$paddle_lite_opt --model_dir=./inference_model/yolov3_mobilenet_v1_roadsign --valid_targets=arm --optimize_out_type=naive_buffer --optimize_out=yolov3_mobilenet_v1_roadsign_paddle_lite_opt
WARNING: Logging before InitGoogleLogging() is written to STDERR
I0305 02:28:37.414717 60546 cxx_api.cc:262] Load model from file.
F0305 02:28:37.435568 60546 model_parser.cc:67] Check failed: version == 0U (22045 vs. 0) Only version 0 is supported
Check failure stack trace:
Aborted (core dumped)
6条答案
按热度按时间kyvafyod1#
您好，我们已经收到了您的问题，会安排技术人员尽快解答您的问题，请耐心等待。请您再次检查是否提供了清晰的问题描述、复现代码、环境&版本、报错信息等。同时，您也可以通过查看官网文档、常见问题、历史Issue来寻求解答。祝您生活愉快～
Hi! We've received your issue and please be patient to get responded. We will arrange technicians to answer your questions as soon as possible. Please make sure that you have posted enough message to demo your request. You may also check out the API，FAQ and Github Issue to get the answer.Have a nice day!
bq9c1y662#
你的paddle模型应该是combined形式的,应该用--model_file和--param_file。不应该用--model_dir
olmpazwi3#
我用paddle_lite_opt 转换模型成功了，但是放到PaddleDetection的android工程里去，app加载模型的时候崩溃了，log上看不到任何错误，
咋回事呢？
zd287kbt4#
你可以编译lite时打开with_log=on选项，查看具体的的错误log。模型加载不成功一般是生成nb工具和lite库版本不一致或者是有lite不支持的层。
am46iovg5#
paddle_lite支持yolov3_mobilenet_v1模型吗？就是PaddleDetection官方教程里用的那个模型。
mi7gmzs66#
the version of opt that transformed this model is not consistent with current Paddle-Lite version. 我这个确实是提示两个版本不一至，但这个怎么处理呢