aleksss
aleksss
Hi @serizba, Yes, I finally figured it out. Based on the c_api_experimental.h: ``` std::string checkpoint_path = path_to_model + "/variables/variables"; //path_to_model must be absolute path const char * c = checkpoint_path.c_str();...
when I want to extract the data using `var.get_data()` I run into the sigfpe (arithmetic error) on this line from tensor.h: `size_t size = TF_TensorByteSize(res_tensor) / TF_DataTypeSize(TF_TensorType(res_tensor));` I would really...
Hi @DwayneDuane, I have the same problem, did you maybe find any solution? I would appreciate any help! :)
no, I was just using Windows for building libcoral, which scripts should I use exactly or how to build it with Bazel?
I ran docker_build.bat and got .exe files in the out directory, how can I generate the .lib files? My bazel-out folder is empty
This is my out directory: [out.zip](https://github.com/google-coral/libcoral/files/7692381/out.zip)
Hi, I tested it but unfortunately the training process hangs and does not output any information about loss or accuracy like it happens in case of edgetpu version.