Category: Software
Product Number: MAX78002
Hi,
I am trying to adapt a pre-trained model on a MAX78002. My model contain some Depthwise Convolution layers with the kernel size of 5 with 1D (or 5x1 with 2D).
The documentation states that Conv1d can take the groups parameter same as the number of input channels. However, on the scripts (ai8x.py), that feature is not supported.
Document (Model Training and Synthesis)
Scripts (ai8x.py)
This causes the problem:
TypeError: Conv1d.__init__() got an unexpected keyword argument 'groups'
when I tried to use "groups" in my Conv1D layer.
Please help. Thank you very much.
Edit Notes
added tag[edited by: emassa at 8:56 PM (GMT -5) on 21 Feb 2023]
