Performance issues in examples/train_embedding.py(P2)

[DLPerf]

Hello,I found a performance issue in tf-TabNet/blob/master/examples/train_embedding.py
ds_train.map was called without num_parallel_calls.
I think it will increase the efficiency of your program if you add this.

The same issues also exist in ds_test = ds_test.map

Here is the documemtation of tensorflow to support this thing.

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