Error Converting MobileNetV2 ONNX Model to TLTB Format

Accelerated Computing Intelligent Video Analytics TAO Toolkit
1

I have downloaded a MobileNetV2 PyTorch classification model and converted it to ONNX format with opset 11. When I try to convert it to TLTB format using the TAO BYOM converter with the following command:

tao_byom -m mobilenet_v2_128_0_5_opset_11.onnx -r results/mobilenet -n mobilenet_v2

I encounter the following error:

TypeError: Expected name argument to be a string, but got: [‘LAYER_1_0’, ‘LAYER_1_1’, ‘LAYER_1_2’, ‘LAYER_1_3’, ‘LAYER_1_4’]

How can I resolve this issue?

2

Could you try another mobilenetv2 classification model? Please refer to BYOM Converter - NVIDIA Docs → BYOM Example repo .

3

There is no update from you for a period, assuming this is not an issue anymore. Hence we are closing this topic. If need further support, please open a new one. Thanks