When running the inception v3 model, an error occurred in ClassifyImageTask.java:56.
Tensor shape can not be null or empty.
Posted: Mon, 2017-09-04 06:16
When running the inception v3 model, an error occurred in ClassifyImageTask.java:56.
Opinions expressed in the content posted here are the personal opinions of the original authors, and do not necessarily reflect those of Qualcomm Incorporated or its subsidiaries (“Qualcomm”). The content is provided for informational purposes only and is not meant to be an endorsement or representation by Qualcomm or any other party. This site may also provide links or references to non-Qualcomm sites and resources. Qualcomm makes no representations, warranties, or other commitments whatsoever about any non-Qualcomm sites or third-party resources that may be referenced, accessible from, or linked to this site.
Hi ,
I am facing similar issue with snpe.1.15.0 version.
Can anyone help in figuring out this issue?
hi snpe-tensorflow-to-dlc input_dim cann't be null or emplty??
Hi cljustb2008,
If issue is in sample android application, we must need to setup environment of inceptionv3 for sample app. It will copy the required assets into the android source's directory. Please before building the app make sure all the required assets are inplace. The source for getting the input shape of the model is written into sample application. This issue may cause because of unavalability of the required assets.
Please follow the below docs to setup the enviroment for inceptionv3:
Follow the steps from Build Example android App in Getting Started of Neural Processing SDK for AI