损失。向后()没有毕业生在pytorch NN

代码提供了一个错误的损失。向后() 错误是： untimeError:元0张量不需要的研究和没有grad_fn

for epoch in range(N_EPOCHS):
    model.train()
    for i,(im1, im2, labels) in enumerate(train_dl):
        i1 = torch.flatten(im1,1)
        i2 = torch.flatten(im2,1)
        inp = torch.cat([i1,i2],1)
        
        b_x = Variable(inp) # batch x
        b_y = Variable(labels) # batch y
        y_ = model(b_x).squeeze()
        y_ = (y_>0.5).float()
        
        print(y_)
        print(l)
        loss = criterion(y_,b_y)
        print(loss.item())
        loss.backward()
        optimizer.step()