NVIDIA-AI-IOT/deepstream_lpr_app

Error: no input dimensions given

Swapnil-gautam opened this issue · 5 comments

Swapnil-gautam commented

while running

./tlt-converter -k nvidia_tlt -p image_input,1x3x48x96,4x3x48x96,16x3x48x96
models/LP/LPR/ch_lprnet_baseline18_deployable.etlt -t fp16 -e models/LP/LPR/lpr_ch_onnx_b16.engine

I am getting

Error: no input dimensions given

I am using jetson nano (2gb) anf my jetpack version is 4.4.1

florisdesmedt commented

did you find a solution? I have the same issue

Swapnil-gautam commented

No mate, I switched to other approach. Their forum is very active though you may get some help from there.

jdavidd commented

@Swapnil-gautam Hello, what is the solution?

Thoye commented

I have the same problem. Can you help me? @Swapnil-gautam @florisdesmedt @jdavidd

abhinavvsharma commented

Follow this solve the error:

  1. Download the tao-converter/ tlt-converter according to the hardware and platform being used, as mentioned on the NVIDIA page.
  2. The "-d" argument is not required for TLT 3.0 New model, so the NVIDIA page doesn't include the "-d" argument.
  3. Change directory to the LPR directory.
  4. Use the command -
  5. path-to-tlt-converter /tlt-converter -k nvidia_tlt -p image_input,1x3x48x96,4x3x48x96,16x3x48x96 ./us_lprnet_baseline18_deployable.etlt -t fp16 -e /opt/nvidia/deepstream/deepstream <5.0/ 5.1> /samples/models/LP/LPR/lpr_us_onnx_b16.engine -d 1x3x48x96,4x3x48x96,16x3x48x96