Qazi Mazhar
Qazi Mazhar
Hi @ziniuwang You can follow the following similar code and see how it improved. https://github.com/engrqazi/3dObjectdetectin If you have any problems don't hesitate to comment.
I think I solved it before sounds like a library version problem.
Change the classes
You need to input correct calibration matrix files
> I just want to know which backbone is good enough to train for a mono 3d prediction task. I tried ResNet18 34, 50 and 101.. the best one is...
Thank you so much Garrick Brazil for commenting and making the code. I am still having the same error which i faced when i try to use layer4 of resnet50...
well, after training with layer3 with the code you provided following are the results.. test_iter 100000 2d car --> easy: 0.0004, mod: 0.0008, hard: 0.0013 test_iter 100000 gr car -->...
when i use the model resnet101 with depthaware i get the following results still reasonable test_iter 50000 2d car --> easy: 0.8680, mod: 0.8214, hard: 0.6647 test_iter 50000 gr car...
> Attached are fixed model files (I briefly check that they begin training on my machine). > > [resnet_models_fixed.tar.gz](https://github.com/garrickbrazil/M3D-RPN/files/3774966/resnet_models_fixed.tar.gz) > > Regarding the performance you posted, that is very alarming....
Change you batch size