Yağmur Çiğdem Aktaş

An example of calibration file: P0: 7.215377000000e+02 0.000000000000e+00 6.095593000000e+02 0.000000000000e+00 0.000000000000e+00 7.215377000000e+02 1.728540000000e+02 0.000000000000e+00 0.000000000000e+00 0.000000000000e+00 1.000000000000e+00 0.000000000000e+00 P1: 7.215377000000e+02 0.000000000000e+00 6.095593000000e+02 -3.875744000000e+02 0.000000000000e+00 7.215377000000e+02 1.728540000000e+02 0.000000000000e+00 0.000000000000e+00 0.000000000000e+00 1.000000000000e+00...

Because the code simply writes 0 for mAP calculation and go... It's not something calculated. So it's not important but it would be nice how to calculate mAP and write...

You have to arrange the calibration file strings like this P0: value P1: value P2: value P3: value R_rect: value Tr_velo_cam: value Tr_imu_velo: value So just add ":" without any...

You're welcome!

anybody has any idea?? I have the same issue when I run training not in my local but in Docker. I copy the files directly into docker container so there...

Okay I solved the problem: when I run the code, it search finds test module from python path (usr/lib/python3.8/test.py), not the test.py from yolov7... Since I didn't have any other...

Hello, thanks for mentioning that the reason is number of workers, at least the training doesn't stuck now with multiple GPU which I have no other choice, since I get...

> ```shell > export NCCL_LL_THRESHOLD=0 > export NCCL_P2P_DISABLE=1 > export NCCL_IB_DISABLE=1 > ``` This solution did not work for me ://

Hello, using ota loss creates gpu memory increasement and it can cause run time errors by exploiting the CUDA memory. You should just put loss_ota to 0 (loss_ota: 0) in...