Does your code write detections on images? Or read the detection from pth files and plot them?

chengchunhsu / EveryPixelMatters

Implementation of ECCV 2020 paper "Every Pixel Matters: Center-aware Feature Alignment for Domain Adaptive Object Detector"

Other

164 stars 21 forks source link

Does your code write detections on images? Or read the detection from pth files and plot them? #2

Closed mamunir closed 4 years ago

chengchunhsu commented 4 years ago

Hi @mamunir,

During the evaluation stage, our code will evaluate the result in mAP and save it as a JSON file (COCO format). After that, you can plot the result or do anything else via the COCO API with the saved file.

Let me know if you have any further questions!

Cheng-Chun