- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Hi,
I use model optimizer to to generate IR files from caffe model.
I got an error like this:
[ 2018-05-22 18:16:16,146 ] [ ERROR ] [ main:230 ] ------------------------------------------------- [ 2018-05-22 18:16:16,146 ] [ ERROR ] [ main:231 ] ----------------- INTERNAL ERROR ---------------- [ 2018-05-22 18:16:16,146 ] [ ERROR ] [ main:232 ] Unexpected exception happened. [ 2018-05-22 18:16:16,146 ] [ ERROR ] [ main:233 ] Please contact Model Optimizer developers and forward the following information: [ 2018-05-22 18:16:16,147 ] [ ERROR ] [ main:234 ] 'PriorBoxParameter' object has no attribute 'width' [ 2018-05-22 18:16:16,147 ] [ ERROR ] [ main:235 ] Traceback (most recent call last): File "/opt/intel/computer_vision_sdk_2018.0.234/deployment_tools/model_optimizer/mo/main.py", line 222, in main return driver(argv) File "/opt/intel/computer_vision_sdk_2018.0.234/deployment_tools/model_optimizer/mo/main.py", line 202, in driver custom_layers_mapping_path=custom_layers_mapping_path) File "/opt/intel/computer_vision_sdk_2018.0.234/deployment_tools/model_optimizer/mo/pipeline/caffe.py", line 106, in driver extract_node_attrs(graph, lambda node: caffe_extractor(node, check_for_duplicates(caffe_type_extractors))) File "/opt/intel/computer_vision_sdk_2018.0.234/deployment_tools/model_optimizer/mo/front/extractor.py", line 413, in extract_node_attrs supported, new_attrs = extractor(Node(graph, node)) File "/opt/intel/computer_vision_sdk_2018.0.234/deployment_tools/model_optimizer/mo/pipeline/caffe.py", line 106, in <lambda> extract_node_attrs(graph, lambda node: caffe_extractor(node, check_for_duplicates(caffe_type_extractors))) File "/opt/intel/computer_vision_sdk_2018.0.234/deployment_tools/model_optimizer/mo/front/caffe/extractor.py", line 127, in caffe_extractor result.update(caffe_type_extractors[name](node)) File "/opt/intel/computer_vision_sdk_2018.0.234/deployment_tools/model_optimizer/mo/front/common/register_custom_ops.py", line 95, in <lambda> node, cls, disable_omitting_optional, enable_flattening_optional_params), File "/opt/intel/computer_vision_sdk_2018.0.234/deployment_tools/model_optimizer/mo/front/common/register_custom_ops.py", line 27, in extension_extractor supported = ex.extract(node) File "/opt/intel/computer_vision_sdk_2018.0.234/deployment_tools/model_optimizer/extensions/front/caffe/priorbox_ext.py", line 42, in extract 'width': list(param.width), AttributeError: 'PriorBoxParameter' object has no attribute 'width' [ 2018-05-22 18:16:16,147 ] [ ERROR ] [ main:236 ] ---------------- END OF BUG REPORT -------------- [ 2018-05-22 18:16:16,147 ] [ ERROR ] [ main:237 ] -------------------------------------------------
My CVSDK version is 2018.0.234.
My model is trained by intel caffe.
Attachment is my caffe.proto from intel caffe. There is no "width" attribute in PriorBoxParameter.
Best regards,
Hj
Link Copied
2 Replies
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Hi hsing,
Thanks for posting the issue, we will escalate to fix.
Best regards,
Fiona
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Hi hsing,
We will fix it in next release, currently you may can avoid error by modifying the source code of priorbox_ext.py, removing attribute 'width' & 'height' or any other attributes, you are not set for PriorBoxLayer in your prototxt.
Best regards,
Fiona
Reply
Topic Options
- Subscribe to RSS Feed
- Mark Topic as New
- Mark Topic as Read
- Float this Topic for Current User
- Bookmark
- Subscribe
- Printer Friendly Page