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.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(' -----------------------------------------------------')
## Define Dataloaders
train_data = Video_Dataset_small_clip(
'__background__', 'Basketball', 'BasketballDunk', 'Biking',
'CliffDiving', 'CricketBowling', 'Diving', 'Fencing',
'FloorGymnastics', 'GolfSwing', 'HorseRiding', 'IceDancing',
'LongJump', 'PoleVault', 'RopeClimbing', 'SalsaSpin', 'SkateBoarding',
'Skiing', 'Skijet', 'SoccerJuggling', 'Surfing', 'TennisSwing',
'TrampolineJumping', 'VolleyballSpiking', 'WalkingWithDog'
]
cls2idx = {actions[i]: i for i in range(0, len(actions))}
### get videos id
spatial_transform = Compose([
Scale(sample_size), # [Resize(sample_size),
ToTensor(),
Normalize(mean, [1, 1, 1])
])
temporal_transform = LoopPadding(sample_duration)
n_classes = len(actions)
# Init action_net
model = ACT_net(actions, sample_duration)
model.create_architecture()
model = nn.DataParallel(model)
model.to(device)
model_data = torch.load('./action_net_model_both_without_avg.pwf')
# model.load_state_dict(model_data)