def define_F(opt, use_bn=False):
gpu_ids = opt['gpu_ids']
device = torch.device('cuda' if gpu_ids else 'cpu')
if (not 'network_F' in opt) or opt['network_F']['which_model_F'] == 'VGG':
# PyTorch pretrained VGG19-54, before ReLU.
if use_bn:
feature_layer = 49
else:
feature_layer = 34
netF = SRGAN_arch.VGGFeatureExtractor(feature_layer=feature_layer,
use_bn=use_bn,
use_input_norm=True,
device=device)
elif opt['network_F']['which_model_F'] == 'squeezenet':
netF = SRGAN_arch.SqueezeNetFeatureExtractor(use_input_norm=True,
device=device)
elif opt['network_F']['which_model_F'] == 'mobilenet':
# raise NotImplementedError
netF = SRGAN_arch.MobileNetFeatureExtractor(use_input_norm=True,
device=device)
elif opt['network_F']['which_model_F'] == 'shufflenet':
# raise NotImplementedError
netF = SRGAN_arch.ShuffleNetFeatureExtractor(use_input_norm=True,
device=device)
else:
raise NotImplementedError
netF.eval() # No need to train
return netF
def define_F(opt, use_bn=False):
gpu_ids = opt['gpu_ids']
device = torch.device('cuda' if gpu_ids else 'cpu')
# PyTorch pretrained VGG19-54, before ReLU.
if use_bn:
feature_layer = 49
else:
feature_layer = 34
netF = SRGAN_arch.VGGFeatureExtractor(feature_layer=feature_layer, use_bn=use_bn,
use_input_norm=True, device=device)
netF.eval() # No need to train
return netF