Nan value for semantic loss

[saliteta]

After training for several epochs, the semantic loss will be nan.

[saliteta]

I solved this issue by adding the clip_grad_norm to contain the gradient of index_decoder

        total_loss = dataset.reconstruction_loss_weight * loss \
                    + dataset.semantic_loss_weight * semantic_loss \
                    + dataset.uncertainty_loss_weight * uncertainty_loss \
                    + dataset.xyzmlp_loss_weight * xyz_mlp_loss \
                    + dataset.smooth_loss_weight * smooth_loss

        total_loss.backward()

        torch.nn.utils.clip_grad_norm_(index_decoder.parameters(), max_norm=1)

        iter_end.record()