Open neherh opened 6 years ago
The pretrained model is trained only on MPII. Benchmarking for the paper is done by training and evaluating on a each dataset separately.
The result in the paper is 90.09, but the recurring result is 88.78, where do you think the problem occurred?
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.
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.