- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
When i used openvino(2020.2) convert retinaface.onnx (Opset 11) to Ir model, the Resize op had erros;
File "D:\IntelSWTools\openvino_2020.2.117\deployment_tools\model_optimizer\extensions\ops\upsample.py", line 66, in upsample_infer
node.out_node().shape = input_shape * node.in_node(1).value
ValueError: operands could not be broadcast together with shapes (4,) (0,).
you can download my model,and recurre the problems. think you very much!
Link Copied
2 Replies
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Hi,
As per the supported layers for onnx, the resize operation is supported with opset-10. Could you please use the opset-10 version and let us know the results.
Hope this helps.
Regards,
Ram prasad
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
It is very helpful to me! think you very much!

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