Performance issues in the programs

[DLPerf]

Hello,I found a performance issue in the definition of init_input_pipeline ,QingyongHu_RandLA-Net/main_S3DIS.py,self.batch_train_data.map was called without num_parallel_calls.I think it will increase the efficiency of your program if you add this.Here is the documemtation of tensorflow to support this thing.

The same issues also exist in self.batch_val_data.map ,self.batch_train_data,self.batch_val_data,self.batch_test_data and three similar place

Looking forward to your reply. Btw, I am very glad to create a PR to fix it if you are too busy.