TLT Converter

Accelerated Computing Intelligent Video Analytics TAO Toolkit
1

Hi,
I am working on Lisence Plate Recognition model on deepstream. I downloaded .etlt file as well as tlt- converter. When I try to execute ./tlt-converter, it is showing warning and I am unable to create .engine file using tlt converter.

vamsisiddharthasiddhu2041@linux:/opt/nvidia/deepstream/deepstream-5.1/samples/models/LP/LPR$ ./tlt-converter -k nvidia_tlt -p image_input,1x3x48x96,4x3x48x96,16x3x48x96 ./us_lprnet_baseline18_deployable.etlt -t fp16 -e lpr_us_onnx_b16.engine
[WARNING] onnx2trt_utils.cpp:220: Your ONNX model has been generated with INT64 weights, while TensorRT does not natively support INT64. Attempting to cast down to INT32.
[WARNING] Tensor DataType is determined at build time for tensors not marked as input or output.
[INFO] Detected input dimensions from the model: (-1, 3, 48, 96)
[INFO] Model has dynamic shape. Setting up optimization profiles.
[INFO] Using optimization profile min shape: (1, 3, 48, 96) for input: image_input
[INFO] Using optimization profile opt shape: (4, 3, 48, 96) for input: image_input
[INFO] Using optimization profile max shape: (16, 3, 48, 96) for input: image_input
[INFO] Detected 1 inputs and 2 output network tensors.
vamsisiddharthasiddhu2041@linux:/opt/nvidia/deepstream/deepstream-5.1/samples/models/LP/LPR$
I am enclosing screenshot of the error. Please help me to sort out this error.
Thanks…

Screenshot (528)
Screenshot (528)1920×1080 252 KB

2

I don’t see any error in the attached info.
Please run it with higher verbosity and post the log

3

Sir,
After executing tlt converter command, it will give .engine file as output right. But, when I execute that command, i could not find any output file .

5

Please check if you have write access to this path. Try to chmod it.

6

Yeah, I tried that also, still could not get .engine file after executing tlt converter.

7

Can you run below?
$ ll -sh /opt/nvidia/deepstream/deepstream-5.1/samples/models/LP/LPR