Open 60999 opened 4 years ago
请问下你所用GPU的显存是多大?是否有其他进程也占用了显存?
aistudio平台 16/32 G
@60999 是否可以提供下aistudio的链接?我们fork复现看。此外,下面的代码建议放在for循环外,没有必要每次都加载一次module
module = paddlehub.Module(name="stylepro_artistic")
怀疑就是多次载入模型导致的。调用其他模型时候也遇到过这种情况,在升级其他模型的更新版本后没出现过问题,stylepro_artistic 模型后来没有再测试过。 建议其他模型都载入几百次测试下,没准其他模型也有这种问题。
@nepeplwu
This can be used on Android?
@InternetMaster1 As for mobile-end usage, please refer to PaddleLite: https://github.com/PaddlePaddle/Paddle-Lite
@Steffy-zxf @nepeplwu
Any guide on how to convert "stylepro_artistic" to Android using PaddleLite. I don't see any demo present like other projects such as segmentation, etc have. https://github.com/PaddlePaddle/Paddle-Lite-Demo/tree/master/PaddleLite-android-demo
What is the model size and the processing time for style transfer? If you check Tensorflow document, they have mentioned the model file size and time taken. https://blog.tensorflow.org/2020/04/optimizing-style-transfer-to-run-on-mobile-with-tflite.html
What are the similar size and latency values for Paddle StyleTransfer module?
@Steffy-zxf @nepeplwu
Is it possible to run "stylepro_artistic" on our own server, or on the mobile phone as offline code?
On PaddleHub, I only see the API.
We wish to provide stylepro_artistic for offline purpose on mobile phone similar to other libraries like PaddleSeg. Is this possible?
欢迎您反馈PaddleHub使用问题,非常感谢您对PaddleHub的贡献! 在留下您的问题时,辛苦您同步提供如下信息:
2)系统环境:
aistudio平台GPU环境
stylepro_artistic 使用GPU出错,在转换多张照片之后.
代码: `def stylepro_artistic(fore_image_path,paddlehub_out_path):
1.指定待预测图片路径,遍历循环抠图 保存到 paddlehub_out_path
stylepro_artistic(front_path,HUMANSEG_SPACE) `