Tencent / Real-SR

Real-World Super-Resolution via Kernel Estimation and Noise Injection
Apache License 2.0
788 stars 118 forks source link

inferrence #27

Open FengMu1995 opened 3 years ago

FengMu1995 commented 3 years ago

why exits "self.netG.train()" in SRGAN_model.SRGANModel.test函数中as follows:,推理应该只包括test部分吧?

def test(self): self.netG.eval() with torch.no_grad(): self.fake_H = self.netG(self.var_L) self.netG.train()