Skip To Main Content
Support Knowledge Base

Is There Any Way to Change the Model Layout When Inferencing with OpenVINO™ Inference Engine?

Content Type: Product Information & Documentation   |   Article ID: 000090386   |   Last Reviewed: 05/20/2022

Description

  • Failed to prepare inputs for a cascade of networks.
  • The output for the first model is in CHW layout but the input for the second model is in NCHW layout.

Resolution

Use InferenceEngine::CNNNetwork::reshape to set new input shapes for your first model that does not have batch dimension into NCHW layout.

Related Products

This article applies to 4 products.
Intel® Xeon Phi™ Processor Software OpenVINO™ toolkit Performance Libraries

Discontinued Products

Intel® Developer Cloud for the Edge