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

请问到哪里找yolo-fastest.conv.109? #9

Closed JimXu1989 closed 3 years ago

JimXu1989 commented 3 years ago

感谢您的技术分享!! 请问预训练weights yolo-fastest.conv.109要到哪里下载呢? 多谢!

dog-qiuqiu commented 3 years ago

需要用我提供的weights生成conv,readme有说明哦

JimXu1989 commented 3 years ago

需要用我提供的weights生成conv,readme有说明哦

谢谢!问题已解决

meanmee commented 3 years ago

你提供的weights不是在COCO上训练了的吗,那我再用来训练有什么意义呢? @dog-qiuqiu

DESXIE commented 3 years ago

感谢您的技术分享!! 请问预训练weights yolo-fastest.conv.109要到哪里下载呢? 多谢!

你好,我也遇到了相同的问题,在输入 "./darknet partial yolo-fastest.cfg yolo-fastest.weights yolo-fastest.conv.109 109" 时,显示"Couldn't open file: yolo-fastest.cfg",在根目录下 ls 后也没有看见相关文件,应该怎么解决呢?

juniorWu96 commented 2 years ago

你提供的weights不是在COCO上训练了的吗,那我再用来训练有什么意义呢? @dog-qiuqiu

没意思,所以不要弄了

juniorWu96 commented 2 years ago

感谢您的技术分享!! 请问预训练weights yolo-fastest.conv.109要到哪里下载呢? 多谢!

你好,我也遇到了相同的问题,在输入 "./darknet partial yolo-fastest.cfg yolo-fastest.weights yolo-fastest.conv.109 109" 时,显示"Couldn't open file: yolo-fastest.cfg",在根目录下 ls 后也没有看见相关文件,应该怎么解决呢?

正是因为没有config文件才会报错,没有文件就自己创建一个。从他项目路径下把*.1.1.cfg拷过来,修改下batch_size和yolo层啥的,就行了。

DESXIE commented 2 years ago

@juniorWu96 已经解决啦~不过还是谢谢您!