def get_training_set(opt, spatial_transform, temporal_transform,
target_transform):
assert opt.dataset in ['kinetics', 'activitynet', 'ucf101', 'hmdb51']
if opt.dataset == 'kinetics':
training_data = Kinetics(opt.video_path,
opt.annotation_path,
'training',
spatial_transform=spatial_transform,
temporal_transform=temporal_transform,
target_transform=target_transform)
elif opt.dataset == 'activitynet':
training_data = ActivityNet(opt.video_path,
opt.annotation_path,
'training',
False,
spatial_transform=spatial_transform,
temporal_transform=temporal_transform,
target_transform=target_transform)
elif opt.dataset == 'ucf101':
training_data = UCF101(opt.video_path,
opt.annotation_path,
'training',
spatial_transform=spatial_transform,
temporal_transform=temporal_transform,
target_transform=target_transform)
elif opt.dataset == 'hmdb51':
training_data = HMDB51(opt.video_path,
opt.annotation_path,
'training',
spatial_transform=spatial_transform,
temporal_transform=temporal_transform,
target_transform=target_transform)
return training_data
def get_training_set(opt, spatial_transform, temporal_transform,
target_transform):
assert opt.dataset in ['kinetics', 'jester', 'ucf101']
if opt.dataset == 'kinetics':
training_data = Kinetics(opt.video_path,
opt.annotation_path,
'training',
spatial_transform=spatial_transform,
temporal_transform=temporal_transform,
target_transform=target_transform,
sample_duration=opt.sample_duration)
elif opt.dataset == 'jester':
training_data = Jester(opt.video_path,
opt.annotation_path,
'training',
spatial_transform=spatial_transform,
temporal_transform=temporal_transform,
target_transform=target_transform,
sample_duration=opt.sample_duration)
elif opt.dataset == 'ucf101':
training_data = UCF101(opt.video_path,
opt.annotation_path,
'training',
spatial_transform=spatial_transform,
temporal_transform=temporal_transform,
target_transform=target_transform,
sample_duration=opt.sample_duration)
return training_data
def get_test_set(opt, spatial_transform, temporal_transform, target_transform):
assert opt.dataset in ['kinetics', 'activitynet', 'ucf101', 'hmdb51', 'wedding']
assert opt.test_subset in ['val', 'test']
if opt.test_subset == 'val':
subset = 'validation'
elif opt.test_subset == 'test':
subset = 'testing'
if opt.dataset == 'kinetics':
test_data = Kinetics(
opt.video_path,
opt.annotation_path,
subset,
0,
spatial_transform,
temporal_transform,
target_transform,
sample_duration=opt.sample_duration)
elif opt.dataset == 'activitynet':
test_data = ActivityNet(
opt.video_path,
opt.annotation_path,
subset,
True,
0,
spatial_transform,
temporal_transform,
target_transform,
sample_duration=opt.sample_duration)
elif opt.dataset == 'ucf101':
test_data = UCF101(
opt.video_path,
opt.annotation_path,
subset,
0,
spatial_transform,
temporal_transform,
target_transform,
sample_duration=opt.sample_duration)
elif opt.dataset == 'hmdb51':
test_data = HMDB51(
opt.video_path,
opt.annotation_path,
subset,
0,
spatial_transform,
temporal_transform,
target_transform,
sample_duration=opt.sample_duration)
elif opt.dataset == 'wedding':
test_data = Wedding(
opt.video_path,
opt.annotation_path,
subset,
0,
spatial_transform,
temporal_transform,
target_transform,
sample_duration=opt.sample_duration)
return test_data
def get_validation_set(opt, spatial_transform, temporal_transform,
target_transform):
assert opt.dataset in ['kinetics', 'ucf101', 'hmdb51', 'something']
if opt.dataset == 'kinetics':
validation_data = Kinetics(opt.video_path, opt.annotation_path,
'validation', opt.n_val_samples,
spatial_transform, temporal_transform,
target_transform)
elif opt.dataset == 'ucf101':
validation_data = UCF101(opt.video_path, opt.annotation_path,
'validation', opt.n_val_samples,
spatial_transform, temporal_transform,
target_transform)
elif opt.dataset == 'hmdb51':
validation_data = HMDB51(opt.video_path, opt.annotation_path,
'validation', opt.n_val_samples,
spatial_transform, temporal_transform,
target_transform)
elif opt.dataset == 'something':
validation_data = Something(opt.video_path, opt.annotation_path,
'validation', opt.n_val_samples,
spatial_transform, temporal_transform,
target_transform)
return validation_data
def get_validation_set(opt, spatial_transform, temporal_transform,
target_transform):
assert opt.dataset in ['kinetics', 'jester', 'ucf101']
if opt.dataset == 'kinetics':
validation_data = Kinetics(opt.video_path,
opt.annotation_path,
'validation',
opt.n_val_samples,
spatial_transform,
temporal_transform,
target_transform,
sample_duration=opt.sample_duration)
elif opt.dataset == 'jester':
validation_data = Jester(opt.video_path,
opt.annotation_path,
'validation',
opt.n_val_samples,
spatial_transform,
temporal_transform,
target_transform,
sample_duration=opt.sample_duration)
elif opt.dataset == 'ucf101':
validation_data = UCF101(opt.video_path,
opt.annotation_path,
'validation',
opt.n_val_samples,
spatial_transform,
temporal_transform,
target_transform,
sample_duration=opt.sample_duration)
return validation_data
def get_validation_set(opt,
spatial_transform,
temporal_transform,
target_transform,
score_sens_mode=False):
assert opt.dataset in [
'kinetics', 'activitynet', 'ucf101', 'hmdb51', 'something'
]
if opt.dataset == 'kinetics':
validation_data = Kinetics(opt.video_path,
opt.annotation_path,
'validation',
opt.n_val_samples,
spatial_transform,
temporal_transform,
target_transform,
sample_duration=opt.sample_duration)
elif opt.dataset == 'activitynet':
validation_data = ActivityNet(opt.video_path,
opt.annotation_path,
'validation',
opt.n_val_samples,
spatial_transform,
temporal_transform,
target_transform,
sample_duration=opt.sample_duration)
elif opt.dataset == 'ucf101':
validation_data = UCF101(opt.video_path,
opt.annotation_path,
'validation',
opt.n_val_samples,
spatial_transform,
temporal_transform,
target_transform,
sample_duration=opt.sample_duration,
score_sens_mode=score_sens_mode)
elif opt.dataset == 'hmdb51':
validation_data = HMDB51(opt.video_path,
opt.annotation_path,
'validation',
opt.n_val_samples,
spatial_transform,
temporal_transform,
target_transform,
sample_duration=opt.sample_duration)
elif opt.dataset == 'something':
validation_data = Something(opt.video_path,
opt.annotation_path,
'validation',
opt.n_val_samples,
spatial_transform,
temporal_transform,
target_transform,
sample_duration=opt.sample_duration,
score_sens_mode=score_sens_mode)
return validation_data
def get_test_set(opt, spatial_transform, temporal_transform, target_transform):
assert opt.dataset in [
'kinetics', 'jester', 'ucf101', 'egogesture', 'nvgesture'
]
assert opt.test_subset in ['val', 'test']
if opt.test_subset == 'val':
subset = 'validation'
elif opt.test_subset == 'test':
subset = 'testing'
if opt.dataset == 'kinetics':
test_data = Kinetics(opt.video_path,
opt.annotation_path,
subset,
0,
spatial_transform,
temporal_transform,
target_transform,
sample_duration=opt.sample_duration)
elif opt.dataset == 'jester':
test_data = Jester(opt.video_path,
opt.annotation_path,
subset,
0,
spatial_transform,
temporal_transform,
target_transform,
sample_duration=opt.sample_duration)
elif opt.dataset == 'ucf101':
test_data = UCF101(opt.video_path,
opt.annotation_path,
subset,
0,
spatial_transform,
temporal_transform,
target_transform,
sample_duration=opt.sample_duration)
elif opt.dataset == 'egogesture':
test_data = EgoGesture(opt.video_path,
opt.annotation_path,
subset,
opt.n_val_samples,
spatial_transform,
temporal_transform,
target_transform,
modality=opt.modality,
sample_duration=opt.sample_duration)
elif opt.dataset == 'nvgesture':
test_data = NV(opt.video_path,
opt.annotation_path,
'validation',
spatial_transform=spatial_transform,
temporal_transform=temporal_transform,
target_transform=target_transform,
sample_duration=opt.sample_duration,
modality=opt.modality)
return test_data
def get_validation_set(opt, spatial_transform, temporal_transform,
target_transform):
assert opt.dataset in ['kinetics', 'activitynet', 'ucf101', 'hmdb51', 'grit']
if opt.dataset == 'kinetics':
validation_data = Kinetics(
opt.video_path,
opt.annotation_path,
'validation',
opt.n_val_samples,
spatial_transform,
temporal_transform,
target_transform,
sample_duration=opt.sample_duration)
elif opt.dataset == 'activitynet':
validation_data = ActivityNet(
opt.video_path,
opt.annotation_path,
'validation',
False,
opt.n_val_samples,
spatial_transform,
temporal_transform,
target_transform,
sample_duration=opt.sample_duration)
elif opt.dataset == 'ucf101':
validation_data = UCF101(
opt.video_path,
opt.annotation_path,
'validation',
opt.n_val_samples,
spatial_transform,
temporal_transform,
target_transform,
sample_duration=opt.sample_duration)
elif opt.dataset == 'hmdb51':
validation_data = HMDB51(
opt.video_path,
opt.annotation_path,
'validation',
opt.n_val_samples,
spatial_transform,
temporal_transform,
target_transform,
sample_duration=opt.sample_duration)
elif opt.dataset == 'grit':
validation_data = GRIT(
opt.video_path,
opt.annotation_path,
'validation',
opt.sample_duration,
opt.n_val_samples,
spatial_transform,
temporal_transform,
target_transform)
return validation_data
def get_training_set(opt, spatial_transform, temporal_transform,
target_transform):
assert opt.dataset in ['kinetics', 'activitynet', 'ucf101', 'hmdb51','something','fire']
if opt.dataset == 'kinetics':
training_data = Kinetics(
opt.video_path+"/train_256",
opt.annotation_path,
'training',
spatial_transform=spatial_transform,
temporal_transform=temporal_transform,
target_transform=target_transform)
elif opt.dataset == 'activitynet':
training_data = ActivityNet(
opt.video_path,
opt.annotation_path,
'training',
spatial_transform=spatial_transform,
temporal_transform=temporal_transform,
target_transform=target_transform)
elif opt.dataset == 'ucf101':
opt.annotation_path = opt.annotation_path + "/train_rgb_ucf101.txt"
training_data = UCF101(
opt.video_path,
opt.annotation_path,
num_segments = opt.num_segments,
modality = opt.modality,
transform = spatial_transform)
elif opt.dataset == 'hmdb51':
opt.annotation_path = opt.annotation_path + "/train_rgb_hmdb51.txt"
training_data = HMDB51(
opt.video_path,
opt.annotation_path,
num_segments = opt.num_segments,
modality = opt.modality,
transform = spatial_transform)
elif opt.dataset == 'something':
training_data = Something(
opt.video_path,
opt.annotation_path,
'training',
spatial_transform=spatial_transform,
temporal_transform=temporal_transform,
target_transform=target_transform)
elif opt.dataset == 'fire':
opt.annotation_path = opt.annotation_path + "/train_fire.txt"
training_data = FIRE(
opt.video_path,
opt.annotation_path,
num_segments = opt.num_segments,
modality = opt.modality,
transform = spatial_transform)
return training_data
def get_validation_set(opt, spatial_transform, temporal_transform,
target_transform, image_type):
assert opt.dataset in [
'kinetics', 'activitynet', 'ucf101', 'hmdb51', 'synthetic'
]
if opt.dataset == 'kinetics':
validation_data = Kinetics(opt.video_path,
opt.annotation_path,
'validation',
opt.n_val_samples,
spatial_transform,
temporal_transform,
target_transform,
sample_duration=opt.sample_duration)
elif opt.dataset == 'activitynet':
validation_data = ActivityNet(opt.video_path,
opt.annotation_path,
'validation',
False,
opt.n_val_samples,
spatial_transform,
temporal_transform,
target_transform,
sample_duration=opt.sample_duration)
elif opt.dataset == 'ucf101':
validation_data = UCF101(opt.video_path,
opt.annotation_path,
'validation',
opt.n_val_samples,
spatial_transform,
temporal_transform,
target_transform,
sample_duration=opt.sample_duration)
elif opt.dataset == 'hmdb51':
validation_data = HMDB51(opt.video_path,
opt.annotation_path,
'validation',
opt.n_val_samples,
spatial_transform,
temporal_transform,
target_transform,
sample_duration=opt.sample_duration)
elif opt.dataset == 'synthetic':
validation_data = Synthetic(opt.video_path,
opt.annotation_path,
'validation',
opt.n_val_samples,
spatial_transform,
temporal_transform,
target_transform,
sample_duration=opt.sample_duration,
channel_fuse_step=opt.channel_fuse,
image_type=image_type)
return validation_data
def get_validation_set(config, spatial_transform, temporal_transform, target_transform):
assert config.dataset in ['kinetics', 'activitynet', 'ucf101', 'blender']
# Disable evaluation
if config.no_eval:
return None
if config.dataset == 'kinetics':
validation_data = Kinetics(
config.video_path,
config.annotation_path,
'validation',
config.num_val_samples,
spatial_transform,
temporal_transform,
target_transform,
sample_duration=config.sample_duration)
elif config.dataset == 'activitynet':
validation_data = ActivityNet(
config.video_path,
config.annotation_path,
'validation',
False,
config.num_val_samples,
spatial_transform,
temporal_transform,
target_transform,
sample_duration=config.sample_duration)
elif config.dataset == 'ucf101':
validation_data = UCF101(
config.video_path,
config.annotation_path,
'validation',
config.num_val_samples,
spatial_transform,
temporal_transform,
target_transform,
sample_duration=config.sample_duration)
elif config.dataset == 'blender':
validation_data = BlenderSyntheticDataset(
root_path=config.video_path,
subset='validation',
spatial_transform=spatial_transform,
temporal_transform=temporal_transform,
target_transform=target_transform)
return validation_data
def get_training_set(opt, spatial_transform, temporal_transform,
target_transform):
assert opt.dataset in [
'kinetics', 'jester', 'ucf101', 'egogesture', 'nvgesture'
]
if opt.train_validate:
subset = ['training', 'validation']
else:
subset = 'training'
if opt.dataset == 'kinetics':
training_data = Kinetics(opt.video_path,
opt.annotation_path,
'training',
spatial_transform=spatial_transform,
temporal_transform=temporal_transform,
target_transform=target_transform,
sample_duration=opt.sample_duration)
elif opt.dataset == 'jester':
training_data = Jester(opt.video_path,
opt.annotation_path,
'training',
spatial_transform=spatial_transform,
temporal_transform=temporal_transform,
target_transform=target_transform,
sample_duration=opt.sample_duration)
elif opt.dataset == 'ucf101':
training_data = UCF101(opt.video_path,
opt.annotation_path,
'training',
spatial_transform=spatial_transform,
temporal_transform=temporal_transform,
target_transform=target_transform,
sample_duration=opt.sample_duration)
elif opt.dataset == 'egogesture':
training_data = EgoGesture(opt.video_path,
opt.annotation_path,
subset,
spatial_transform=spatial_transform,
temporal_transform=temporal_transform,
target_transform=target_transform,
sample_duration=opt.sample_duration,
modality=opt.modality)
elif opt.dataset == 'nvgesture':
training_data = NV(opt.video_path,
opt.annotation_path,
subset,
spatial_transform=spatial_transform,
temporal_transform=temporal_transform,
target_transform=target_transform,
sample_duration=opt.sample_duration,
modality=opt.modality)
return training_data
def get_test_set(opt, spatial_transform, temporal_transform, target_transform):
assert opt.dataset in ['kinetics', 'ucf101', 'hmdb51', 'something']
assert opt.test_subset in ['val', 'test']
if opt.test_subset == 'val':
subset = 'validation'
elif opt.test_subset == 'test':
subset = 'testing'
if opt.dataset == 'kinetics':
test_data = Kinetics(opt.video_path,
opt.annotation_path,
subset,
0,
spatial_transform,
temporal_transform,
target_transform,
sample_duration=opt.sample_duration,
n_test_clips_for_each_video=opt.n_test_clips,
n_test_crops_for_each_video=opt.n_test_crops)
elif opt.dataset == 'ucf101':
test_data = UCF101(opt.video_path,
opt.annotation_path,
subset,
0,
spatial_transform,
temporal_transform,
target_transform,
sample_duration=opt.sample_duration,
n_test_clips_for_each_video=opt.n_test_clips,
n_test_crops_for_each_video=opt.n_test_crops)
elif opt.dataset == 'hmdb51':
test_data = HMDB51(opt.video_path,
opt.annotation_path,
subset,
0,
spatial_transform,
temporal_transform,
target_transform,
sample_duration=opt.sample_duration,
n_test_clips_for_each_video=opt.n_test_clips,
n_test_crops_for_each_video=opt.n_test_crops)
elif opt.dataset == 'something':
test_data = Something(opt.video_path,
opt.annotation_path,
subset,
0,
spatial_transform,
temporal_transform,
target_transform,
sample_duration=opt.sample_duration,
n_test_clips_for_each_video=opt.n_test_clips,
n_test_crops_for_each_video=opt.n_test_crops)
return test_data
def get_validation_set(opt, spatial_transform, temporal_transform,
target_transform):
assert opt.dataset in ['kinetics', 'activitynet', 'ucf101', 'hmdb51', 'moments']
if opt.dataset == 'kinetics':
validation_data = Kinetics(
opt.video_path,
opt.annotation_path,
'validation',
opt.n_val_samples,
spatial_transform,
temporal_transform,
target_transform,
sample_duration=opt.sample_duration)
elif opt.dataset == 'activitynet':
validation_data = ActivityNet(
opt.video_path,
opt.annotation_path,
'validation',
False,
opt.n_val_samples,
spatial_transform,
temporal_transform,
target_transform,
sample_duration=opt.sample_duration)
elif opt.dataset == 'ucf101':
validation_data = UCF101(
opt.video_path,
opt.annotation_path,
'validation',
opt.n_val_samples,
spatial_transform,
temporal_transform,
target_transform,
sample_duration=opt.sample_duration)
elif opt.dataset == 'hmdb51':
validation_data = HMDB51(
opt.video_path,
opt.annotation_path,
'validation',
opt.n_val_samples,
spatial_transform,
temporal_transform,
target_transform,
sample_duration=opt.sample_duration)
elif opt.dataset == "moments":
validation_data = Moments(
"/media/lili/fce9875a-a5c8-4c35-8f60-db60be29ea5d/Moments_in_Time_Raw/validation/",
opt.annotation_path,
'validation',
spatial_transform=spatial_transform,
temporal_transform=temporal_transform,
target_transform=target_transform)
return validation_data
def get_validation_set(opt, spatial_transform, temporal_transform,
target_transform):
assert opt.dataset in [
'kinetics', 'activitynet', 'ucf101', 'hmdb51', 'modelnet'
]
if opt.dataset == 'kinetics':
validation_data = Kinetics(opt.video_path,
opt.annotation_path,
'validation',
opt.n_val_samples,
spatial_transform,
temporal_transform,
target_transform,
sample_duration=opt.sample_duration)
elif opt.dataset == 'activitynet':
validation_data = ActivityNet(opt.video_path,
opt.annotation_path,
'validation',
False,
opt.n_val_samples,
spatial_transform,
temporal_transform,
target_transform,
sample_duration=opt.sample_duration)
elif opt.dataset == 'ucf101':
validation_data = UCF101(opt.video_path,
opt.annotation_path,
'validation',
opt.n_val_samples,
spatial_transform,
temporal_transform,
target_transform,
sample_duration=opt.sample_duration)
elif opt.dataset == 'hmdb51':
validation_data = HMDB51(opt.video_path,
opt.annotation_path,
'validation',
opt.n_val_samples,
spatial_transform,
temporal_transform,
target_transform,
sample_duration=opt.sample_duration)
elif opt.dataset == 'modelnet':
if opt.video_path == 'modelnet10x12':
data = np.load(opt.root_path + 'modelnet10_test_32.npz')
elif opt.video_path == 'modelnet40x12':
data = np.load(opt.root_path + 'modelnet40_test_32.npz')
validation_data = modelnet(data)
return validation_data
def get_test_set(config, spatial_transform, temporal_transform, target_transform):
assert config.dataset in ['kinetics', 'activitynet', 'ucf101', 'blender']
assert config.test_subset in ['val', 'test']
if config.test_subset == 'val':
subset = 'validation'
elif config.test_subset == 'test':
subset = 'testing'
if config.dataset == 'kinetics':
test_data = Kinetics(
config.video_path,
config.annotation_path,
subset,
0,
spatial_transform,
temporal_transform,
target_transform,
sample_duration=config.sample_duration)
elif config.dataset == 'activitynet':
test_data = ActivityNet(
config.video_path,
config.annotation_path,
subset,
True,
0,
spatial_transform,
temporal_transform,
target_transform,
sample_duration=config.sample_duration)
elif config.dataset == 'ucf101':
test_data = UCF101(
config.video_path,
config.annotation_path,
subset,
0,
spatial_transform,
temporal_transform,
target_transform,
sample_duration=config.sample_duration)
return test_data
def get_training_set(opt, spatial_transform, temporal_transform,
target_transform):
assert opt.dataset in ['kinetics', 'activitynet', 'ucf101', 'hmdb51', 'moments']
if opt.dataset == 'kinetics':
training_data = Kinetics(
opt.video_path,
opt.annotation_path,
'training',
spatial_transform=spatial_transform,
temporal_transform=temporal_transform,
target_transform=target_transform)
elif opt.dataset == 'activitynet':
training_data = ActivityNet(
opt.video_path,
opt.annotation_path,
'training',
False,
spatial_transform=spatial_transform,
temporal_transform=temporal_transform,
target_transform=target_transform)
elif opt.dataset == 'ucf101':
training_data = UCF101(
opt.video_path,
opt.annotation_path,
'training',
spatial_transform=spatial_transform,
temporal_transform=temporal_transform,
target_transform=target_transform)
elif opt.dataset == 'hmdb51':
training_data = HMDB51(
opt.video_path,
opt.annotation_path,
'training',
spatial_transform=spatial_transform,
temporal_transform=temporal_transform,
target_transform=target_transform)
elif opt.dataset == "moments":
training_data = Moments(
"/media/lili/fce9875a-a5c8-4c35-8f60-db60be29ea5d/Moments_in_Time_Raw/training/",
opt.annotation_path,
'training',
spatial_transform=spatial_transform,
temporal_transform=temporal_transform,
target_transform=target_transform)
return training_data
def get_training_set(opt, spatial_transform, temporal_transform,
target_transform, image_type):
assert opt.dataset in [
'kinetics', 'activitynet', 'ucf101', 'hmdb51', 'synthetic'
]
if opt.dataset == 'kinetics':
training_data = Kinetics(opt.video_path,
opt.annotation_path,
'training',
spatial_transform=spatial_transform,
temporal_transform=temporal_transform,
target_transform=target_transform)
elif opt.dataset == 'activitynet':
training_data = ActivityNet(opt.video_path,
opt.annotation_path,
'training',
False,
spatial_transform=spatial_transform,
temporal_transform=temporal_transform,
target_transform=target_transform)
elif opt.dataset == 'ucf101':
training_data = UCF101(opt.video_path,
opt.annotation_path,
'training',
spatial_transform=spatial_transform,
temporal_transform=temporal_transform,
target_transform=target_transform)
elif opt.dataset == 'hmdb51':
training_data = HMDB51(opt.video_path,
opt.annotation_path,
'training',
spatial_transform=spatial_transform,
temporal_transform=temporal_transform,
target_transform=target_transform)
elif opt.dataset == 'synthetic':
training_data = Synthetic(opt.video_path,
opt.annotation_path,
'training',
spatial_transform=spatial_transform,
temporal_transform=temporal_transform,
target_transform=target_transform,
channel_fuse_step=opt.channel_fuse,
image_type=image_type)
return training_data
def get_training_set(opt, spatial_transform, temporal_transform,
target_transform):
assert opt.dataset in [
'kinetics', 'activitynet', 'ucf101', 'hmdb51', 'modelnet'
]
if opt.dataset == 'kinetics':
training_data = Kinetics(
opt.video_path,
opt.annotation_path,
'training',
n_samples_for_each_video=opt.samples_per_video,
spatial_transform=spatial_transform,
temporal_transform=temporal_transform,
target_transform=target_transform)
elif opt.dataset == 'activitynet':
training_data = ActivityNet(opt.video_path,
opt.annotation_path,
'training',
False,
spatial_transform=spatial_transform,
temporal_transform=temporal_transform,
target_transform=target_transform)
elif opt.dataset == 'ucf101':
training_data = UCF101(opt.video_path,
opt.annotation_path,
'training',
spatial_transform=spatial_transform,
temporal_transform=temporal_transform,
target_transform=target_transform)
elif opt.dataset == 'hmdb51':
training_data = HMDB51(opt.video_path,
opt.annotation_path,
'training',
spatial_transform=spatial_transform,
temporal_transform=temporal_transform,
target_transform=target_transform)
elif opt.dataset == 'modelnet':
if opt.video_path == 'modelnet10x12':
data = np.load(opt.root_path + 'modelnet10_train12_32.npz')
elif opt.video_path == 'modelnet40x12':
data = np.load(opt.root_path + 'modelnet40_train12_32.npz')
#data = np.load(opt.root_path+'modelnet10_train_32.npz')
training_data = modelnet(data)
return training_data
def get_training_set(config, spatial_transform, temporal_transform, target_transform):
assert config.dataset in ['kinetics', 'activitynet', 'ucf101', 'blender']
if config.dataset == 'kinetics':
training_data = Kinetics(
config.video_path,
config.annotation_path,
'training',
spatial_transform=spatial_transform,
temporal_transform=temporal_transform,
target_transform=target_transform)
elif config.dataset == 'activitynet':
training_data = ActivityNet(
config.video_path,
config.annotation_path,
'training',
False,
spatial_transform=spatial_transform,
temporal_transform=temporal_transform,
target_transform=target_transform)
elif config.dataset == 'ucf101':
training_data = UCF101(
config.video_path,
config.annotation_path,
'training',
spatial_transform=spatial_transform,
temporal_transform=temporal_transform,
target_transform=target_transform)
elif config.dataset == 'blender':
training_data = BlenderSyntheticDataset(
root_path=config.video_path,
subset='train',
spatial_transform=spatial_transform,
temporal_transform=temporal_transform,
target_transform=target_transform)
return training_data
def get_test_set(opt, spatial_transform, temporal_transform, target_transform):
assert opt.dataset in ['kinetics', 'jester', 'ucf101', 'dad']
assert opt.test_subset in ['val', 'test']
if opt.test_subset == 'val':
subset = 'validation'
elif opt.test_subset == 'test':
subset = 'testing'
if opt.dataset == 'kinetics':
test_data = Kinetics(opt.video_path,
opt.annotation_path,
subset,
0,
spatial_transform,
temporal_transform,
target_transform,
sample_duration=opt.sample_duration)
elif opt.dataset == 'jester':
test_data = Jester(opt.video_path,
opt.annotation_path,
subset,
0,
spatial_transform,
temporal_transform,
target_transform,
sample_duration=opt.sample_duration)
elif opt.dataset == 'dad':
test_data = Dad(opt.video_path,
opt.annotation_path,
subset,
0,
spatial_transform,
temporal_transform,
target_transform,
sample_duration=opt.sample_duration)
elif opt.dataset == 'ucf101':
test_data = UCF101(opt.video_path,
opt.annotation_path,
subset,
0,
spatial_transform,
temporal_transform,
target_transform,
sample_duration=opt.sample_duration)
return test_data
def get_training_set(opt, spatial_transform, temporal_transform,
target_transform):
assert opt.dataset in [
'kinetics', 'activitynet', 'ucf101', 'hmdb51', 'moments'
]
if opt.dataset == 'kinetics':
training_data = Kinetics(opt.video_path,
opt.annotation_path,
'training',
spatial_transform=spatial_transform,
temporal_transform=temporal_transform,
target_transform=target_transform)
elif opt.dataset == 'activitynet':
training_data = ActivityNet(opt.video_path,
opt.annotation_path,
'training',
False,
spatial_transform=spatial_transform,
temporal_transform=temporal_transform,
target_transform=target_transform)
elif opt.dataset == 'ucf101':
training_data = UCF101(opt.video_path,
opt.annotation_path,
'training',
spatial_transform=spatial_transform,
temporal_transform=temporal_transform,
target_transform=target_transform)
elif opt.dataset == 'hmdb51':
training_data = HMDB51(opt.video_path,
opt.annotation_path,
'training',
spatial_transform=spatial_transform,
temporal_transform=temporal_transform,
target_transform=target_transform)
elif opt.dataset == "moments":
training_data = Moments(
"/ssd/Lili/Moments_raw_imgs/Moments_in_Time_Raw/training/",
opt.annotation_path,
'training',
spatial_transform=spatial_transform,
temporal_transform=temporal_transform,
target_transform=target_transform)
return training_data
def get_test_set(opt, spatial_transform, temporal_transform, target_transform):
assert opt.dataset in ['kinetics', 'ucf101', 'hmdb51']
assert opt.test_subset in ['val', 'test']
if opt.test_subset == 'val':
subset = 'validation'
elif opt.test_subset == 'test':
subset = 'testing'
if opt.dataset == 'kinetics':
test_data = Kinetics(opt.video_path,
opt.annotation_path,
subset,
0,
spatial_transform,
temporal_transform,
target_transform,
sample_duration=opt.sample_duration,
num_vid_samples=5)
elif opt.dataset == 'ucf101':
test_data = UCF101(opt.video_path,
opt.annotation_path,
subset,
1,
spatial_transform,
temporal_transform,
target_transform,
sample_duration=opt.sample_duration,
num_vid_samples=5)
elif opt.dataset == 'hmdb51':
test_data = HMDB51(opt.video_path,
opt.annotation_path,
subset,
1,
spatial_transform,
temporal_transform,
target_transform,
sample_duration=opt.sample_duration,
num_vid_samples=5)
return test_data
def get_test_set(opt,
spatial_transform,
temporal_transform,
target_transform,
spatio_temporal_transform=None):
assert opt.dataset in [
'kinetics',
'activitynet',
'ucf101',
'hmdb51',
'kth',
'kth2',
'sth',
'sth_init',
'gtea',
'jester',
'ucf50',
'ucf50_color',
'real',
]
assert opt.test_subset in ['val', 'test']
if opt.test_subset == 'val':
subset = 'validation'
elif opt.test_subset == 'test':
subset = 'testing'
if opt.dataset == 'kinetics':
test_data = Kinetics(opt.video_path,
opt.annotation_path,
subset,
0,
spatial_transform,
temporal_transform,
target_transform,
sample_duration=opt.sample_duration)
elif opt.dataset == 'activitynet':
test_data = ActivityNet(opt.video_path,
opt.annotation_path,
subset,
True,
0,
spatial_transform,
temporal_transform,
target_transform,
sample_duration=opt.sample_duration)
elif opt.dataset == 'ucf101':
test_data = UCF101(opt.video_path,
opt.annotation_path,
subset,
10,
spatial_transform=spatial_transform,
temporal_transform=temporal_transform,
spatio_temporal_transform=spatio_temporal_transform,
target_transform=target_transform,
sample_duration=opt.sample_duration)
elif opt.dataset == 'hmdb51':
test_data = HMDB51(opt.video_path,
opt.annotation_path,
subset,
0,
spatial_transform=spatial_transform,
temporal_transform=temporal_transform,
spatio_temporal_transform=spatio_temporal_transform,
target_transform=target_transform,
sample_duration=opt.sample_duration)
elif opt.dataset == 'kth':
test_data = KTH(opt.video_path,
opt.annotation_path,
subset,
0,
spatial_transform=spatial_transform,
temporal_transform=temporal_transform,
spatio_temporal_transform=spatio_temporal_transform,
target_transform=target_transform,
sample_duration=opt.sample_duration)
elif opt.dataset == 'kth2':
test_data = KTH2(opt.video_path,
opt.annotation_path,
subset,
0,
spatial_transform=spatial_transform,
temporal_transform=temporal_transform,
spatio_temporal_transform=spatio_temporal_transform,
target_transform=target_transform,
sample_duration=opt.sample_duration)
elif opt.dataset == 'sth':
test_data = Something2(
opt.video_path,
opt.annotation_path,
subset,
0,
spatial_transform=spatial_transform,
temporal_transform=temporal_transform,
spatio_temporal_transform=spatio_temporal_transform,
target_transform=target_transform,
sample_duration=opt.sample_duration)
elif opt.dataset == 'jester':
test_data = Jester(opt.video_path,
opt.annotation_path,
subset,
0,
spatial_transform=spatial_transform,
temporal_transform=temporal_transform,
spatio_temporal_transform=spatio_temporal_transform,
target_transform=target_transform,
sample_duration=opt.sample_duration)
elif opt.dataset == 'sth_init':
test_data = Something2Init(
opt.video_path,
opt.annotation_path,
subset,
0,
spatial_transform=spatial_transform,
temporal_transform=temporal_transform,
spatio_temporal_transform=spatio_temporal_transform,
target_transform=target_transform,
sample_duration=opt.sample_duration)
elif opt.dataset == 'gtea':
test_data = GTEA(opt.video_path,
opt.annotation_path,
subset,
0,
spatial_transform=spatial_transform,
temporal_transform=temporal_transform,
spatio_temporal_transform=spatio_temporal_transform,
target_transform=target_transform,
sample_duration=opt.sample_duration,
test_split=opt.test_split)
elif opt.dataset == 'ucf50':
test_data = UCF50(opt.video_path,
opt.annotation_path,
subset,
0,
spatial_transform=spatial_transform,
temporal_transform=temporal_transform,
spatio_temporal_transform=spatio_temporal_transform,
target_transform=target_transform,
sample_duration=opt.sample_duration,
test_split=opt.test_split)
elif opt.dataset == 'ucf50_color':
test_data = UCF50(opt.video_path,
opt.annotation_path,
subset,
0,
spatial_transform=spatial_transform,
temporal_transform=temporal_transform,
spatio_temporal_transform=spatio_temporal_transform,
target_transform=target_transform,
sample_duration=opt.sample_duration,
test_split=opt.test_split)
elif opt.dataset == 'real':
test_data = REAL(opt.video_path,
opt.annotation_path,
subset,
0,
spatial_transform=spatial_transform,
temporal_transform=temporal_transform,
spatio_temporal_transform=spatio_temporal_transform,
target_transform=target_transform,
sample_duration=opt.sample_duration)
return test_data
def get_test_set(opt, spatial_transform, temporal_transform, target_transform,
image_type):
assert opt.dataset in [
'kinetics', 'activitynet', 'ucf101', 'hmdb51', 'synthetic', 'vlog'
]
assert opt.test_subset in ['val', 'test']
if opt.test_subset == 'val':
subset = 'validation'
elif opt.test_subset == 'test':
subset = 'testing'
if opt.dataset == 'kinetics':
test_data = Kinetics(opt.video_path,
opt.annotation_path,
subset,
0,
spatial_transform,
temporal_transform,
target_transform,
sample_duration=opt.sample_duration)
elif opt.dataset == 'activitynet':
test_data = ActivityNet(opt.video_path,
opt.annotation_path,
subset,
True,
0,
spatial_transform,
temporal_transform,
target_transform,
sample_duration=opt.sample_duration)
elif opt.dataset == 'ucf101':
test_data = UCF101(opt.video_path,
opt.annotation_path,
subset,
0,
spatial_transform,
temporal_transform,
target_transform,
sample_duration=opt.sample_duration)
elif opt.dataset == 'hmdb51':
test_data = HMDB51(opt.video_path,
opt.annotation_path,
subset,
0,
spatial_transform,
temporal_transform,
target_transform,
sample_duration=opt.sample_duration)
elif opt.dataset == 'synthetic':
test_data = Synthetic(opt.video_path,
opt.annotation_path,
subset,
1,
spatial_transform,
temporal_transform,
target_transform,
sample_duration=opt.sample_duration,
channel_fuse_step=opt.channel_fuse,
image_type=image_type)
elif opt.dataset == 'vlog':
test_data = Vlog(opt.video_path,
opt.annotation_path,
subset,
1,
spatial_transform,
temporal_transform,
target_transform,
sample_duration=opt.sample_duration,
image_type=image_type)
return test_data
def get_test_set(opt,
spatial_transform,
temporal_transform,
target_transform,
score_sens_mode=False,
score_inf_mode=False,
inner_temp_transform=None):
assert opt.dataset in [
'kinetics', 'activitynet', 'ucf101', 'hmdb51', 'something'
]
assert opt.test_subset in ['val', 'test']
if opt.test_subset == 'val':
subset = 'validation'
elif opt.test_subset == 'test':
subset = 'testing'
if opt.dataset == 'kinetics':
test_data = Kinetics(opt.video_path,
opt.annotation_path,
subset,
0,
spatial_transform,
temporal_transform,
target_transform,
sample_duration=opt.sample_duration,
sample_stride=opt.sample_stride)
elif opt.dataset == 'activitynet':
test_data = ActivityNet(opt.video_path,
opt.annotation_path,
subset,
0,
spatial_transform,
temporal_transform,
target_transform,
sample_duration=opt.sample_duration)
elif opt.dataset == 'ucf101':
test_data = UCF101(
opt.video_path,
opt.annotation_path,
subset,
# 0,
1, # sample 1 clip each video
spatial_transform,
temporal_transform,
target_transform,
sample_duration=opt.sample_duration,
score_sens_mode=score_sens_mode,
score_inf_mode=score_inf_mode)
elif opt.dataset == 'hmdb51':
test_data = HMDB51(opt.video_path,
opt.annotation_path,
subset,
0,
spatial_transform,
temporal_transform,
target_transform,
sample_duration=opt.sample_duration)
elif opt.dataset == 'something':
test_data = Something(
opt.video_path,
opt.annotation_path,
subset,
# 0,
1, # sample 1 clip each video
spatial_transform,
temporal_transform,
target_transform,
sample_duration=opt.sample_duration,
score_sens_mode=score_sens_mode,
score_inf_mode=score_inf_mode,
inner_temp_transform=inner_temp_transform)
return test_data
def get_test_set(opt, spatial_transform, temporal_transform, target_transform):
assert opt.dataset in ['kinetics', 'activitynet', 'ucf101', 'hmdb51','something','fire']
assert opt.test_subset in ['val', 'test']
if opt.test_subset == 'val':
subset = 'validation'
elif opt.test_subset == 'test':
subset = 'testing'
if opt.dataset == 'kinetics':
test_data = Kinetics(
opt.video_path,
opt.annotation_path,
subset,
0,
spatial_transform,
temporal_transform,
target_transform,
sample_duration=opt.sample_duration,
sample_stride=opt.sample_stride)
elif opt.dataset == 'activitynet':
test_data = ActivityNet(
opt.video_path,
opt.annotation_path,
subset,
0,
spatial_transform,
temporal_transform,
target_transform,
sample_duration=opt.sample_duration)
elif opt.dataset == 'ucf101':
opt.annotation_path = opt.annotation_path + "/test_rgb_ucf101.txt"
test_data = UCF101(
opt.video_path,
opt.annotation_path,
num_segments = opt.num_segments,
modality = opt.modality,
transform = spatial_transform,
test_mode = True)
elif opt.dataset == 'hmdb51':
test_data = HMDB51(
opt.video_path,
opt.annotation_path,
subset,
0,
spatial_transform,
temporal_transform,
target_transform,
sample_duration=opt.sample_duration)
elif opt.dataset == 'something':
test_data = Something(
opt.video_path,
opt.annotation_path,
subset,
0,
spatial_transform,
temporal_transform,
target_transform,
sample_duration=opt.sample_duration)
elif opt.dataset == 'fire':
opt.annotation_path = "/DATACENTER2/wxy/workspace/senet-3d/datasets/txt/test_fire.txt"
test_data = FIRE(
opt.video_path,
opt.annotation_path,
num_segments = opt.num_segments,
modality = opt.modality,
transform = spatial_transform,
test_mode=True,
test_idx=opt.test_idx)
return test_data
def get_validation_set(opt, spatial_transform, temporal_transform,
target_transform):
assert opt.dataset in ['kinetics', 'kinetics_adv', 'kinetics_bkgmsk', 'kinetics_human_msk', 'kinetics_adv_msk', 'activitynet', 'ucf101', 'hmdb51', 'diving48']
if opt.dataset == 'kinetics':
validation_data = Kinetics(
opt.video_path+'/val',
opt.annotation_path,
'validation',
opt.n_val_samples,
spatial_transform,
temporal_transform,
target_transform,
sample_duration=opt.sample_duration)
elif opt.dataset == 'kinetics_adv':
validation_data = Kinetics_adv(
opt.video_path+'/val',
opt.annotation_path,
'validation',
opt.n_val_samples,
spatial_transform,
temporal_transform,
target_transform,
sample_duration=opt.sample_duration,
place_pred_path=opt.place_pred_path,
is_place_soft_label=opt.is_place_soft)
elif opt.dataset == 'kinetics_bkgmsk':
validation_data = Kinetics_bkgmsk(
opt.video_path+'/val',
opt.annotation_path,
'validation',
opt.n_val_samples,
spatial_transform,
temporal_transform,
target_transform,
sample_duration=opt.sample_duration,
detection_path=opt.human_dets_path,
mask_ratio=opt.mask_ratio)
elif opt.dataset == 'kinetics_adv_msk':
validation_data_1 = Kinetics_adv(
opt.video_path+'/val',
opt.annotation_path,
'validation',
opt.n_val_samples,
spatial_transform,
temporal_transform,
target_transform,
sample_duration=opt.sample_duration,
place_pred_path=opt.place_pred_path,
is_place_soft_label=opt.is_place_soft)
validation_data_2 = Kinetics_human_msk(
opt.video_path+'/val',
opt.annotation_path,
'validation',
opt.n_val_samples,
spatial_transform,
temporal_transform,
target_transform,
sample_duration=opt.sample_duration,
detection_path=opt.human_dets_path,
mask_ratio=opt.mask_ratio)
validation_data = [validation_data_1, validation_data_2]
elif opt.dataset == 'activitynet':
validation_data = ActivityNet(
opt.video_path,
opt.annotation_path,
'validation',
False,
opt.n_val_samples,
spatial_transform,
temporal_transform,
target_transform,
sample_duration=opt.sample_duration)
elif opt.dataset == 'ucf101':
validation_data = UCF101(
opt.video_path,
opt.annotation_path,
'validation',
opt.n_val_samples,
spatial_transform,
temporal_transform,
target_transform,
sample_duration=opt.sample_duration,
vis=opt.vis)
elif opt.dataset == 'hmdb51':
validation_data = HMDB51(
opt.video_path,
opt.annotation_path,
'validation',
opt.n_val_samples,
spatial_transform,
temporal_transform,
target_transform,
sample_duration=opt.sample_duration,
vis=opt.vis)
elif opt.dataset == 'diving48':
validation_data = Diving48(
opt.video_path,
opt.annotation_path,
'validation',
opt.n_val_samples,
spatial_transform,
temporal_transform,
target_transform,
sample_duration=opt.sample_duration,
vis=opt.vis)
return validation_data
def get_training_set(opt, spatial_transform, temporal_transform,
target_transform):
assert opt.dataset in ['kinetics', 'kinetics_adv', 'kinetics_bkgmsk', 'kinetics_adv_msk', 'activitynet', 'ucf101', 'hmdb51', 'diving48']
if opt.dataset == 'kinetics':
training_data = Kinetics(
opt.video_path+'/train',
opt.annotation_path,
'training',
spatial_transform=spatial_transform,
temporal_transform=temporal_transform,
target_transform=target_transform)
elif opt.dataset == 'kinetics_adv':
training_data = Kinetics_adv(
opt.video_path+'/train',
opt.annotation_path,
'training',
spatial_transform=spatial_transform,
temporal_transform=temporal_transform,
target_transform=target_transform,
place_pred_path=opt.place_pred_path,
is_place_soft_label=opt.is_place_soft)
elif opt.dataset == 'kinetics_bkgmsk':
training_data = Kinetics_bkgmsk(
opt.video_path+'/train',
opt.annotation_path,
'training',
spatial_transform=spatial_transform,
temporal_transform=temporal_transform,
target_transform=target_transform,
detection_path=opt.human_dets_path,
mask_ratio=opt.mask_ratio)
elif opt.dataset == 'kinetics_adv_msk':
training_data_1 = Kinetics_adv(
opt.video_path+'/train',
opt.annotation_path,
'training',
spatial_transform=spatial_transform,
temporal_transform=temporal_transform,
target_transform=target_transform,
place_pred_path=opt.place_pred_path,
is_place_soft_label=opt.is_place_soft)
training_data_2 = Kinetics_human_msk(
opt.video_path+'/train',
opt.annotation_path,
'training',
spatial_transform=spatial_transform,
temporal_transform=temporal_transform,
target_transform=target_transform,
detection_path=opt.human_dets_path,
mask_ratio=opt.mask_ratio)
training_data = [training_data_1, training_data_2]
elif opt.dataset == 'activitynet':
training_data = ActivityNet(
opt.video_path,
opt.annotation_path,
'training',
False,
spatial_transform=spatial_transform,
temporal_transform=temporal_transform,
target_transform=target_transform)
elif opt.dataset == 'ucf101':
training_data = UCF101(
opt.video_path,
opt.annotation_path,
'training',
spatial_transform=spatial_transform,
temporal_transform=temporal_transform,
target_transform=target_transform)
elif opt.dataset == 'hmdb51':
training_data = HMDB51(
opt.video_path,
opt.annotation_path,
'training',
spatial_transform=spatial_transform,
temporal_transform=temporal_transform,
target_transform=target_transform)
elif opt.dataset == 'diving48':
training_data = Diving48(
opt.video_path,
opt.annotation_path,
'training',
spatial_transform=spatial_transform,
temporal_transform=temporal_transform,
target_transform=target_transform)
return training_data
def get_validation_set(opt, spatial_transform, temporal_transform,
target_transform):
assert opt.dataset in ['kinetics', 'activitynet', 'ucf101', 'hmdb51','something','fire']
if opt.dataset == 'kinetics':
validation_data = Kinetics(
opt.video_path+"/val_256",
opt.annotation_path,
'validation',
opt.n_val_samples,
spatial_transform,
temporal_transform,
target_transform,
sample_duration=opt.sample_duration)
elif opt.dataset == 'activitynet':
validation_data = ActivityNet(
opt.video_path,
opt.annotation_path,
'validation',
opt.n_val_samples,
spatial_transform,
temporal_transform,
target_transform,
sample_duration=opt.sample_duration)
elif opt.dataset == 'ucf101':
opt.annotation_path = opt.annotation_path.replace("train","test")
#opt.annotation_path = opt.annotation_path + "/test_rgb_ucf101.txt"
validation_data = UCF101(
opt.video_path,
opt.annotation_path,
num_segments = opt.num_segments,
modality = opt.modality,
transform = spatial_transform,
test_mode = True)
elif opt.dataset == 'hmdb51':
opt.annotation_path = opt.annotation_path.replace("train","val")
validation_data = HMDB51(
opt.video_path,
opt.annotation_path,
num_segments = opt.num_segments,
modality = opt.modality,
transform = spatial_transform)
elif opt.dataset == 'fire':
opt.annotation_path = opt.annotation_path.replace("train","test")
validation_data = FIRE(
opt.video_path,
opt.annotation_path,
num_segments = opt.num_segments,
modality = opt.modality,
transform = spatial_transform)
elif opt.dataset == 'something':
validation_data = Something(
opt.video_path,
opt.annotation_path,
'validation',
opt.n_val_samples,
spatial_transform,
temporal_transform,
target_transform,
sample_duration=opt.sample_duration)
return validation_data
