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

CUDNN < 7 doesn't support groups, please upgrade! #6

Open monoloxo opened 3 years ago

monoloxo commented 3 years ago

您好，请教一下，我是在alexeyAB的darknet下训练的，会报上面的错误，是要更新cudnn吗？ 因为修改环境不太方便，所以我试着将groups都改为=1和将所有的groups行删掉，然后用一个数据集进行训练，跑一小会就nan了。。。请问有什么解决办法吗？

dog-qiuqiu commented 3 years ago

只有更新cudnn，没有彼得办法，你cudnn版本太老的啊，这个模型轻量化全依靠这深度可分离卷积，你不能去掉groups，去掉的就成普通卷积了

monoloxo commented 3 years ago

好的，谢谢啦