dataset next batch issue.

[tracer9]

Hi Jiyang!
I have been followed your a series of work in action detection area. Very solid work.

Thanks to open source your TURN-TAP model.

When reading your code, I found that in dataset.py, you give mini-batch by using:

The point is: random sample here is not a good choice. when training, some samples may be trained multiple times while others may not be trained. That's werid.

In other words, you cannot train a whole epoch.

I think pytorch's dataset wrapper would be a good choice.

[jiyanggao]

Hi, Good idea! Sorry for the late reply. I will try this idea definately.