if args.cuda:
print('Using CUDA with {0} GPUs'.format(torch.cuda.device_count()))
speech_net = torch.nn.DataParallel(speech_net).cuda()
# model = speech_net.cuda()
# define optimizer
if args.opt.lower() == 'adam':
optimizer = optim.Adam(speech_net.parameters(), lr=args.lr)
elif args.opt.lower() == 'sgd':
optimizer = optim.SGD(speech_net.parameters(), lr=args.lr, momentum=args.momentum)
else:
optimizer = optim.SGD(speech_net.parameters(), lr=args.lr, momentum=args.momentum)
f_train = np.loadtxt(args.train_data, dtype='str', delimiter='\t')
f_train = f_train.tolist()
train_dataset = Datasets.PSCDataset(classes_file = args.classes_file, data_list = f_train, max_audio_len = args.audio_len,
noise_type = args.noise_type, noise_amp = args.noise_amp)
f_val = np.loadtxt(args.val_data, dtype='str', delimiter='\t')
f_val = f_val.tolist()
val_dataset = Datasets.PSCDataset(classes_file = args.classes_file, data_list = f_val, max_audio_len = args.audio_len,
noise_type = args.noise_type, noise_amp = args.noise_amp)
train_loader = torch.utils.data.DataLoader(
train_dataset, batch_size=args.batch_size, shuffle=True,
num_workers=10, pin_memory=args.cuda, sampler = None)
val_loader = torch.utils.data.DataLoader(
val_dataset, batch_size=args.batch_size, shuffle=True,
num_workers=10, pin_memory=args.cuda, sampler=None)
best_valid_loss = np.inf
args = parser.parse_args()
args.cuda = args.cuda and torch.cuda.is_available()
torch.manual_seed(args.seed)
if args.cuda:
torch.cuda.manual_seed(args.seed)
model = psc_model.load_model(args.model)
if args.cuda:
print('Using CUDA with {0} GPUs'.format(torch.cuda.device_count()))
model = torch.nn.DataParallel(model).cuda()
f_test = np.loadtxt(args.test_data, dtype='str', delimiter='\t')
f_test = f_test.tolist()
test_dataset = Datasets.PSCDataset(classes_file=args.classes_file, data_list=f_test, max_audio_len = args.wav_len,
noise_type = args.noise_type, noise_amp = args.noise_amp)
test_loader = torch.utils.data.DataLoader(
test_dataset, batch_size=args.batch_size, shuffle=True, num_workers=20, pin_memory=args.cuda, sampler=None)
range_split = args.theta_range.split('_')
start_theta = float(range_split[0])
end_theta = float(range_split[1])
step_theta = float(range_split[2])
atwv_dict = {} #dict: theta: atwv val
for theta in np.arange(start_theta, end_theta, step_theta):
acc = train_psc.test_acc(test_loader, model, args.wav_len, 1.0, theta, args.cuda)
atwv = train_psc.keyword_spotting_test_mtwv(test_loader, model, args.wav_len, 1.0, theta, args.cuda)
atwv_dict[theta] = atwv
