I'm having trouble converting a frozen tf model to IR. It's a Multi Column CNN arhitecture. Frozen model can be found here: https://github.com/RobertStancu/CrowdCount. Here is the repository from where I've trained and frozen the model: https://github.com/uestcchicken/crowd-counting-MCNN.
Here's the error: shape [-1,-1,-1,1]. is not fully defined for output 0 "PlaceHolder". Same happens when trying to change the input shape with the --input_shape parameter.
Thanks in advance.
Dear Stancu, Robert
Though numpy is "A-OK" with -1 as values for layer shapes OpenVino is not. OpenVino expects that layer shapes and dimensions within a model are explicitly defined and also positive (greater than 0).
Hope it helps,