def load_checkpoints(config_path, checkpoint_path, device='cuda'):
with open(config_path) as f:
config = yaml.load(f)
generator = OcclusionAwareGenerator(
**config['model_params']['generator_params'],
**config['model_params']['common_params'])
generator.to(device)
kp_detector = KPDetector(**config['model_params']['kp_detector_params'],
**config['model_params']['common_params'])
kp_detector.to(device)
checkpoint = torch.load(checkpoint_path, map_location=device)
generator.load_state_dict(checkpoint['generator'])
kp_detector.load_state_dict(checkpoint['kp_detector'])
generator = DataParallelWithCallback(generator)
kp_detector = DataParallelWithCallback(kp_detector)
generator.eval()
kp_detector.eval()
return generator, kp_detector
def load_checkpoints(config_path, checkpoint_path, device="cuda"):
with open(config_path) as f:
config = yaml.load(f, Loader=yaml.FullLoader)
generator = OcclusionAwareGenerator(
**config["model_params"]["generator_params"],
**config["model_params"]["common_params"],
)
generator.to(device)
kp_detector = KPDetector(
**config["model_params"]["kp_detector_params"],
**config["model_params"]["common_params"],
)
kp_detector.to(device)
checkpoint = torch.load(checkpoint_path, map_location=device)
generator.load_state_dict(checkpoint["generator"])
kp_detector.load_state_dict(checkpoint["kp_detector"])
generator = DataParallelWithCallback(generator)
kp_detector = DataParallelWithCallback(kp_detector)
generator.eval()
kp_detector.eval()
return generator, kp_detector
def load_generator_and_keypoint_detector(self):
config = self.load_config()
generator = OcclusionAwareGenerator(
**config['model_params']['generator_params'],
**config['model_params']['common_params'])
generator.to(self.device)
kp_detector = KPDetector(
**config['model_params']['kp_detector_params'],
**config['model_params']['common_params'])
kp_detector.to(self.device)
checkpoints = self.load_checkpoints()
generator.load_state_dict(checkpoints['generator'])
kp_detector.load_state_dict(checkpoints['kp_detector'])
generator.eval()
kp_detector.eval()
return generator, kp_detector
def load_checkpoints(self):
with open(self.config_path) as f:
config = yaml.load(f)
generator = OcclusionAwareGenerator(**config['model_params']['generator_params'],
**config['model_params']['common_params'])
generator.to(self.device)
kp_detector = KPDetector(**config['model_params']['kp_detector_params'],
**config['model_params']['common_params'])
kp_detector.to(self.device)
checkpoint = torch.load(self.checkpoint_path, map_location=self.device)
generator.load_state_dict(checkpoint['generator'])
kp_detector.load_state_dict(checkpoint['kp_detector'])
generator.eval()
kp_detector.eval()
return generator, kp_detector
# Declare a discriminator
discriminator = MultiScaleDiscriminator(
**config['model_params']['discriminator_params'],
**config['model_params']['common_params'])
if torch.cuda.is_available():
discriminator.to(opt.device_ids[0])
if opt.verbose:
print(discriminator)
# Declare a key point detector
kp_detector = KPDetector(**config['model_params']['kp_detector_params'],
**config['model_params']['common_params'])
if torch.cuda.is_available():
kp_detector.to(opt.device_ids[0])
# Print network details if using --verbose flag
if opt.verbose:
print(kp_detector)
# Read in dataset details, defined in *.yaml config file, "dataset_params" section
# Refer to ./config/vox-256.yaml for details
# 数据预处理在此步骤完成，并读取进 dataset 变量中
dataset = FramesDataset(is_train=(opt.mode == 'train'),
**config['dataset_params'])
print("Dataset size: {}, repeat number: {}".format(
len(dataset), config['train_params']['num_repeats']))
# Create the logging direction
if not os.path.exists(log_dir):