Caomei

Results 4 comments of Caomei

> > > 大概率是标签处理的问题。建议仔细阅读文档和代码自行处理。你可以先用小样本进行过拟合测试。 好的,多谢了哈,后面查明是学习率的原因;另外想请问一下您在DOTA数据集下的学习率是怎么设置的呢?

> > > 这个代码用adam优化器的情况下,lr我设置的是1e-4,训练12轮多就能在DOTA到50+的mAP,更多轮没试过,因为训练太慢了。 好的好的,非常感谢!

I have the same problem. I debug the code on Nvidia jetson AGX, after debugging, I think torch2trt will really impact the original pytorch. Can anyone solve it? Or tell...

> > > @dancingpipi @PressEtoRace Did you succeed in optimizing inference time of YOLOv3? if yes, Do you detect all objects well with a good accuracy? because the model I...