How to evaluate and test the data after training

[ZhouAo-ZA]

After using the COCO data set for training, 1、 how to evaluate and test the accuracy, 2、the training efficiency is too low. Has anyone tried to modify it to batch training? 3、The single-machine multi-card merge time reports the dimensionality error. Does anyone try to solve it?

Thanks to HeatherJiaZG for the training code, but unfortunately he doesn't seem to maintain this library anymore. Someone can provide some help, thanks a lot

[Liukailong9560]

Hi, Did you solve this problem?

[sunset326]

老哥，请问你知道训练结束后如何评估吗

[Shuhul24]

I think we can execute the match_pairs.py to check the matching (visualizations), but the problem is that when I run the match_path.py file, the error comes to be

Will write matches to directory "dump_match_pairs"
[ WARN:[email protected]] global loadsave.cpp:248 findDecoder imread_('/home/shuhulh/assets/scannet_sample_images/scene0711_00_frame-001680.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:248 findDecoder imread_('/home/shuhulh/assets/scannet_sample_images/scene0711_00_frame-001995.jpg'): can't open/read file: check file path/integrity
Problem reading image pair: /home/shuhulh/assets/scannet_sample_images/scene0711_00_frame-001680.jpg /home/shuhulh/assets/scannet_sample_images/scene0711_00_frame-001995.jpg

Is there any way I can check how this can be avoided?