-
Notifications
You must be signed in to change notification settings - Fork 1.6k
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-Lite通过X2Paddle转化出的nb模型出错 #10506
Comments
您好,从报错信息来看,得不到有用的信息。 转换方式的分辨率一般是与ONNX一致的,精度默认是fp32。 如果自己定义精度,可参考https://www.paddlepaddle.org.cn/lite/v2.12/demo_guides/android_app_demo.html ,使用fp16精度进行部署。 |
可以使用x2paddle先保存成paddle的pd_model模型在cpu上运行 这步我之前验证了(用python),没有问题的。 |
我这边使用的yolov5的pth模型,转化成onnx之后,通过paddle-lite (2.13rc0)与 X2Paddle(1.4.1) 转化成了nb文件,试图部署在安卓环境下,报错
使用的命令是 x2paddle --framework=onnx --model=onnx_model.onnx --save_dir=pd_model --to_lite=True --lite_valid_places=arm --lite_model_type=naive_buffer 不知道是什么问题?以及问一句,这种转化方式的分辨率是和onnx一致么?精度是多少呢?可以自己定义精度么?
The text was updated successfully, but these errors were encountered: