Support Knowledge Base

Unable to Optimize Converted Custom YOLOv5 ONNX Model into INT8 Intermediate Representation (IR)

Content Type: Error Messages | Article ID: 000092780 | Last Reviewed: 11/16/2022

Description Resolution

Description

Converted custom YOLOv5 ONNX model into FP32 IR:
mo --input_model model.onnx
Ran Post Training Optimization Tool (POT) with the FP32 IR.
Received error:
Error: AssertionError: Incorrect mapping then_graph outputs with Result_6617 outputs! Can't find port with ID 4 in If operation.

Visualize the ONNX model in Netron.
Search the keyword Transpose in Netron.
Obtain the convolution node name.
Specify the convolution node name when converting ONNX model into IR:
mo --input_model model.onnx --output <conv_node_name>
Run POT with IR:
pot -c model.json

This article applies to 3 products.

Intel® Xeon Phi™ Processor Software OpenVINO™ toolkit Performance Libraries

Contact support