Performance issues in input_fn.py (by P3)

[DLPerf]

Hello! I've found a performance issue in input_fn.py: batch() should be called before map(), which could make your program more efficient. Here is the tensorflow document to support it.

Detailed description is listed below:

• dataset = dataset.batch(batch_size)(line 206) should be called before dataset = dataset.map(...)(line 197, line 198, line 200, line 202, line 204).

Besides, you need to check the function called in map()(e.g., normalize_image called indataset.map(normalize_image, num_parallel_calls=num_parallel_calls)) whether to be affected or not to make the changed code work properly. For example, if normalize_image needs data with shape (x, y, z) as its input before fix, it would require data with shape (batch_size, x, y, z).

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

[DLPerf]

Hello, I'm looking forward to your reply~