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
复现流程 运行命令:./paddle_lite_ocr rec ch_ppocr_mobile_v2.0_rec_slim_opt.nb arm8 INT8 10 1 vis.jpg ppocr_keys_v1.txt config.txt
注意ch_ppocr_mobile_v2.0_rec_slim_opt.nb只是在使用opt工具转换时没改名字,实际上还是使用ch_PP-OCRv4_rec_server_train训练出的模型。
以下是运行结果: `[I 11/21 19:41:16.950 ...addle-Lite-2.12/lite/core/device_info.cc:1275 Setup] ARM multiprocessors name: HARDWARE : ROCKCHIP RK3568 EVB1 DDR4 V10 BOARD
[I 11/21 19:41:16.951 ...addle-Lite-2.12/lite/core/device_info.cc:1276 Setup] ARM multiprocessors number: 4 [I 11/21 19:41:16.951 ...addle-Lite-2.12/lite/core/device_info.cc:1278 Setup] ARM multiprocessors ID: 0, max freq: 1992, min freq: 1992, cluster ID: 0, CPU ARCH: A55 [I 11/21 19:41:16.951 ...addle-Lite-2.12/lite/core/device_info.cc:1278 Setup] ARM multiprocessors ID: 1, max freq: 1992, min freq: 1992, cluster ID: 0, CPU ARCH: A55 [I 11/21 19:41:16.951 ...addle-Lite-2.12/lite/core/device_info.cc:1278 Setup] ARM multiprocessors ID: 2, max freq: 1992, min freq: 1992, cluster ID: 0, CPU ARCH: A55 [I 11/21 19:41:16.951 ...addle-Lite-2.12/lite/core/device_info.cc:1278 Setup] ARM multiprocessors ID: 3, max freq: 1992, min freq: 1992, cluster ID: 0, CPU ARCH: A55 [I 11/21 19:41:16.951 ...addle-Lite-2.12/lite/core/device_info.cc:1284 Setup] L1 DataCache size is: [I 11/21 19:41:16.951 ...addle-Lite-2.12/lite/core/device_info.cc:1286 Setup] 32 KB [I 11/21 19:41:16.951 ...addle-Lite-2.12/lite/core/device_info.cc:1286 Setup] 32 KB [I 11/21 19:41:16.951 ...addle-Lite-2.12/lite/core/device_info.cc:1286 Setup] 32 KB [I 11/21 19:41:16.951 ...addle-Lite-2.12/lite/core/device_info.cc:1286 Setup] 32 KB [I 11/21 19:41:16.951 ...addle-Lite-2.12/lite/core/device_info.cc:1288 Setup] L2 Cache size is: [I 11/21 19:41:16.951 ...addle-Lite-2.12/lite/core/device_info.cc:1290 Setup] 512 KB [I 11/21 19:41:16.951 ...addle-Lite-2.12/lite/core/device_info.cc:1290 Setup] 512 KB [I 11/21 19:41:16.951 ...addle-Lite-2.12/lite/core/device_info.cc:1290 Setup] 512 KB [I 11/21 19:41:16.951 ...addle-Lite-2.12/lite/core/device_info.cc:1290 Setup] 512 KB [I 11/21 19:41:16.951 ...addle-Lite-2.12/lite/core/device_info.cc:1292 Setup] L3 Cache size is: [I 11/21 19:41:16.951 ...addle-Lite-2.12/lite/core/device_info.cc:1294 Setup] 0 KB [I 11/21 19:41:16.951 ...addle-Lite-2.12/lite/core/device_info.cc:1294 Setup] 0 KB [I 11/21 19:41:16.951 ...addle-Lite-2.12/lite/core/device_info.cc:1294 Setup] 0 KB [I 11/21 19:41:16.951 ...addle-Lite-2.12/lite/core/device_info.cc:1294 Setup] 0 KB [I 11/21 19:41:16.951 ...addle-Lite-2.12/lite/core/device_info.cc:1296 Setup] Total memory: 1998392KB [I 11/21 19:41:16.951 ...addle-Lite-2.12/lite/core/device_info.cc:1297 Setup] SVE2 support: 0 [I 11/21 19:41:16.951 ...addle-Lite-2.12/lite/core/device_info.cc:1298 Setup] SVE2 f32mm support: 0 [I 11/21 19:41:16.951 ...addle-Lite-2.12/lite/core/device_info.cc:1299 Setup] SVE2 i8mm support: 0 [I 11/21 19:41:17.161 ...e-Lite-2.12/lite/operators/squeeze_op.cc:124 AttachImpl] PaddleLiteV2.12 remove XShape OutputTensor for SqueezeOp.`
问题描述:好像是说在PaddleLiteV2.12时移除了XShape OutputTensor导致的
报错图片:
-做出的尝试:我尝试过替换成paddle-lite V2.13 V2.14这些预测库,结果都不行,也试过换成低版本的PaddleLite,如V2.10,2.10等,但是因为缺少paddle_use_kernels.h编译不过去。
目的:因为之间没接触过模型训练和识别类的东西,自己摸索到这里就不知道怎么下手了。希望有大佬能给我提供一些解决方法或者意见,万分感谢!!!
The text was updated successfully, but these errors were encountered:
原始模型太老了,旧版本paddle导出的模型中会带XShape。建议用paddle2.6版本导出原始模型
Sorry, something went wrong.
zhupengyang
No branches or pull requests
1)Paddle Lite 版本:paddle-lite V2.12
2)Host 环境:RK3568
3) 内核信息Linux 4.19.232#5 SMP Tue Nov aarch64 GNU/Linux
4) 训练环境:PaddleOCR V2.9
1)模型名称 : ch_PP-OCRv4_rec_server_train
2)配置文件:ch_PP-OCRv4_rec_hgnet.yml
复现流程
运行命令:./paddle_lite_ocr rec ch_ppocr_mobile_v2.0_rec_slim_opt.nb arm8 INT8 10 1 vis.jpg ppocr_keys_v1.txt config.txt
注意ch_ppocr_mobile_v2.0_rec_slim_opt.nb只是在使用opt工具转换时没改名字,实际上还是使用ch_PP-OCRv4_rec_server_train训练出的模型。
以下是运行结果:
`[I 11/21 19:41:16.950 ...addle-Lite-2.12/lite/core/device_info.cc:1275 Setup] ARM multiprocessors name: HARDWARE : ROCKCHIP RK3568 EVB1 DDR4 V10 BOARD
[I 11/21 19:41:16.951 ...addle-Lite-2.12/lite/core/device_info.cc:1276 Setup] ARM multiprocessors number: 4
[I 11/21 19:41:16.951 ...addle-Lite-2.12/lite/core/device_info.cc:1278 Setup] ARM multiprocessors ID: 0, max freq: 1992, min freq: 1992, cluster ID: 0, CPU ARCH: A55
[I 11/21 19:41:16.951 ...addle-Lite-2.12/lite/core/device_info.cc:1278 Setup] ARM multiprocessors ID: 1, max freq: 1992, min freq: 1992, cluster ID: 0, CPU ARCH: A55
[I 11/21 19:41:16.951 ...addle-Lite-2.12/lite/core/device_info.cc:1278 Setup] ARM multiprocessors ID: 2, max freq: 1992, min freq: 1992, cluster ID: 0, CPU ARCH: A55
[I 11/21 19:41:16.951 ...addle-Lite-2.12/lite/core/device_info.cc:1278 Setup] ARM multiprocessors ID: 3, max freq: 1992, min freq: 1992, cluster ID: 0, CPU ARCH: A55
[I 11/21 19:41:16.951 ...addle-Lite-2.12/lite/core/device_info.cc:1284 Setup] L1 DataCache size is:
[I 11/21 19:41:16.951 ...addle-Lite-2.12/lite/core/device_info.cc:1286 Setup] 32 KB
[I 11/21 19:41:16.951 ...addle-Lite-2.12/lite/core/device_info.cc:1286 Setup] 32 KB
[I 11/21 19:41:16.951 ...addle-Lite-2.12/lite/core/device_info.cc:1286 Setup] 32 KB
[I 11/21 19:41:16.951 ...addle-Lite-2.12/lite/core/device_info.cc:1286 Setup] 32 KB
[I 11/21 19:41:16.951 ...addle-Lite-2.12/lite/core/device_info.cc:1288 Setup] L2 Cache size is:
[I 11/21 19:41:16.951 ...addle-Lite-2.12/lite/core/device_info.cc:1290 Setup] 512 KB
[I 11/21 19:41:16.951 ...addle-Lite-2.12/lite/core/device_info.cc:1290 Setup] 512 KB
[I 11/21 19:41:16.951 ...addle-Lite-2.12/lite/core/device_info.cc:1290 Setup] 512 KB
[I 11/21 19:41:16.951 ...addle-Lite-2.12/lite/core/device_info.cc:1290 Setup] 512 KB
[I 11/21 19:41:16.951 ...addle-Lite-2.12/lite/core/device_info.cc:1292 Setup] L3 Cache size is:
[I 11/21 19:41:16.951 ...addle-Lite-2.12/lite/core/device_info.cc:1294 Setup] 0 KB
[I 11/21 19:41:16.951 ...addle-Lite-2.12/lite/core/device_info.cc:1294 Setup] 0 KB
[I 11/21 19:41:16.951 ...addle-Lite-2.12/lite/core/device_info.cc:1294 Setup] 0 KB
[I 11/21 19:41:16.951 ...addle-Lite-2.12/lite/core/device_info.cc:1294 Setup] 0 KB
[I 11/21 19:41:16.951 ...addle-Lite-2.12/lite/core/device_info.cc:1296 Setup] Total memory: 1998392KB
[I 11/21 19:41:16.951 ...addle-Lite-2.12/lite/core/device_info.cc:1297 Setup] SVE2 support: 0
[I 11/21 19:41:16.951 ...addle-Lite-2.12/lite/core/device_info.cc:1298 Setup] SVE2 f32mm support: 0
[I 11/21 19:41:16.951 ...addle-Lite-2.12/lite/core/device_info.cc:1299 Setup] SVE2 i8mm support: 0
[I 11/21 19:41:17.161 ...e-Lite-2.12/lite/operators/squeeze_op.cc:124 AttachImpl] PaddleLiteV2.12 remove XShape OutputTensor for SqueezeOp.`
问题描述:好像是说在PaddleLiteV2.12时移除了XShape OutputTensor导致的
报错图片:
-做出的尝试:我尝试过替换成paddle-lite V2.13 V2.14这些预测库,结果都不行,也试过换成低版本的PaddleLite,如V2.10,2.10等,但是因为缺少paddle_use_kernels.h编译不过去。
目的:因为之间没接触过模型训练和识别类的东西,自己摸索到这里就不知道怎么下手了。希望有大佬能给我提供一些解决方法或者意见,万分感谢!!!
The text was updated successfully, but these errors were encountered: