We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
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
# 引用Paddlelite预测库 from paddlelite.lite import * # 1. 创建opt实例 opt=Opt() # 2. 指定输入模型地址 #opt.set_model_dir("./Db") opt.set_model_file("./Db/PaddLeOCR_Db.bin") opt.set_param_file("./Db/PaddLeOCR_Db.param") # 3. 指定转化类型: arm、x86、opencl、npu opt.set_valid_places("arm") # 4. 指定模型转化类型: naive_buffer、protobuf opt.set_model_type("naive_buffer") # 4. 输出模型地址 opt.set_optimize_out("./Output/det") # 5. 执行模型优化 opt.run()
...\lite\core\model\general\program_desc.cc:51 paddle::lite::general::ProgramDesc::GetBlock] Check failed: (idx < static_cast<int32_t>(BlocksSize())): 0!<0 idx >= blocks.size()
The text was updated successfully, but these errors were encountered:
看样子是模型加载和解析过程中的问题,通过BlocksSize()[https://github.com/PaddlePaddle/Paddle-Lite/blob/9b53b4a39722bbf29bdf9b799c1ab9e28cd93e4d/lite/core/model/general/program_desc.cc#L51]获取的结果为0,这似乎不太符合预期,请问你.bin和.param文件是从哪里导出的
Sorry, something went wrong.
这些文件是从一个安卓程序里的PaddleOCR库导出来的
似乎是模型文件的问题,paddle模型文件应是.pdmodel格式, 而不是.bin格式,建议再确认一下模型正确性,https://www.paddlepaddle.org.cn/lite/develop/user_guides/model_visualization.html
您可以在上面的模型信息里的模型链接里下载我所导出的模型文件,可以请您帮忙查看一下是什么类型的模型么?
你的模型看起来是经过某种处理之后的格式,我不知道你是怎么处理的,理论上PaddleOCR本身导出的模型应该是pdmodel和pdiparams格式的文件,所以应该是PaddleOCR处理的结果不对,建议你先自查一下模型处理过程,或者在PaddleOCR官方repo寻找帮助,https://github.com/PaddlePaddle/PaddleOCR
iosmers
No branches or pull requests
1)Paddle Lite 版本:v2.12
2)Host 环境:Windows10 + Anaconda3
1)模型名称 PaddleOCR
2)模型链接 PaddleOCR.zip
The text was updated successfully, but these errors were encountered: