def test_FFTNetModelStep(self):
print(" ---- Test FFTNetModel step forward ----")
net = FFTNetModel(hid_channels=256, out_channels=256, n_layers=11, cond_channels=80)
time_start = time.time()
for i in range(1024):
x = torch.rand(1, 1, 1)
cx = torch.rand(1, 80, 1)
out = net.forward_step(x, cx)
time_avg = (time.time() - time_start) / 1024
print("> Avg time per step inference on CPU: {}".format(time_avg))
assert abs(net.layers[0].buffer.queue1.sum().item()) > 0
assert abs(net.layers[0].buffer.queue2.sum().item()) == 0
# on GPU
net = FFTNetModel(hid_channels=256, out_channels=256, n_layers=11, cond_channels=80)
net.cuda()
time_start = time.time()
for i in range(1024):
x = torch.rand(1, 1, 1)
cx = torch.rand(1, 80, 1)
out = net.forward_step(x.cuda(), cx.cuda())
time_avg = (time.time() - time_start) / 1024
print("> Avg time per step inference on GPU: {}".format(time_avg))
assert abs(net.layers[0].buffer.queue1.sum().item()) > 0
assert abs(net.layers[0].buffer.queue2.sum().item()) == 0
# check the second queue
net = FFTNetModel(hid_channels=256, out_channels=256, n_layers=11, cond_channels=80)
time_start = time.time()
for i in range(1025):
x = torch.rand(1, 1, 1)
cx = torch.rand(1, 80, 1)
out = net.forward_step(x, cx)
assert abs(net.layers[0].buffer.queue1.sum().item()) > 0
assert abs(net.layers[0].buffer.queue2.sum().item()) > 0
assert abs(net.layers[0].buffer.queue2[:, :, :-1].sum().item()) == 0
# setup TensorBoard
tb = SummaryWriter(OUT_PATH)
# create the FFTNet model
model = FFTNetModel(hid_channels=256,
out_channels=256,
n_layers=c.num_quant,
cond_channels=80)
criterion = MaskedCrossEntropyLoss()
optimizer = torch.optim.Adam(model.parameters(), lr=c.lr)
num_params = count_parameters(model)
print(" > Models has {} parameters".format(num_params))
if use_cuda:
model.cuda()
criterion.cuda()
# these two classes extend torch.utils.data.Dataset class to create the batches
# the batches are tuples of three elements: wav, mels, audio file name
train_dataset = LJSpeechDataset(
os.path.join(c.data_path, "mels", "meta_fftnet_train.csv"),
os.path.join(c.data_path,
"mels"), c.sample_rate, c.num_mels, c.num_freq,
c.min_level_db, c.frame_shift_ms, c.frame_length_ms, c.preemphasis,
c.ref_level_db, c.num_quant, c.min_wav_len, c.max_wav_len, False)
val_dataset = LJSpeechDataset(
os.path.join(c.data_path, "mels", "meta_fftnet_val.csv"),
os.path.join(c.data_path,
"mels"), c.sample_rate, c.num_mels, c.num_freq,
print(" ---- Test FFTNetModel step forward ----")
net = FFTNetModel(hid_channels=256,
out_channels=256,
n_layers=11,
cond_channels=80)
net.eval()
print(" > Number of model params: ", count_parameters(net))
x = torch.rand(1, 1, 1)
cx = torch.rand(1, 80, 1)
time_start = time.time()
with torch.no_grad():
for i in tqdm(range(20000)):
out = net.forward_step(x, cx)
time_avg = (time.time() - time_start) / 20000
print("> Avg time per step inference on CPU: {}".format(time_avg))
# on GPU
net = FFTNetModel(hid_channels=256,
out_channels=256,
n_layers=11,
cond_channels=80)
net.cuda()
net.eval()
x = torch.rand(1, 1, 1).cuda()
cx = torch.rand(1, 80, 1).cuda()
time_start = time.time()
for i in tqdm(range(20000)):
out = net.forward_step(x, cx)
time_avg = (time.time() - time_start) / 20000
print("> Avg time per step inference on GPU: {}".format(time_avg))