Search code examples
pythonwindowstensorflowopenvino

Internal error while converting TensorFlow Faster R-CNN frozen graph to intel openVINO framework

I installed intel distribution of openVINO to run inference on the neural compute stick v2. This was successful with our home-trained TensorFlow SSD model. However the stick did not handle any of our Faster R-CNN architectures. In order to solve this problem I tried to convert the TensorFlow1.13 Faster R-CNN resnet101 model to the OpenVINO framework using the model optimizer they include in the windows 10 installation. During the conversion I got the following error:

[ ERROR ]  -------------------------------------------------
[ ERROR ]  ----------------- INTERNAL ERROR ----------------
[ ERROR ]  Unexpected exception happened.
[ ERROR ]  Please contact Model Optimizer developers and forward the following information:
[ ERROR ]  [Errno 13] Permission denied: 'C:\\Program Files (x86)\\IntelSWTools\\openvino\\deployment_tools\\model_optimizer\\.\\frozen_inference_graph.bin'
[ ERROR ]  Traceback (most recent call last):
  File "C:\Program Files (x86)\IntelSWTools\openvino\deployment_tools\model_optimizer\mo\main.py", line 309, in main
    ret_code = driver(argv)
  File "C:\Program Files (x86)\IntelSWTools\openvino\deployment_tools\model_optimizer\mo\main.py", line 270, in driver
    ret_res = emit_ir(prepare_ir(argv), argv)
  File "C:\Program Files (x86)\IntelSWTools\openvino\deployment_tools\model_optimizer\mo\main.py", line 254, in emit_ir
    meta_info=get_meta_info(argv))
  File "C:\Program Files (x86)\IntelSWTools\openvino\deployment_tools\model_optimizer\mo\pipeline\common.py", line 223, in prepare_emit_ir
    serialize_constants(graph, bin_file)
  File "C:\Program Files (x86)\IntelSWTools\openvino\deployment_tools\model_optimizer\mo\back\ie_ir_ver_2\emitter.py", line 43, in serialize_constants
    with open(bin_file_name, 'wb') as bin_file:
PermissionError: [Errno 13] Permission denied: 'C:\\Program Files (x86)\\IntelSWTools\\openvino\\deployment_tools\\model_optimizer\\.\\frozen_inference_graph.bin'

 
[ ERROR ]  ---------------- END OF BUG REPORT --------------
[ ERROR ]  -------------------------------------------------

Can anyone help me out? We would like to run TensorFlow Faster R-CNN on intel's neural compute stick v2.

Solution

  • This is an issue with writing permissions for the directory that you are converting the model. Since you are using Windows, I would suggest two approaches to you:

    • Open Command Prompt and run as Administrator.
    • Change to a directory that doesn't need Administrator rights to write to it, for example C:\Users\your-username\Desktop