proj_size=train_dataset.n_speakers
if args.softmax != 'none' or args.pretrain else 0,
ncoef=args.ncoef,
sm_type=args.softmax,
delta=args.delta)
elif args.model == 'TDNN':
model = model_.TDNN(n_z=args.latent_size,
proj_size=train_dataset.n_speakers
if args.softmax != 'none' or args.pretrain else 0,
ncoef=args.ncoef,
sm_type=args.softmax,
delta=args.delta)
elif args.model == 'TDNN_att':
model = model_.TDNN_att(n_z=args.latent_size,
proj_size=train_dataset.n_speakers
if args.softmax != 'none' or args.pretrain else 0,
ncoef=args.ncoef,
sm_type=args.softmax,
delta=args.delta)
elif args.model == 'TDNN_multihead':
model = model_.TDNN_multihead(
n_z=args.latent_size,
proj_size=train_dataset.n_speakers
if args.softmax != 'none' or args.pretrain else 0,
ncoef=args.ncoef,
sm_type=args.softmax,
delta=args.delta)
elif args.model == 'TDNN_lstm':
model = model_.TDNN_lstm(n_z=args.latent_size,
proj_size=train_dataset.n_speakers
if args.softmax != 'none' or args.pretrain else 0,
ncoef=args.ncoef,
proj_size=0,
ncoef=args.ncoef,
delta=args.delta)
elif args.model == 'resnet_2d':
model = model_.ResNet_2d(n_z=args.latent_size,
proj_size=0,
ncoef=args.ncoef,
delta=args.delta)
elif args.model == 'TDNN':
model = model_.TDNN(n_z=args.latent_size,
proj_size=0,
ncoef=args.ncoef,
delta=args.delta)
elif args.model == 'TDNN_att':
model = model_.TDNN_att(n_z=args.latent_size,
proj_size=0,
ncoef=args.ncoef,
delta=args.delta)
elif args.model == 'TDNN_multihead':
model = model_.TDNN_multihead(n_z=args.latent_size,
proj_size=0,
ncoef=args.ncoef,
delta=args.delta)
elif args.model == 'TDNN_lstm':
model = model_.TDNN_lstm(n_z=args.latent_size,
proj_size=0,
ncoef=args.ncoef,
delta=args.delta)
elif args.model == 'TDNN_aspp':
model = model_.TDNN_aspp(n_z=args.latent_size,
proj_size=0,
ncoef=args.ncoef,
elif args.model == 'TDNN':
model = model_.TDNN(n_z=args.latent_size,
proj_size=train_dataset.n_speakers,
ncoef=args.ncoef,
sm_type=args.softmax,
delta=args.delta)
elif args.model == 'TDNN_logpool':
model = model_.TDNN_logpool(n_z=args.latent_size,
proj_size=train_dataset.n_speakers,
ncoef=args.ncoef,
sm_type=args.softmax,
delta=args.delta)
elif args.model == 'TDNN_att':
model = model_.TDNN_att(n_z=args.latent_size,
proj_size=train_dataset.n_speakers,
ncoef=args.ncoef,
sm_type=args.softmax,
delta=args.delta)
elif args.model == 'TDNN_multihead':
model = model_.TDNN_multihead(n_z=args.latent_size,
proj_size=train_dataset.n_speakers,
ncoef=args.ncoef,
sm_type=args.softmax,
delta=args.delta)
elif args.model == 'TDNN_lstm':
model = model_.TDNN_lstm(n_z=args.latent_size,
proj_size=train_dataset.n_speakers,
ncoef=args.ncoef,
sm_type=args.softmax,
delta=args.delta)
elif args.model == 'TDNN_aspp':
print('resnet_2d', mu.size(), emb.size(), out.size())
if args.model == 'TDNN' or args.model == 'all':
batch = torch.rand(3, 3 if args.delta else 1, args.ncoef, 200)
model = model_.TDNN(n_z=args.latent_size,
ncoef=args.ncoef,
delta=args.delta,
proj_size=10,
sm_type='softmax')
mu, emb = model.forward(batch)
out = model.out_proj(mu, torch.ones(mu.size(0)))
print('TDNN', mu.size(), emb.size(), out.size())
if args.model == 'TDNN_att' or args.model == 'all':
batch = torch.rand(3, 3 if args.delta else 1, args.ncoef, 200)
model = model_.TDNN_att(n_z=args.latent_size,
ncoef=args.ncoef,
delta=args.delta,
proj_size=10,
sm_type='softmax')
mu, emb = model.forward(batch)
out = model.out_proj(mu, torch.ones(mu.size(0)))
print('TDNN_att', mu.size(), emb.size(), out.size())
if args.model == 'TDNN_multihead' or args.model == 'all':
batch = torch.rand(3, 3 if args.delta else 1, args.ncoef, 200)
model = model_.TDNN_multihead(n_z=args.latent_size,
ncoef=args.ncoef,
delta=args.delta,
proj_size=10,
sm_type='softmax')
mu, emb = model.forward(batch)
out = model.out_proj(mu, torch.ones(mu.size(0)))
print('TDNN_multihead', mu.size(), emb.size(), out.size())
def train(lr, l2, max_gnorm, momentum, margin, lambda_, swap, latent_size, n_frames, model, ncoef, epochs, batch_size, valid_batch_size, n_workers, cuda, train_hdf_file, valid_hdf_file, cp_path, softmax, delta, logdir):
if cuda:
device=get_freer_gpu()
if args.model == 'resnet_qrnn':
import cupy
cupy.cuda.Device(int(str(device).split(':')[-1])).use()
cp_name = get_file_name(cp_path)
if args.logdir:
from torch.utils.tensorboard import SummaryWriter
writer = SummaryWriter(log_dir=logdir+cp_name, comment=args.model, purge_step=True)
else:
writer = None
train_dataset = Loader(hdf5_name = train_hdf_file, max_nb_frames = int(n_frames), delta = delta)
train_loader = torch.utils.data.DataLoader(train_dataset, batch_size=batch_size, shuffle=True, num_workers=n.workers, worker_init_fn=set_np_randomseed)
valid_dataset = Loader_valid(hdf5_name = valid_hdf_file, max_nb_frames = int(n_frames), delta = delta)
valid_loader = torch.utils.data.DataLoader(valid_dataset, batch_size=valid_batch_size, shuffle=True, num_workers=n_workers, worker_init_fn=set_np_randomseed)
if model == 'resnet_mfcc':
model=model_.ResNet_mfcc(n_z=int(latent_size), proj_size=train_dataset.n_speakers, ncoef=ncoef, sm_type=softmax, delta=delta)
elif model == 'resnet_34':
model=model_.ResNet_34(n_z=int(latent_size), proj_size=train_dataset.n_speakers, ncoef=ncoef, sm_type=softmax, delta=delta)
elif model == 'resnet_lstm':
model=model_.ResNet_lstm(n_z=int(latent_size), proj_size=train_dataset.n_speakers, ncoef=ncoef, sm_type=softmax, delta=delta)
elif model == 'resnet_qrnn':
model=model_.ResNet_qrnn(n_z=int(latent_size), proj_size=train_dataset.n_speakers, ncoef=ncoef, sm_type=softmax, delta=delta)
elif model == 'resnet_stats':
model=model_.ResNet_stats(n_z=int(latent_size), proj_size=train_dataset.n_speakers, ncoef=ncoef, sm_type=softmax, delta=delta)
elif args.model == 'resnet_large':
model = model_.ResNet_large(n_z=int(latent_size), proj_size=train_dataset.n_speakers, ncoef=args.ncoef, sm_type=softmax, delta=delta)
elif args.model == 'resnet_small':
model = model_.ResNet_small(n_z=int(latent_size), proj_size=train_dataset.n_speakers, ncoef=args.ncoef, sm_type=softmax, delta=delta)
elif args.model == 'resnet_2d':
model = model_.ResNet_2d(n_z=int(latent_size), proj_size=train_dataset.n_speakers, ncoef=args.ncoef, sm_type=softmax, delta=delta)
elif args.model == 'TDNN':
model = model_.TDNN(n_z=int(latent_size), proj_size=train_dataset.n_speakers, ncoef=args.ncoef, sm_type=softmax, delta=delta)
elif args.model == 'TDNN_att':
model = model_.TDNN_att(n_z=int(latent_size), proj_size=train_dataset.n_speakers, ncoef=args.ncoef, sm_type=softmax, delta=delta)
elif args.model == 'TDNN_multihead':
model = model_.TDNN_multihead(n_z=int(latent_size), proj_size=train_dataset.n_speakers, ncoef=args.ncoef, sm_type=softmax, delta=delta)
elif args.model == 'TDNN_lstm':
model = model_.TDNN_lstm(n_z=int(latent_size), proj_size=train_dataset.n_speakers, ncoef=args.ncoef, sm_type=softmax, delta=delta)
elif args.model == 'TDNN_aspp':
model = model_.TDNN_aspp(n_z=int(latent_size), proj_size=train_dataset.n_speakers, ncoef=args.ncoef, sm_type=softmax, delta=delta)
elif args.model == 'TDNN_mod':
model = model_.TDNN_mod(n_z=int(latent_size), proj_size=train_dataset.n_speakers, ncoef=args.ncoef, sm_type=softmax, delta=delta)
elif args.model == 'TDNN_multipool':
model = model_.TDNN_multipool(n_z=int(latent_size), proj_size=train_dataset.n_speakers, ncoef=args.ncoef, sm_type=softmax, delta=delta)
elif args.model == 'transformer':
model = model_.transformer_enc(n_z=int(latent_size), proj_size=train_dataset.n_speakers, ncoef=args.ncoef, sm_type=softmax, delta=delta)
if cuda:
model=model.to(device)
else:
device=None
optimizer=optim.SGD(model.parameters(), lr=lr, momentum=momentum, weight_decay=l2)
trainer=TrainLoop(model, optimizer, train_loader, valid_loader, max_gnorm=max_gnorm, margin=margin, lambda_=lambda_, verbose=-1, device=device, cp_name=cp_name, save_cp=True, checkpoint_path=cp_path, swap=swap, softmax=True, pretrain=False, mining=True, cuda=cuda, logger=writer)
return trainer.train(n_epochs=epochs)
