def test_multisource(Res_model, A_model, featurenet, main=False):
Res_model.eval()
test_record = []
# testset = FAB_DataSet(TEST_DIR, ['people_to_people.json']) # use this for multispeaker
testset = FMA_DataSet(TEST_DIR, ['captaincook_white.json'], TEST_DIR,
['captaincook_clean.json'])
if main:
testloader = torch.utils.data.DataLoader(dataset = testset, \
batch_size = BS, \
shuffle = False)
else:
testloader = torch.utils.data.DataLoader(dataset = testset, \
batch_size = BS, \
shuffle = False)
for i, data in enumerate(testloader, 0):
# get mix spec & label
feat_data, mix_specs, a_specs = data # use this for denoise test
print("mix_specs = ", np.sum(np.array(mix_specs)))
mix_specs = mel_norm(mix_specs) / 10 # use this for denoise test
# feat_data, a_specs, b_specs = data # use this for multispeaker test
# mix_specs = mel_norm(mix(a_specs, b_specs)) # use this for multispeaker test
print("mix_specs = ", np.sum(np.array(mix_specs)))
target_specs = mel_norm(a_specs) / 10
# b_specs = mel_norm(b_specs) # use this for multispeaker test
# target_specs = a_specs # use this for multispeaker test
if ATTEND:
# get feature
feats = featurenet.feature(feat_data)
# feed in feature to ANet
a7, a6, a5, a4, a3, a2 = A_model(feats)
# Res_model
tops = Res_model.upward(mix_specs, a7, a6, a5, a4, a3, a2)
else:
tops = Res_model.upward(mix_specs)
#top_record.append(tops.detach().numpy().tolist())
outputs = Res_model.downward(tops, shortcut=True)
loss_test = criterion(outputs, target_specs)
if (not main) or (main and i % 1 == 0):
# print images: mix, target, attention, separated
tarr = (target_specs[0]).view(256, 128).detach().numpy()
#mask = (b_specs[0]).view(256, 128).detach().numpy()
mixx = (mix_specs[0]).view(256, 128).detach().numpy()
outt = (outputs[0]).view(256, 128).detach().numpy()
cv2.imwrite(
os.path.join(ROOT_DIR, 'results/people_to_people/' + str(i) +
"_tar.png"), tarr)
# cv2.imwrite(os.path.join(ROOT_DIR, 'results/people_to_people/' + str(i) + "_mask.png"), mask)
cv2.imwrite(
os.path.join(ROOT_DIR, 'results/people_to_people/' + str(i) +
"_mix.png"), mixx)
cv2.imwrite(
os.path.join(ROOT_DIR, 'results/people_to_people/' + str(i) +
"_sep.png"), outt)
print(np.mean(inv_mel(tarr[-10:])), np.mean(inv_mel(mixx[-10:])))
return np.average(test_record)
# ============================================
from mel import mel_norm, mel
zeros = torch.zeros(bs, 256, 128)
Res_model.eval()
for epo in range(1):
# train
for i, data in enumerate(testloader, 0):
# get mix spec & label
feat_data, _, a_specs = data
feat_data = feat_data.squeeze()
a_specs = a_specs.squeeze()
a_specs = mel_norm(a_specs)
target_specs = a_specs
# get feature
feats = featurenet.feature(feat_data)
# feed in feature to ANet
a7, a6, a5, a4, a3, a2 = A_model(feats)
# Res_model
tops = Res_model.upward(a_specs, a7, a6, a5, a4, a3, a2)
outputs = Res_model.downward(tops, shortcut = True).squeeze()
loss_train = criterion(outputs, target_specs)
zeros = torch.zeros(BS, 256, 128)
for epo in range(epoch):
# train
for i, data in enumerate(mixloader, 0):
Res_model.train()
# get mix spec & label
feat_data, a_specs, b_specs = data
feat_data = feat_data.squeeze()
#a_specs = norm(a_specs.squeeze())
#b_specs = norm(b_specs.squeeze())
mix_specs = mel_norm(mix(a_specs, b_specs))
target_specs = mel_norm(a_specs)
#feat_optimizer.zero_grad()
anet_optimizer.zero_grad()
res_optimizer.zero_grad()
# get feature
feats = featurenet.feature(feat_data)
# feed in feature to ANet
a7, a6, a5, a4, a3, a2 = A_model(feats)
# Res_model
tops = Res_model.upward(mix_specs, a7, a6, a5, a4, a3, a2)
except:
print("model not available")
#=============================================
# Loss
#=============================================
criterion = nn.MSELoss()
loss_record = []
from mel import mel_norm
model.eval()
for i, data in enumerate(testloader, 0):
data = mel_norm(data)
top = model.upward(data)
outputs = model.downward(top, shortcut=True)
targets = data.view(bs, 1, 256, 128)
outputs = outputs.view(bs, 1, 256, 128)
loss = criterion(outputs, targets)
loss_record.append(loss.item())
print('[%d] loss: %.3f' % (i, loss.item()))
if i % 1 == 0:
inn = data[0].view(256, 128).detach().numpy() * 255
cv2.imwrite(
# Train
#=============================================
from mel import mel, norm, mel_norm
zeros = torch.zeros(BS, 256, 128)
Res_model.train()
for epo in range(epoch):
# train
for i, data in enumerate(mixloader, 0):
# get mix spec & label
feat_data, a_specs, _ = data
feat_data = feat_data.squeeze()
target_specs = mel_norm(a_specs.squeeze())
# a_specs = a_specs.squeeze()
# a_specs = norm(a_specs)
# target_specs = a_specs
# feat_optimizer.zero_grad()
anet_optimizer.zero_grad()
res_optimizer.zero_grad()
# get feature
feats = featurenet.feature(feat_data)
# feed in feature to ANet
a7, a6, a5, a4, a3, a2 = A_model(feats)