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

paddle android capi 加载模型太慢 #3477

Closed
bushidonggua opened this issue Aug 14, 2017 · 4 comments
Closed

paddle android capi 加载模型太慢 #3477

bushidonggua opened this issue Aug 14, 2017 · 4 comments
Assignees

Comments

@bushidonggua
Copy link

两个接口在我的安卓机上耗时:
paddle_init= 1660ms
paddle_gradient_machine_create_for_inference_with_parameters time=146978ms
再加上一些模型资源拷贝,加解密,处理等,整个预测开始工作的时间要上3分钟了,在移动端无法忍受!

安卓机型号:三星Note4
模型尺寸:31M
模型配置:v1版本的small_vgg网络
image

@hedaoyuan
Copy link
Contributor

@Xreki Please check the time-consuming issue of the paddle_gradient_machine_create_for_inference_with_parameters api. I think the time(146978ms) is not right.
@bushidonggua Can you share your code, about how did you test the time of these two interfaces?

@bushidonggua
Copy link
Author

@hedaoyuan 不好意思,找到原因了,模型放在assert里面会导致加载巨慢

@Xreki
Copy link
Contributor

Xreki commented Aug 15, 2017

@bushidonggua 你的意思是从assets里面读取模型,这个过程比较耗时?

@bushidonggua
Copy link
Author

@Xreki 是的,我换了一种方式就好了

@Xreki Xreki closed this as completed Sep 21, 2017
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

3 participants