load the pretrained identity enconder

[yangyangma97]

Couldyou please tell me whether the pretrained identity encoder network you are training in stage 2 is idnet or gen_ pth\dis_.th？ For this problem, I can modify the K value without reporting an error, but I feel that it will affect the training accuracy.

[chenhao2345]

Please first check you are working on Pytorch 1.2. Some people said newer Pytorch version might raise a problem, because of the updated syntax.

In stage 2, we pre-train generator and discriminator. The identity encoder is frozen, but is still saved. After stage 2, you should have saved weights like this.