Is the pre-trained model trained using both the FLIC AND MPII dataset?

[neherh]

Is the pre-trained model trained using both the FLIC AND MPII dataset? Or is it just pre-trained on one of the datasets? In your paper, you are unclear as to whether you trained on both or separately.

[anewell]

The pretrained model is trained only on MPII. Benchmarking for the paper is done by training and evaluating on a each dataset separately.

[vicdu]

The result in the paper is 90.09, but the recurring result is 88.78, where do you think the problem occurred?

[anewell]

If you're getting 88.78 on validation then that's probably fine. The performance on the official test set (what we report in the paper) is always different, and usually a little bit higher than validation performance in my experience.