- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Hello,
I was trying to convert the yolo v2 model to IR representation.
In the YOLO cfg file, I could see softmax is 0 in the detection layer. After setting 0 in do_softmax param in the region layer in the JSON file, I could see the following error in the conversion of IR representation.
[ ERROR ] Cannot infer shapes or values for node "output/YoloRegion".
[ ERROR ] 'do_softmax'
[ ERROR ]
[ ERROR ] It can happen due to bug in custom shape infer function <function RegionYoloOp.regionyolo_infer at 0x7fa37426a598>.
[ 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 ] Stopped shape/value propagation at "output/YoloRegion" node.
Can you please help me to find the error?
Thanks in advance.
Link Copied

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