train error

[forAlgorithm]

---

RuntimeError Traceback (most recent call last) in <cell line: 1>() 30 # y = torch.cat([i.y for i in data], 0).view(-1, out_channels).to(device) 31 optimizer.zero_grad() ---> 32 out = model(data) 33 # loss = F.mse_loss(out, y) 34 loss = F.mse_loss(out, data.y)

4 frames in masked_softmax(X, valid_len) 25 X = X.reshape(-1, shape[-1]) 26 for count, row in enumerate(X): ---> 27 row[int(valid_len[count]):] = -1e6 28 return nn.functional.softmax(X.reshape(shape), dim=-1) 29

RuntimeError: Output 0 of SliceBackward0 is a view and is being modified inplace. This view is the output of a function that returns multiple views. Such functions do not allow the output views to be modified inplace. You should replace the inplace operation by an out-of-place one.