调用预训练vgg模型参数问题’NoneType’ object is not callable
报错如下
Traceback (most recent call last):
File "train.py", line 50, in <module>
init_vgg16('./')
File "/home/aistudio/work/utils.py", line 52, in init_vgg16
for (src, dst) in zip(vgglua.parameters()[0], vgg.parameters()):
TypeError: 'NoneType' object is not callable
用的DID-MDN 代码,去雨模型,用了vgg16感知损失代码如下
def init_vgg16(model_folder):
"""load the vgg16 model feature"""
if not os.path.exists(os.path.join(model_folder, 'vgg16.weight')):
if not os.path.exists(os.path.join(model_folder, 'vgg16.t7')):
os.system(
'wget http://cs.stanford.edu/people/jcjohns/fast-neural-style/models/vgg16.t7 -O ' + os.path.join(model_folder, 'vgg16.t7'))
vgglua = torchfile.load(os.path.join(model_folder, 'vgg16.t7'))
vgg = Vgg16()
print(type(vgglua))
for (src, dst) in zip(vgglua.parameters()[0], vgg.parameters()):
dst.data[:] = src
torch.save(vgg.state_dict(), os.path.join(model_folder, 'vgg16.weight'))
因为用了云虚拟机 直接下载vgg16太慢而且不能保存,想预先下载好模型参数这样,但是这个报错求大神。。。。
来源:CSDN
作者:小狐狸啊!
链接:https://blog.csdn.net/weixin_43209906/article/details/103663138