When I use trained keras model in tensorRT 5.1, I got the problem:

AI & Data Science Deep Learning (Training & Inference) TensorRT
1

[TensorRT] ERROR: (Unnamed Layer* 605) [Deconvolution]: kernel weights has count 5242880 but 32768 was expected
[TensorRT] ERROR: (Unnamed Layer* 605) [Deconvolution]: kernel weights has count 5242880 but 32768 was expected
python: uff/UffParser.cpp:1070: std::shared_ptr UffParser::parseConvTranspose(const uff::Node&, const Fields&, NodesMap&): Assertion `(outSpatial[0] == layer->getOutput(0)->getDimensions().d[1] && outSpatial[1] == layer->getOutput(0)->getDimensions().d[2]) && “Uff parser gets incorrect outSpacial”’ failed.

2

I got the same error when parsing my UFF, did you figure out how to resolve this?

Thanks