Performance issue in /libs/models/backbones/efficientnet (by P3)

[DLPerf]

Hello! I've found a performance issue in /utils.py: dataset.batch(self.batch_size,drop_remainder=batch_drop_remainder)(here) should be called before dataset.map(_parse_function)(here), which could make your program more efficient.

Here is the tensorflow document to support it.

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

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~