Hi, I am testing my DNN model on linux using version 2018.3.343 of OpenVINO. I have installed OpenVINO correctly refering to the OpenVINO Installation Guide. But while running model-optimizer, internal error occurs and the log is following. On previous version 2018.2.319, always succeeded.
Link Copied
Hi,
Do you mind attaching your model's files so I can reproduce the issue on my end and providing the command line you used?
Kind Regards,
Monique Jones
I have a similar issue when I am trying to run a Mxnet (Resnet50 model).
Here is the bug report.
Model Optimizer version: unknown version
[ ERROR ] -------------------------------------------------
[ ERROR ] ----------------- INTERNAL ERROR ----------------
[ ERROR ] Unexpected exception happened.
[ ERROR ] Please contact Model Optimizer developers and forward the following information:
[ ERROR ] 3
[ ERROR ] Traceback (most recent call last):
File "/home/nfawad/openvino/dldt/model-optimizer/mo/main.py", line 312, in main
return driver(argv)
File "/home/nfawad/openvino/dldt/model-optimizer/mo/main.py", line 278, in driver
ret_res = mo_mxnet.driver(argv, argv.input_model, model_name, argv.output_dir)
File "/home/nfawad/openvino/dldt/model-optimizer/mo/pipeline/mx.py", line 95, in driver
convert_batch_norm(graph)
File "/home/nfawad/openvino/dldt/model-optimizer/mo/middle/passes/fusing/decomposition.py", line 48, in convert_batch_norm
mean = node.in_node(3)
File "/home/nfawad/openvino/dldt/model-optimizer/mo/graph/graph.py", line 139, in in_node
return self.in_nodes(control_flow=control_flow)[key]
KeyError: 3
[ ERROR ] ---------------- END OF BUG REPORT --------------
[ ERROR ] -------------------------------------------------
Command line used:
python3 mo.py --framework mxnet --input_model mxnetmodels/resnet50/resnet-50-0000.params --input_shape [1,3,224,224]
Dear Nofil F.,
From where are you getting this MxNet model ? Are you following The MO MxNet Conversion Doc instructions ?
Thanks,
Shubha
For more complete information about compiler optimizations, see our Optimization Notice.