Yukun-Huang / Person-Attribute-Recognition-MarketDuke

A simple baseline implemented in PyTorch for pedestrian attribute recognition task, evaluating on Market-1501 and DukeMTMC-reID dataset.

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Questions about evaluation criteria

Vivinia opened this issue · comments

Recently, I have been trying to adjust the code and found that there are usually four evaluation criteria. mA is the mean accuracy of attributes, acc is the average accuracy of instances. Does your code implement mA? And if so, how does ACC implement it?May I have your contact information?thank you.