Python varLengthFeatの例

コード例 #1

ファイル: output_extract.py プロジェクト: taalua/SpeakerVerifiaction-pytorch

np.random.seed(args.seed)
torch.manual_seed(args.seed)
torch.multiprocessing.set_sharing_strategy('file_system')

if args.cuda:
    cudnn.benchmark = True

# Define visulaize SummaryWriter instance
kwargs = {'num_workers': args.nj, 'pin_memory': False} if args.cuda else {}
l2_dist = nn.CosineSimilarity(
    dim=1, eps=1e-6) if args.cos_sim else PairwiseDistance(2)

if args.input_length == 'var':
    transform = transforms.Compose([
        # concateinputfromMFB(num_frames=c.NUM_FRAMES_SPECT, remove_vad=False),
        varLengthFeat(remove_vad=args.remove_vad),
        to2tensor()
    ])
    transform_T = transforms.Compose([
        # concateinputfromMFB(num_frames=c.NUM_FRAMES_SPECT, input_per_file=args.test_input_per_file, remove_vad=False),
        varLengthFeat(remove_vad=args.remove_vad),
        to2tensor()
    ])
elif args.input_length == 'fix':
    transform = transforms.Compose(
        [concateinputfromMFB(remove_vad=args.remove_vad),
         to2tensor()])
    transform_T = transforms.Compose([
        concateinputfromMFB(input_per_file=args.test_input_per_file,
                            remove_vad=args.remove_vad),
        to2tensor()

コード例 #2

ファイル: train_asoftmax_sures10.py プロジェクト: taalua/SpeakerVerifiaction-pytorch

#     num_pro = 1.
#     for datum in voxceleb:
#         # Data/voxceleb1/
#         # /data/voxceleb/voxceleb1_wav/
#         GenerateSpect(wav_path='/data/voxceleb/voxceleb1_wav/' + datum['filename']+'.wav',
#                       write_path=args.dataroot +'/spectrogram/voxceleb1_wav/' + datum['filename']+'.npy')
#         print('\rprocessed {:2f}% {}/{}.'.format(num_pro/len(voxceleb), num_pro, len(voxceleb)), end='\r')
#         num_pro += 1
#     print('\nComputing Spectrograms success!')
#     exit(1)

if args.acoustic_feature == 'fbank':
    transform = transforms.Compose([
        # concateinputfromMFB(),
        # truncatedinputfromMFB(),
        varLengthFeat(),
        totensor()
    ])
    transform_T = transforms.Compose([
        # truncatedinputfromMFB(input_per_file=args.test_input_per_file),
        concateinputfromMFB(input_per_file=args.test_input_per_file),
        totensor()
    ])
    file_loader = read_MFB

elif args.acoustic_feature == 'spectrogram':
    # Start from spectrogram
    transform = transforms.Compose([truncatedinputfromMFB(), totensor()])
    transform_T = transforms.Compose([
        truncatedinputfromMFB(input_per_file=args.test_input_per_file),
        totensor()

コード例 #3

np.random.seed(args.seed)
torch.manual_seed(args.seed)

if args.cuda:
    cudnn.benchmark = True

# create logger
# Define visulaize SummaryWriter instance

kwargs = {'num_workers': 12, 'pin_memory': True} if args.cuda else {}

l2_dist = nn.CosineSimilarity(
    dim=1, eps=1e-6) if args.cos_sim else PairwiseDistance(2)

if args.acoustic_feature == 'fbank':
    transform = transforms.Compose([varLengthFeat(), totensor()])
    transform_T = transforms.Compose([varLengthFeat(), totensor()])
    file_loader = read_mat
else:
    transform = transforms.Compose([
        truncatedinput(),
        toMFB(),
        totensor(),
        # tonormal()
    ])
    file_loader = read_audio

# pdb.set_trace()
train_dir = KaldiExtractDataset(dir=args.train_dir,
                                loader=file_loader,
                                transform=transform)

コード例 #4

ファイル: train_exres_var.py プロジェクト: Wenhao-Yang/SpeakerVerifiaction-pytorch

opt_kwargs = {
    'lr': args.lr,
    'lr_decay': args.lr_decay,
    'weight_decay': args.weight_decay,
    'dampening': args.dampening,
    'momentum': args.momentum
}

l2_dist = nn.CosineSimilarity(
    dim=1, eps=1e-6) if args.cos_sim else PairwiseDistance(2)

if args.acoustic_feature == 'fbank':
    transform = transforms.Compose([
        # concateinputfromMFB(num_frames=c.NUM_FRAMES_SPECT, remove_vad=False),
        varLengthFeat(remove_vad=True),
        to2tensor()
    ])
    transform_T = transforms.Compose([
        # concateinputfromMFB(num_frames=c.NUM_FRAMES_SPECT, input_per_file=args.test_input_per_file, remove_vad=False),
        varLengthFeat(remove_vad=True),
        to2tensor(),
        # tonormal()
    ])
    transform_V = transforms.Compose(
        [varLengthFeat(remove_vad=args.remove_vad),
         to2tensor()])

else:
    transform = transforms.Compose([
        truncatedinput(),

コード例 #5

opt_kwargs = {
    'lr': args.lr,
    'lr_decay': args.lr_decay,
    'weight_decay': args.weight_decay,
    'dampening': args.dampening,
    'momentum': args.momentum
}

l2_dist = nn.CosineSimilarity(
    dim=1, eps=1e-6) if args.cos_sim else PairwiseDistance(2)

if args.acoustic_feature == 'fbank':
    transform = transforms.Compose([
        # concateinputfromMFB(num_frames=c.NUM_FRAMES_SPECT, remove_vad=False),
        varLengthFeat(remove_vad=True),
        to2tensor()
    ])
    transform_T = transforms.Compose([
        # concateinputfromMFB(num_frames=c.NUM_FRAMES_SPECT, input_per_file=args.test_input_per_file, remove_vad=False),
        varLengthFeat(remove_vad=True),
        to2tensor(),
        # tonormal()
    ])

else:
    transform = transforms.Compose([
        truncatedinput(),
        toMFB(),
        totensor(),
        # tonormal()