search

fredzzhang / pvic

[ICCV'23] Official PyTorch implementation for paper "Exploring Predicate Visual Context in Detecting Human-Object Interactions"
BSD 3-Clause "New" or "Revised" License
67 stars 8 forks source link

How to obtain the metrics of Default (DT) mode and Known-Object (KO) mode on the hico-det dataset? #54

Closed AngleBeats147753 closed 4 months ago

AngleBeats147753 commented 4 months ago

Hello! I'm very grateful for your work achievements. I encountered a problem when conducting the test. I sincerely hope to get your help.

How to obtain the metrics of Default (DT) mode and Known-Object (KO) mode on the hico-det dataset? The current eval will only output the map of full, rare, and none-rare for one mode.

fredzzhang commented 4 months ago

Hi @AngleBeats147753,

The mAP returned from the Python evaluation script is the default mode. To get results for the know-object mode, you need to cache the detections in Matlab format and evaluate it using the code provided by the original HO-RCNN repo. The command to cache detection in Matlab format is included in the docs.

Fred.