SpursLipu

Results 19 comments of SpursLipu

Thank you for your quick reply. My version of Openvino is 2019 R1, and I have already cheak my bashrc file. Just like following picture. ![2d57e38aee69469ec2a1731a5e1bb58](https://user-images.githubusercontent.com/31196757/56362818-54ee7c80-621d-11e9-9c4d-c0ea7847cd29.jpg) But it still doesn't...

Still doesn't work..... ![0b6ef8e56b98f267dd1b76aa6e45b96](https://user-images.githubusercontent.com/31196757/56363490-f1654e80-621e-11e9-87cc-0808b5c6b406.jpg)

![a3e06b55eeb369be1ce4bd26a5ccce9](https://user-images.githubusercontent.com/31196757/56364696-c6302e80-6221-11e9-8de4-626e902fcf62.jpg) Still doesn't work...... I don't knwo why, and I want to cry.......

![ce40af07f337e5fedd54bed13e88112](https://user-images.githubusercontent.com/31196757/56372512-bb7d9580-6231-11e9-960f-51945d206824.jpg)

I also solved this problem as you said, think you very much!

你把 -pt去掉就可以了。

-pt是在使用coco80类预训练文件的时候使用。mAP训练也无法提升吗?

不会一直很低吧?还是要看最后的best.pt,有突变的很低也正常

转化是darknet weights是可以的,你可以用我的convert.py这个文件。

你可以试试减小batchsize 或者减小imgsize,yolov4就是比较吃显存