question of Comparison experiment #4
Description
Hello, sorry to bother you. I would like to ask about the Efficiency Comparison in Table 4 of your paper SCAPE: A Simple and Strong Category-Agnostic Pose Estimator. When testing the FPS of CAPEformer, I achieved 87.4 task/s, which is significantly higher than the 26.09 task/s reported in the paper. Could you kindly provide the configuration details of the Efficiency Comparison experiment to help understand this discrepancy?