lianghao

> Sorry for the interruption, but I'd like to digress for a moment. Could you tell me the version of BasicSR？ the version is the same as NAFNet

I have the same problem. The device I used is the RTX 3090ti.​ After 200 epochs, both the char loss and edge loss grow graduallty.

> > > > 我和你情况一样。我该如何解决？ clipping the gradient, ```python torch.nn.utils.clip_grad_norm_(self.net.parameters(), 0.01) ```

> > > > Could you tell me where to put this code？ ```python loss.backward() torch.nn.utils.clip_grad_norm_(model_restoration.parameters(), 0.01) optimizer.step() ````