def main():
# Views the training images and displays the distance on anchor-negative and anchor-positive
test_display_triplet_distance = False
# print the experiment configuration
print('\nparsed options:\n{}\n'.format(vars(args)))
print('\nNumber of Classes:\n{}\n'.format(len(train_dir.classes)))
# instantiate model and initialize weightsNUM_FEATURES
# TODO(xin): IMPORTANT load num_classes from checkpoint
model = DeepSpeakerModel(embedding_size=args.embedding_size,
num_classes=len(train_dir.classes),
feature_dim=num_features,
frame_dim=c.NUM_FRAMES)
if args.cuda:
model.cuda()
from torchsummary import summary
summary(model, (1, c.NUM_FRAMES, c.NUM_FEATURES))
# # More detailed information on model
# print(model)
optimizer = create_optimizer(model, args.lr)
# optionally resume from a checkpoint
if args.resume:
if os.path.isfile(args.resume):
print('=> loading checkpoint {}'.format(args.resume))
checkpoint = torch.load(args.resume)
args.start_epoch = checkpoint['epoch']
model.load_state_dict(checkpoint['state_dict'])
optimizer.load_state_dict(checkpoint['optimizer'])
else:
print('=> no checkpoint found at {}'.format(args.resume))
start = args.start_epoch
end = start + args.epochs
train_loader = torch.utils.data.DataLoader(train_dir, batch_size=args.batch_size, shuffle=False, **kwargs)
test_loader = torch.utils.data.DataLoader(test_dir, batch_size=args.test_batch_size, shuffle=False, **kwargs)
for epoch in range(start, end):
if args.test_only:
test(test_loader, model, epoch)
return
train(train_loader, model, optimizer, epoch)
test(test_loader, model, epoch)
def main():
model = DeepSpeakerModel(embedding_size=256, num_classes=10)
if args.resume:
if os.path.isfile(args.resume):
print('=> loading checkpoint {}'.format(args.resume))
checkpoint = torch.load(args.resume)
model.load_state_dict(checkpoint['state_dict'])
else:
print('=> no checkpoint found at {}'.format(args.resume))
# print(calculateOneEmbedding('/home/zinzin/Documents/pytorch/deepspeaker-pytorch/data/test_set/dnl/s1/t1/s1_t1_1.wav', model))
embeddings = enrollment(model)
test(model, embeddings)
def main():
# Views the training images and displays the distance on anchor-negative and anchor-positive
test_display_triplet_distance = False
# print the experiment configuration
print('\nparsed options:\n{}\n'.format(vars(args)))
print('\nNumber of Classes:\n{}\n'.format(len(train_dir.classes)))
# instantiate model and initialize weights
model = DeepSpeakerModel(embedding_size=args.embedding_size,
num_classes=len(train_dir.classes))
if args.cuda:
model.cuda()
optimizer = create_optimizer(model, args.lr)
# optionally resume from a checkpoint
if args.resume:
if os.path.isfile(args.resume):
print('=> loading checkpoint {}'.format(args.resume))
checkpoint = torch.load(args.resume)
args.start_epoch = checkpoint['epoch']
checkpoint = torch.load(args.resume)
model.load_state_dict(checkpoint['state_dict'])
optimizer.load_state_dict(checkpoint['optimizer'])
else:
print('=> no checkpoint found at {}'.format(args.resume))
start = args.start_epoch
#start = 0
end = start + args.epochs
train_loader = torch.utils.data.DataLoader(train_dir,
batch_size=args.batch_size,
shuffle=False,
**kwargs)
for epoch in range(start, end):
train(train_loader, model, optimizer, epoch)
#test(test_loader, model, epoch)
#break;
if test_display_triplet_distance:
display_triplet_distance(model, train_loader,
LOG_DIR + "/train_{}".format(epoch))
pretrained_dict = {
k: v
for k, v in pretrained_dict.items()
if k in model_dict.keys() and v.size() == model_dict[k].size()
}
missed_params = [
k for k, v in model_dict.items()
if not k in pretrained_dict.keys()
]
print('loaded params/tot params:{}/{}'.format(len(pretrained_dict),
len(model_dict)))
print('miss matched params:{}'.format(missed_params))
model_dict.update(pretrained_dict)
model.load_state_dict(model_dict)
train_dataset = Mydataset(opt.data_path, 'train')
train_loader = DataLoader(train_dataset,
batch_size=opt.batch_size,
num_workers=opt.num_workers,
drop_last=False,
shuffle=True)
test_dataset = Mydataset(opt.data_path, 'test')
test_loader = DataLoader(test_dataset,
batch_size=opt.batch_size,
num_workers=opt.num_workers,
drop_last=False,
shuffle=True)
def load_model(ckp_path):
model = DeepSpeakerModel(embedding_size=512, num_classes=251)
checkpoint = torch.load(ckp_path, map_location='cpu')
model.load_state_dict(checkpoint)
return model