search

dog-qiuqiu / Yolo-Fastest

:zap: Based on yolo's ultra-lightweight universal target detection algorithm, the calculation amount is only 250mflops, the ncnn model size is only 666kb, the Raspberry Pi 3b can run up to 15fps+, and the mobile terminal can run up to 178fps+
Other
1.98k stars 427 forks source link

total loss is very large #21

Open yunxiaozimeng opened 3 years ago

yunxiaozimeng commented 3 years ago

I follow the README file to train my dataset. but the total loss is still very large(>=350)at 1000 epochs and without ant decrease tread,HOW CAN I SOLVE THIS PROBLEM?

xingshuohan commented 3 years ago

I follow the README file to train my dataset. but the total loss is still very large(>=350)at 1000 epochs and without ant decrease tread,HOW CAN I SOLVE THIS PROBLEM?

1, confirm you are training with GPU 2, try to change the parameter burn_in in your .cfg file.

GeneralJing commented 3 years ago

一样的问题，训练完检测效果还不错，但是日志loss非常大，iou_loss很大，而且是随着训练的进行loss一直在增加，不知道是什么原因，而且另外一个尺度的各个指标输出都为0