- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Hi All,
I am trying to convert a mxnet model to IR. but meet some error regarding shape. the error message is as below. the command is python3 mo_mxnet.py --input_model model_algo_1-0000.params --input_shape [1,3,512,512] --data_type=FP16 . enclosed is corresponding json file. Pls comment how to fix the issue.
Model Optimizer version: 2019.3.0-375-g332562022
[ ERROR ] Size of weights 221184 does not match kernel shape: [ 36 2048 3 3]
Possible reason is wrong channel number in input shape
[ ERROR ] Cannot infer shapes or values for node "_plus15_cls_pred_conv".
[ ERROR ] Cannot reshape weights to kernel shape
[ ERROR ]
[ ERROR ] It can happen due to bug in custom shape infer function <function Convolution.infer at 0x7f4a93621e18>.
[ ERROR ] Or because the node inputs have incorrect values/shapes.
[ ERROR ] Or because input shapes are incorrect (embedded to the model or passed via --input_shape).
[ ERROR ] Run Model Optimizer with --log_level=DEBUG for more information.
[ ERROR ] Cannot reshape weights to kernel shape
Stopped shape/value propagation at "_plus15_cls_pred_conv" node.
For more information please refer to Model Optimizer FAQ (https://docs.openvinotoolkit.org/latest/_docs_MO_DG_prepare_model_Model_Optimizer_FAQ.html), question #38.
Exception occurred during running replacer "REPLACEMENT_ID" (<class 'extensions.middle.PartialInfer.PartialInfer'>): Cannot reshape weights to kernel shape
Stopped shape/value propagation at "_plus15_cls_pred_conv" node.
For more information please refer to Model Optimizer FAQ (https://docs.openvinotoolkit.org/latest/_docs_MO_DG_prepare_model_Model_Optimizer_FAQ.html), question #38.
Link Copied
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Sorry I don't have better experience of it. Hope someone will help you. Thanks!

- Subscribe to RSS Feed
- Mark Topic as New
- Mark Topic as Read
- Float this Topic for Current User
- Bookmark
- Subscribe
- Printer Friendly Page