Augmentation of data

[GarrickLin]

I noted that you did little effort on data augmentation, and this is the end of the training of pnet:

INFO:root:Epoch[15] Train-Accuracy=0.931125
INFO:root:Epoch[15] Train-LogLoss=0.206840
INFO:root:Epoch[15] Train-BBOX_MSE=0.015009
INFO:root:Epoch[15] Time cost=118.500
INFO:root:Saved checkpoint to "../model/pnet-0016.params"

Is this reproduction of your final experiment？ And will this route achieve the final result of this graph?

[Seanlinx]

@GreenKing The log looks reasonable, I got similar result at the end of pnet. If you want to achieve similar performance, the thresholds you used to generate training data for the following net should be set carefully.
The thresholds I use is the correspond threshold of around 60w false positives(97% recall) for pnet, and 8w false positives(95.5% recall) for rnet