How can I solve this probrem

[lry-123456789]

when I training your net ,The console feed me back "File "C:\Python39\lib\site-packages\torch\nn\modules\module.py", line 201, in _forward_unimplemented
raise NotImplementedError
NotImplementedError"
How can I solve it?

[lry-123456789]

trained_model = EfficientNet.from_pretrained('efficientnet-b0') model = nn.Sequential(*list(trained_model.children())[:-1],Flatten(),nn.Linear(1536,7)).to(device) optimizer=optim.Adam(model.parameters(),lr=lr) criteon=nn.CrossEntropyLoss() best_acc,best_epoch=0,0 global_step=0 viz.line([[0.0,0.0]],[0.],win='test',opts=dict(title='Loss on Training Data and Accuracy on Training Data',xlabel='Epochs',ylabel='Loss and Accuracy',legend=['loss','val_acc'])) for epoch in range(epochs): for step,(x,y) in enumerate(train_loader): x,y = x.to(device),y.to(device) model.train() logits=model(x) loss=criteon(logits,y) optimizer.zero_grad() loss.backward() optimizer.step() viz.line([[loss.item(),evalute(model,val_loader)]],[global_step],win='test',update='append') global_step+=1 if epoch==0: print('the '+str(epoch+1)+' epoch'+' training......') val_acc=evalute(model,val_loader) if val_acc>best_acc: best_epoch=epoch best_acc=val_acc torch.save(model.state_dict(),'best_trans.mdl') print('best accuracy:',best_acc,'best epoch:',(best_epoch+1)) torch.save(model,'model.dll')
However, I do not know what I do is wrong.