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

同一设备, 相同模型相同权重相同输入, 在浏览器中调用 tfjs 和 在 微信小程序中调用 tfjs-wechat 插件预测输出的结果差异明显. #127

Closed
109021017 opened this issue May 26, 2022 · 1 comment
Closed

同一设备, 相同模型相同权重相同输入, 在浏览器中调用 tfjs 和 在 微信小程序中调用 tfjs-wechat 插件预测输出的结果差异明显. #127

109021017 opened this issue May 26, 2022 · 1 comment

Comments

@109021017
Copy link

TensorFlow.js 3.17.0
tfjs-wechat plugin 0.2.0
WeChat 8.0.18
WeChat base API version 2.24.1
WeChat IDE version 1.05.2204250

在部分手机(Google Pixel, 三星)中相同模型, 相同输入在小程序插件中输出的结果和浏览器中输出的结果存在明显差异, 导致无法得到正确的预测结果. 而在其他手机中 (iPhone, HUAWEI) 则正常.

疑似和 #114 #77 遇到的问题类似.
@109021017
Copy link
Author

分层 debug 后发现 MaxPooling 的结果导致预测结果不对, 详细描述见 #128

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
1 participant
@109021017