Seems, that there is no way to convert from the box Mobilenet (and other models from TF OD API) to uff format and then to TensorRT format, because of much unsupported layers. Is there some way to remove \ replace that layers? For example with graph_transform tool maybe? I understand the purpose of not all these layers. Here is the default model, if someone wants to try.
2 Answers
From 2017 year there is still no significant progress. Many new networks has been developed, but UFF and TensorRT converter still can not work with many models even from 2017, what can I say about 2019.
There is also some indirect information in the internet that, in sense, with UFF and TRT convertion in NVIDIA works very small department with just a few guys. So seems that way is dead end.
Better way and the way they are counting on is conversion tools inside framework itself. Like Tensorflow do with their TRT bindings.
With such approach new layers are added by developer of framework and not Nvidia, because guys there don't keep up with marketing. So more chances eventually to get working tool.
Related