Whoever tried to convert a model from Detectron, can share how to do it.
I asked about this example:
Dear Shevchuk, Mikhailo:
The document below tells you exactly how to generate IR for maskrcnn_r50_fpn_2x as described:
Please select your Mask RCNN model from one of OpenVino's validated models here:
That specific example is for a tensorflow model, right? If I remember correctly, model optimisation does not currently support the Detectron framework.
Correct me if I am wrong.
Dear folks, This OpenVino documentation definitely mentions Detectron, so it is supported. The key though is to convert a *.pkl file to a *.pb first, since Model Optimizer does not support *.pkl. There is a script in the Detectron github repo which enables conversion: