Failed in UFFParser after convert tensorflow model.

I used uff.from_tensorflow to convert Tensorflow model and try to Passer in sample code. But it happened some error.

Could you please help me debug this error message?

ERROR: UFFParser: Validator error: Postprocessor/BatchMultiClassNonMaxSuppression/PadOrClipBoxList/cond/cond/concat/Switch: Unsupported operation _Switch

What is the issue? UFF convert or input node error?

Morris

I am using Jetson Nano.

Morris

Hello,
following https://devtalk.nvidia.com/default/topic/1052730/jetson-tx2/cannot-get-custom-uff-file-to-work/post/5344267/#5344267

I’ve been able to solve this problem

Now, instead I’m having this new issue:

[TRT] UffParser: Parser error: Conv1_pad_1/Pad/paddings: Invalid weights types when converted. Trying to convert from INT32 To INT8

with this:+
if (!parser->parse(uffFile, *network, nvinfer1::DataType::kINT8))

I tried to chande the data type to kINT32, kFLOAT or kHAlF, but in these cases en exception occours:

uff/UffParser.cpp:2134: std::shared_ptr UffParser::parsePad(const uff::Node&, const Fields&, NodesMap&): Assertion `nbDims == 4’ failed.