset.append(sample_j)
return dataset, idx_to_class