def __init__(self, dataset_folder, spt_path, boxes_file, vid2idx, mode='train',get_loader=get_default_video_loader,
sample_size=112, classes_idx=None):
self.dataset_folder = dataset_folder
self.sample_size = sample_size
self.boxes_file = boxes_file
self.vid2idx = vid2idx
self.mode = mode
self.data, self.max_frames, self.max_actions = make_dataset_names( dataset_folder, spt_path, boxes_file, mode)
self.loader = get_loader()
self.classes_idx = classes_idx
# mean = [112.07945832, 112.87372333, 106.90993363] # ucf-101 24 classes
mean = [103.29825354, 104.63845484, 90.79830328] # jhmdb from .png
spatial_transform = Compose([Scale(sample_size), # [Resize(sample_size),
ToTensor(),
Normalize(mean, [1, 1, 1])])
self.spatial_transform=spatial_transform
os.path.join(root_path, dataset_cfg.dataset.boxes_file))
split_txt_path = os.path.abspath(
os.path.join(root_path, dataset_cfg.dataset.split_txt_path))
### get videos id
actions = dataset_cfg.dataset.classes
cls2idx = {actions[i]: i for i in range(0, len(actions))}
vid2idx, vid_names = get_vid_dict(dataset_frames)
# # get mean
# mean = [112.07945832, 112.87372333, 106.90993363] # ucf-101 24 classes
mean = [0.5, 0.5, 0.5]
std = [0.5, 0.5, 0.5]
spatial_transform = Compose([
Scale(sample_size), # [Resize(sample_size),
ToTensor(),
Normalize(mean, std)
])
temporal_transform = LoopPadding(sample_duration)
n_classes = len(actions)
#######################################################
# Part 1-1 - train nTPN - without reg #
#######################################################
print(' -----------------------------------------------------')
print('| Part 1-1 - train TPN - without reg |')
print(' -----------------------------------------------------')
def get_default_video_loader():
image_loader = get_default_image_loader()
return functools.partial(video_loader, image_loader=image_loader)
if __name__ == '__main__':
dataset_path = '/gpu-data2/sgal/UCF-101-frames'
output_path = '/gpu-data2/sgal/UCF-101-pickle'
classes = next(os.walk(dataset_path, True))[1]
loader = get_default_video_loader()
sample_size = 112
mean = [112.07945832, 112.87372333, 106.90993363] # ucf-101 24 classes
spatial_transform = Compose([Scale(sample_size), # [Resize(sample_size),
ToTensor(),
Normalize(mean, [1, 1, 1])])
for cls in classes:
videos = next(os.walk(os.path.join(dataset_path, cls), True))[1]
if not os.path.exists(os.path.join(output_path, cls)):
os.mkdir(os.path.join(output_path, cls))
for vid in videos:
video_path = os.path.join(cls,vid)
path = os.path.join(dataset_path,video_path)
print(path)
if not os.path.exists(os.path.join(output_path,cls,vid)):
os.mkdir(os.path.join(output_path,cls,vid))
from utils.get_dataset_mean import get_dataset_mean_and_std
from utils.create_video_id import get_vid_dict
np.random.seed(42)
dataset_folder = '../../dataset_frames'
boxes_file = '../../dataset_actions_annots.json'
split_txt = '../../00sequences.txt'
sample_size = 112
vid2idx, vid_names = get_vid_dict(dataset_folder)
scale = 1
rev_scale = 255 if scale == 1 else 1
mean, std = get_dataset_mean_and_std('kth', scale = 1)
std = (0.5,0.5,0.5)
mean = (0.5,0.5,0.5)
print(f'mean {mean}, {std} std')
spatial_transform = Compose([Scale(sample_size), ToTensor(),
Normalize(mean, std)
])
print(f'boxes_file {boxes_file}')
data = Video_Dataset_small_clip(video_path=dataset_folder, bboxes_file=boxes_file,
split_txt_path=split_txt, spatial_transform=spatial_transform, scale=scale)
# data = Video_Dataset_whole_video(video_path=dataset_folder, bboxes_file=boxes_file,
# split_txt_path=split_txt, spatial_transform=spatial_transform,
# vid2idx=vid2idx
# )
ret = data[5]
print(f'ret : {ret}')
