LeifSun

I find the visual-perforance is better than score-performances too,The score is 0.016903232698188032, Is the rule of score is wrong?

you can add the outs1 = tf.concat([net_cpm,heatmaps1, pafs1], axis=-1) to every refinestage. And using Coco dataset to train ,validating it in the cocoApi .I trained it in the coco dataset...