def get_test_set(opt, spatial_transform, temporal_transform, target_transform): assert opt.dataset in [ 'kinetics', 'activitynet', 'ucf101', 'hmdb51', 'own' ] 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 == 'own': 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_validation_set(opt, spatial_transform, temporal_transform, target_transform): assert opt.dataset in [ 'kinetics', 'activitynet', 'ucf101', 'hmdb51', 'own' ] 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 == 'own': validation_data = UCF101(opt.video_path, 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', '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(config, spatial_transform, temporal_transform, target_transform): assert config.dataset in ['ucf101', 'hmdb51'] # 设置为不进行验证状态 if config.no_eval: return None if 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 == 'hmdb51': validation_data = HMDB51( config.video_path, config.annotation_path, 'validation', config.num_val_samples, spatial_transform, temporal_transform, target_transform, sample_duration=config.sample_duration) 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_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', '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, 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_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', '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): 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_training_set(opt, spatial_transform, temporal_transform, target_transform): training_data = UCF101(opt.video_path, opt.annotation_path, 'training', spatial_transform=spatial_transform, temporal_transform=temporal_transform, target_transform=target_transform, debug=opt.debug) 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_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_training_set(opt, spatial_transform, temporal_transform, target_transform): if 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) return training_data
def get_validation_set(opt, spatial_transform, temporal_transform, target_transform): if 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): 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(opt, spatial_transform, temporal_transform, target_transform): subset = 'validation' if opt.dataset == 'ucf101': test_data = UCF101(opt.video_path, opt.annotation_path, 'validation', 0, spatial_transform, temporal_transform, target_transform, sample_duration=opt.sample_duration) return test_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): 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(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', '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_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(config, spatial_transform, temporal_transform, target_transform): assert config.dataset in ['ucf101', 'hmdb51'] if 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 == 'hmdb51': training_data = HMDB51( config.video_path, config.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', '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', '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