Segmentation fault (core dumped)

[tanjia123456]

Hello, thank you for your works. Now, I want to apply it to my dataset, I split the def train function into two parts: training and testing, but now I report an error: segmentation fault (core damped) Could you help me to see what's wrong? ` def train_before(features,labels): X = features model.train() optimizer.zero_grad() X_list = [] K = args.sample for k in range(K): X_list.append(rand_prop(X, training=True)) output_list = [] for k in range(K): output_list.append(torch.log_softmax(model(X_list[k]), dim=-1)) loss_train = 0. for k in range(K): loss_train += F.nll_loss(output_list[k], labels)

loss_train = loss_train / K
loss_consis = consis_loss(output_list)

loss_train = loss_train + loss_consis
acc_train = accuracy(output_list[0], labels)
loss_train.backward()
optimizer.step()

return loss_train,acc_train

def val_before(features,labels): X = features model.eval() X = rand_prop(X, training=False) output = model(X) output = torch.log_softmax(output, dim=-1)

loss_val = F.nll_loss(output, labels)
acc_val = accuracy(output, labels)

return loss_val,acc_val

`

thank you very much