Open wsung1 opened 5 years ago
https://github.com/AlexeyAB/darknet#how-to-train-to-detect-your-custom-objects change line batch to batch=64 change line subdivisions to subdivisions=8
As traces are left in the above .cfg file, I started my training with subdivisions=8 but I had no choice but to increase it to 64 due to out of memory error :(
Did you check your dataset by using Yolo_mark? How many iterations did you train? What avg-loss and mAP did you get at the end of training? Did you use cuDNN?
Yes, I checked. 40,000 iterations, resulting in an average loss of 0.1, as displayed below Sure, I trained with cuDNN 7.4.2.
@wsung1 i noticed that there is a difference in confidence depending on which version of darknet you are using ( pjreddie/darknet, alexeyab/darknet, C++ wrapper yolo_v2_class.cpp). It mays be that , chekc my issue :
Hi, I'm trying to train a YOLO v3 model for the road traffic sign detection. I believe I've followed most of instructions kindly provided by @AlexeyAB but my results have too many false positives, as shown below. The training conditions include I'd appreciate if you give any pieces of advice.