- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Hello,
I encountered a "Failure due to generic standard exception" error when I'm trying to do inference on FPGA with an MXNet model I trained on the GTSDB dataset. The deploy model is running well with the MXNet python API and able to detect traffic signs.
Here I attach the .params and .json files of the deploy model together with the scripts for converting MXNet models and doing inference:
https://drive.google.com/file/d/1uTjev2s8smG4hbzC_tFB96vV3dHeeI6q/view?usp=sharing
The conversion works well yet has a warning saying:
/opt/intel/computer_vision_sdk_fpga_2018.1.267/deployment_tools/model_optimizer/venv/lib/python3.5/site-packages/mxnet/module/base_module.py:54: UserWarning: You created Module with Module(..., label_names=['softmax_label']) but input with name 'softmax_label' is not found in symbol.list_arguments(). Did you mean one of:
relu4_3_scale
data
warnings.warn(msg)
Any ideas on how to solve this problem? Did I miss anything in converting and using the MXNet model? Thanks!
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Link Copied
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Hi Zhongyi,
This seems to be an environment problem, I tried your param file and did the convert and I didn't get any issues. Or you can try the latest release I am using.
Here is my output:
~/Downloads/mxnet$ python3 /opt/intel/computer_vision_sdk_2018.2.319/deployment_tools/model_optimizer/mo_mxnet.py --input_model deploy_gtsdb_ssd_vgg16_reduced_300_510-0210.params --mean_values [125,127,130] --input_shape [1,3,300,510]
Model Optimizer arguments:
Common parameters:
- Path to the Input Model: /home/aplbuild/Downloads/mxnet/deploy_gtsdb_ssd_vgg16_reduced_300_510-0210.params
- Path for generated IR: /home/aplbuild/Downloads/mxnet/.
- IR output name: deploy_gtsdb_ssd_vgg16_reduced_300_510-0210
- Log level: ERROR
- Batch: Not specified, inherited from the model
- Input layers: Not specified, inherited from the model
- Output layers: Not specified, inherited from the model
- Input shapes: [1,3,300,510]
- Mean values: [125,127,130]
- Scale values: Not specified
- Scale factor: Not specified
- Precision of IR: FP32
- Enable fusing: True
- Enable grouped convolutions fusing: True
- Move mean values to preprocess section: False
- Reverse input channels: False
MXNet specific parameters:
- Load the model trained with MXNet with version lower than 1.0.0: False
- Prefix name for args.nd and argx.nd files:
- Pretrained model which will be merged with .nd files:
- Enable save built params file from nd files: False
Model Optimizer version: 1.2.110.59f62983
[ SUCCESS ] Generated IR model.
[ SUCCESS ] XML file: /home/aplbuild/Downloads/mxnet/./deploy_gtsdb_ssd_vgg16_reduced_300_510-0210.xml
[ SUCCESS ] BIN file: /home/aplbuild/Downloads/mxnet/./deploy_gtsdb_ssd_vgg16_reduced_300_510-0210.bin
[ SUCCESS ] Total execution time: 1.25 seconds.
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Hi Mark:
Thank you for the reply! Yes I was able to get the same result. The bug I encountered actually came out during inferencing. Maybe I didn't make myself clear enough. Have you tried the inference script?
Thanks,
Zhongyi
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
I updated OPENVINO yesterday and I got the exact error message of the bug:
Error: Failure due to generic standard exception => Parameter {%relu4_3_norm = fp32[1, 512, 38, 64] param(0) } should have exactly 1 user, not 2
Any ideas on how to solve this?
Thanks,
Zhongyi
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
The problem has been resolved after upgrading from R2 to R3.
- Subscribe to RSS Feed
- Mark Topic as New
- Mark Topic as Read
- Float this Topic for Current User
- Bookmark
- Subscribe
- Printer Friendly Page