Re-training inception v4

is it possible to retrain the inception v4 and convert it to onnx through the tools inside jetson-interface?

Hi,

Below is a tutorial to retrain and convert a ResNet model.
Please update the pre-train model directly for your use case.

Thanks.

I tried to import the inception-v2.onnx model into my object detection program but it gives me this error: net = jetson.inference.detectNet(argv=[’–model=model/inception-v2-3.onnx’, ‘–labels=model/labels.txt’, ‘–input-blob=input_0’, ‘–output-cvg=scores’, ‘–output-bbox=boxes’])
Exception: jetson.inference – detectNet failed to load network

Hi,

Could you share the complete error log with us?
In general, you should update the model information like below:

Thanks.

This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.