if args.mfb:
transform = transforms.Compose([
concateinputfromMFB(),
# truncatedinputfromMFB(),
totensor()
])
transform_T = transforms.Compose([
concateinputfromMFB(input_per_file=args.test_input_per_file),
# truncatedinputfromMFB(input_per_file=args.test_input_per_file),
totensor()
])
file_loader = read_MFB
else:
transform = transforms.Compose([
truncatedinput(),
toMFB(),
totensor(),
# tonormal()
])
file_loader = read_audio
train_dir = ClassificationDataset(voxceleb=voxceleb_dev,
dir=args.dataroot,
loader=file_loader,
transform=transform)
test_dir = VoxcelebTestset(dir=args.test_dataroot,
pairs_path=args.test_pairs_path,
loader=file_loader,
transform=transform_T)
del voxceleb
transform = transforms.Compose([
# concateinputfromMFB(num_frames=c.NUM_FRAMES_SPECT, remove_vad=True),
varLengthFeat(remove_vad=args.remove_vad),
to2tensor(),
tonormal()
])
transform_T = transforms.Compose([
# concateinputfromMFB(num_frames=c.NUM_FRAMES_SPECT, input_per_file=args.test_input_per_file, remove_vad=True),
varLengthFeat(remove_vad=args.remove_vad),
to2tensor(),
tonormal()
])
else:
transform = transforms.Compose(
[truncatedinput(), toMFB(),
totensor(), tonormal()])
file_loader = read_audio
# pdb.set_trace()
file_loader = read_mat
train_dir = ScriptTrainDataset(dir=args.train_dir,
samples_per_speaker=args.input_per_spks,
loader=file_loader,
transform=transform,
num_valid=args.num_valid)
test_dir = ScriptTestDataset(dir=args.test_dir,
loader=file_loader,
transform=transform_T)
if len(test_dir) < args.veri_pairs:
