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.

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

这个nncase里的yolov5的验证转换精确度的里边用到的bin文件是哪里来的?如何制作?? #65

Open
Culturenotes opened this issue Jul 10, 2024 · 5 comments
Assignees

Comments

@Culturenotes
Copy link

Help

在这个目录里
k230_sdk/src/big/nncase/examples/object_detect/data/input_fp32.bin

@curioyang
Copy link
Member

curioyang commented Jul 11, 2024

同目录下不是有原图么,用Python读之后做前处理,然后numpy转bin

目前的demo里bin文件是不需要的,是图片直接作为输入的,具体可以看代码

@Culturenotes
Copy link
Author

scripts/下的yolov5_onnx_simu.py验证精度是输入的bin 我直接改成读取图片就行呗?

@curioyang
Copy link
Member

@Culturenotes 这俩目录不是一个东西的
你如果只是要做一下精读测试,你直接用随机数也行的
如果要用真是数据测精读,那就自己把图片处理成bin, 步骤就是上面那个

@Culturenotes
Copy link
Author

还有个问题,这个nncase导出的这个量化模型的输出需要反量化到f32么?还是它默认输出就是f32的,如果反量化回f32,这个反量化参数如何获取?

@curioyang
Copy link
Member

就是f32, 如果要输出定点数是需要额外配置的,不推荐

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

4 participants