def run(self):
# Load Dataset
dl = DataLoader(self.config)
X, y = dl.load_data()
# Train Model - No Training Required, Just KF Validation
self.train(X, y)
def train(**kwargs):
kwargs.update({'model': 'pcnnAtt'})
opt.parse(kwargs)
if opt.use_gpu:
torch.cuda.set_device(opt.gpu_id)
model = getattr(models, "pcnnAtt")(opt)
if opt.use_gpu:
model.cuda()
# loading data
DataModel = getattr(dataset, opt.data + "Data")
train_data = DataModel(opt.data_root, train=True)
train_data_loader = DataLoader(train_data,
opt.batch_size,
shuffle=True,
num_workers=opt.num_workers,
collate_fn=collate_fn)
test_data = DataModel(opt.data_root, train=False)
test_data_loader = DataLoader(test_data,
opt.batch_size,
shuffle=False,
num_workers=opt.num_workers,
collate_fn=collate_fn)
print('{} train data: {}; test data: {}'.format(now(), len(train_data),
len(test_data)))
optimizer = optim.Adadelta(model.parameters(), rho=0.95, eps=1e-6)
def _create_dataloader(self, N, identifier, extension):
file = self.path + identifier
file = ensure_file_extension(file, extension)
if os.path.exists(file) and not self._forced_setup:
dataloader = DataLoader.FromFile(file)
else:
print(
"Could not find {} to load dataset (or forced); creating from sampler... "
.format(file))
dataloader = DataLoader.FromSampler(self._rfs, N)
dataloader.save(file)
return dataloader
from config import Options
CMD_DATA1 = "/data/zhangyi/Noisy_dataset/CHJ14_cmd-CHJ/CHJ14_cmd-CHJ-2/CHJ14_cmd-CHJ/"
CMD_DATA2 = "/data/zhangyi/Noisy_dataset/CHJ14_cmd-CHJ/CHJ14_cmd-CHJ-3/CHJ14_cmd-CHJ/hp/"
AISHELL_DATA = "/data/tengxiang/dataset/aishell-chj-hp/"
EXTRA_DATA = "/data/tengxiang/dataset/wenzhifan/4CH/"
HISF_DATA = "/data/tengxiang/dataset/hisf/cmd_input/wav/"
LOG_HOME = "/data/tengxiang/aishell_hp/"
# tt_data_dir = os.path.join(AISHELL_DATA, "cv")
tt_data_dir = EXTRA_DATA
audio_log_dir = os.path.join(EXTRA_DATA, "../v1")
ckpt = "/home/teng.xiang/projects/model-ckpt/aishell_hp-sir_005_020/TasNet-se-19"
# ckpt = "/data/tengxiang/aishell_hp/v0/ckpt/TasNet-se-9"
# ckpt = "/home/teng.xiang/projects/model-ckpt/aishell_time-delay_cln/TasNet-se-17"
if __name__ == "__main__":
opt = Options().parse()
if opt.gpu_num == 1:
os.environ['CUDA_VISIBLE_DEVICES'] = '1'
if opt.tt_data_dir is None:
opt.tt_data_dir = tt_data_dir
if opt.audio_log_dir is None:
opt.audio_log_dir = audio_log_dir
tt_data = SeparatedDataset([opt.tt_data_dir])
tt_loader = DataLoader(tt_data, opt.batch_size * opt.gpu_num)
tasnet = Model(opt)
tasnet.inference(tt_loader, ckpt)
if __name__ == "__main__":
# load configrations
# ==========================================================================
opt = Options().parse()
argchk(opt)
# ==========================================================================
if opt.stage == "tr":
filepatterns = ["*mixture*.wav", "*speech*.wav"]
tr_data = SeparatedDataset(data_dir_list=[opt.tr_data_dir],
file_pattern_list=filepatterns)
cv_data = SeparatedDataset(data_dir_list=[opt.cv_data_dir],
file_pattern_list=filepatterns)
tr_loader = DataLoader(tr_data,
opt.batch_size * opt.gpu_num,
shuffle=True)
cv_loader = DataLoader(cv_data, opt.batch_size * opt.gpu_num)
# pre_trained_model_path = "/data/tengxiang/tasnet/log/v0/"
# ckpt = tf.train.latest_checkpoint(pre_trained_model_path)
tasnet = Model(opt)
tasnet.train(tr_loader, cv_loader)
elif opt.stage == "tt":
tt_data = SeparatedDataset([opt.tt_data_dir])
tt_loader = DataLoader(tt_data, opt.batch_size * opt.gpu_num)
tasnet = Model(opt)
tasnet.inference(tt_loader, opt.ckpt)
