def __init__(self, root, split, clip_len):
super(Kinetics, self).__init__()
# self.root = os.path.join(root, 'frames')
self.root = root
self.bbox = os.path.join(root, 'bbox')
self.split = split
self.clip_len = clip_len
self.sample_frame = [i * 8 for i in range(4)]
if not os.path.exists('data/kinetics_data.pth'):
parse_annotations(self.root)
print('Annotations created!')
annotations = torch.load('data/kinetics_data.pth')
self.labels = annotations['labels']
self.train_data = annotations['train_data']
self.val_data = annotations['val_data']
self.data = self.train_data if self.split == 'train' else self.val_data
print('%d train clips | %d val clips' %
(len(self.train_data), len(self.val_data)))
self.clip_transform = util.clip_transform(self.split, self.clip_len)
self.loader = lambda fl: Image.open(os.path.join(self.root, fl)
).convert('RGB')
def __init__(self, root, split, max_len, sample_rate):
self.root = root
self.split = split
self.max_len = max_len
self.sample_rate = sample_rate
if self.max_len==-1:
self.max_len = 32
print ('Max length not chosen. Setting max length to:', self.max_len)
self.clip_transform = util.clip_transform(self.split, self.max_len)
self.img_transform = util.default_transform(self.split)
self.pair_transform = util.PairedTransform(self.split)
def __init__(self, root, split, clip_len):
super(KineticsMultiCrop, self).__init__(root, split, clip_len)
self.clip_transform = util.clip_transform('3crop', self.clip_len)