Manu Mathew

I am not an expert in CUDA / NCCL. But please search a bit and see if you get a solution. For example, I think these threads may be useful:...

>>> i use netron tool to look the net structure to get "yolo_param(input)", and my yolov7.onnx model can't show the number and show the str, my sample is as follow:...

Having name for layer is not an issue, but too large name can cause issue in TIDL. That is why the name is replaced with number. You can see a...

You can use that function to do that; the whole script does other things as well; just use the function to avoid confusion.

The Python package osrt_model_tools is installed by this line: https://github.com/TexasInstruments/edgeai-benchmark/blob/master/requirements_pc.txt#L21 You install it manually as well: pip install git+https://github.com/TexasInstruments/edgeai-tidl-tools.git#subdirectory=scripts

For compiling your own models and producing compiled output, you can use the following script: https://github.com/TexasInstruments/edgeai-benchmark/blob/master/run_custom_pc.sh Which invokes this: https://github.com/TexasInstruments/edgeai-benchmark/blob/master/scripts/benchmark_custom.py See the above script and modify it to compile your...

The assertion error seems to be saying that: dataset_selection is set, but dataset_category is not defined in pipeline_config: Is this the error that you are referring to? Wondering why dataset_selection...

If you set dataset_selection to default value (null), are you able to run the script?

calibration_... parameters influences the import time and accuracy. Reducing these may reduce accuracy for some models. 25, 25 may give good results, but for quick experimentation you can use 10,...

@shyam-j Can you take a look at this?