Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

大神，我使用官方提供的LResNet100E-IR模型转化为ncnn模型后测试精度很低？ #5

Open
wkj0121 opened this issue Aug 21, 2019 · 3 comments
Open

大神，我使用官方提供的LResNet100E-IR模型转化为ncnn模型后测试精度很低？ #5

wkj0121 opened this issue Aug 21, 2019 · 3 comments

Comments

@wkj0121
Copy link

wkj0121 commented Aug 21, 2019

insightface Model Zoo LResNet100E-IR,ArcFace@ms1m-refine-v2 model-r100-ii 转换为ncnn模型加载测试 Similarity: 0.0810913,哪里的问题呢？
@wkj0121 wkj0121 changed the title 大神，我使用官方提供的LResNet100E-IR模型转化为ncnn模型后测试精度很低？为什么呢？ 大神，我使用官方提供的LResNet100E-IR模型转化为ncnn模型后测试精度很低？ Aug 21, 2019
@AI-LLM2
Copy link

AI-LLM2 commented Aug 22, 2019

@wkj0121 请问官方的模型你是用什么转的？mxnet2ncnn.exe，我用自己编译的转出来，不能运行，对比网络结构相差很大。

Detection Time: 0.0985302s
Detection Time: 0.182536s
layer _copy not exists or registered
network graph not ready
find_blob_index_by_name data failed
find_blob_index_by_name fc1 failed
段错误 (核心已转储)

@wkj0121
Copy link
Author

wkj0121 commented Aug 23, 2019

@HaynesRuan 是的 用mxnet2ncnn转的
_copy layer问题需要对ncnn源码修改增加op对_copy的操作，详见：Tencent/ncnn#417

@AI-LLM2
Copy link

AI-LLM2 commented Aug 30, 2019

@wkj0121 非常感谢你的指导，请问LResNet100E-IR精度低的问题有什么解决思路吗？

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@AI-LLM2 @wkj0121