You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
This discussion was converted from issue #11348 on May 25, 2024 08:02.
Heading
Bold
Italic
Quote
Code
Link
Numbered list
Unordered list
Task list
Attach files
Mention
Reference
Menu
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
-
请提供下述完整信息以便快速定位问题/Please provide the following information to quickly locate the problem
从官网下载的ocr v3模型 通过opt转换工具:
from paddlelite.lite import *
opt = Opt()
opt.set_model_dir("./ch_ppocr_mobile_v2_0_rec_v2_0")
opt.set_valid_places("huawei_kirin_npu,arm")
opt.set_model_type("naive_buffer")
opt.set_optimize_out("ch_PP-OCRv2_rec")
opt.run()
通过这种方式,转换了3个文件 rec.nb,det.nb,cls.nb。
下载PaddleLite官网支持华为机型的预编译库:inference_lite_lib.android.armv8.huawei_kirin_npu.with_cv.with_extra.with_log.tiny_publish.tar
在华为麒麟990上部署后,
加载模型正常没有报错。
但在执行推理识别时报错:
[F 12/ 6 18:32:59.410 ...le-Lite/lite/kernels/nnadapter/engine.cc:294 Engine] Check failed: (device_names.size() > 0): 0!>0 No device specified.
terminating with uncaught exception of type paddle::lite::PaddleLiteException: Paddle-Lite C++ Exception:
[F 12/ 6 18:32:59.410 ...le-Lite/lite/kernels/nnadapter/engine.cc:294 Engine] Check failed: (device_names.size() > 0): 0!>0 No device specified.
程序直接闪退。
转换模型时 不加huawei_kirin_npu类型后 可以正常推理。但是推理速度慢。该怎么办才能使用上npu推理呢?
急需大佬帮助❤️❤️❤️
Beta Was this translation helpful? Give feedback.
All reactions