An open source AutoML toolkit for automate machine learning lifecycle, including feature engineering, neural architecture search, model compression and hyper-parameter tuning.
When the output channels of the last layer is 1, even when there are 2 successive conv blocks, pruning is met with the error assert len(set(num_channels_list)) == 1. This is due to this 1 out channel conv layer is being treated as depthwise convolution and ends up wrongly in dependency group.
Description
When the output channels of the last layer is 1, even when there are 2 successive conv blocks, pruning is met with the error
assert len(set(num_channels_list)) == 1
. This is due to this 1 out channel conv layer is being treated as depthwise convolution and ends up wrongly in dependency group.Fixes #5736