yululu
yululu
I think it's because the number of channels in the pre-trained model he provided was insufficient.
你训练好了嘛?
请问我只能一个一个下载然后传到没有网的机器上吗？
Traceback (most recent call last): File "/home/ma-user/work/PaddleCustomDevice/backends/npu/build/setup.py", line 140, in main() File "/home/ma-user/work/PaddleCustomDevice/backends/npu/build/setup.py", line 99, in main write_custom_op_api_py() File "/home/ma-user/work/PaddleCustomDevice/backends/npu/build/setup.py", line 13, in write_custom_op_api_py op_names = paddle.utils.cpp_extension.extension_utils.load_op_meta_info_and_register_op(libname) File "/home/ma-user/anaconda3/envs/PyTorch-2.1.0/lib/python3.9/site-packages/paddle/utils/cpp_extension/extension_utils.py", line...
> 问题1: 如果机器没有网，确实只能这么干 问题2: 看这个，ZN13custom_kernel14GatherNdKernelIbN3phi13CustomContextEEEvRKT0_RKNS1_11DenseTensorES8_PS6，这个函数没有实现（大概率是没链接到或者没实例化） 第二个问题该怎么解决呢？
https://github.com/Manikandan-Thangaraj-ZS0321/checkbox_detection_opencv 各位可以参考这个项目，把结果加到middle.json里面就可以了