Issue regarding converting tensorflow file to tensorRT

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

Hello, Nvidia community,

I successfully retrained the model using the TensorFlow object detection API for 3 classes with a ssd_inception_v2 pre-trained model.

I want to run this model on Nvidia Jetson nano for that I try to convert the model into tensor_RT’s .UFF format.

when I run tensorRT’s sample_uff_ssd it shows following error:

&&&& RUNNING TensorRT.sample_uff_ssd # ./sample_uff_ssd
[I] …/data/ssd/sample_ssd_relu6.uff
[I] Begin parsing model…
[E] [TRT] UffParser: Validator error: Cast: Unsupported operation _Cast
[E] Failure while parsing UFF file

How am I supposed to tackle this error?

Thanks and regards,
Nikunj Panchani

2

Hi,

The model file has “Cast” operations which is not supported in UFF parser.
Please find the below link:
https://docs.nvidia.com/deeplearning/sdk/tensorrt-api/python_api/uff/Operators.html

You can try tf2onnx + ONNX parser as an alternative.
https://github.com/onnx/tensorflow-onnx

Supported ops:
https://docs.nvidia.com/deeplearning/sdk/tensorrt-archived/tensorrt-515/tensorrt-support-matrix/index.html#supported-ops

Thanks