How to change pretrained model from 3 RGB Channels to 4 Channels without causing non- leaf tensor value error?

[VirginieBfd (Virginie Bonnefond)]

Here is a working solution for ResNet:

How to modify the input channels of a Resnet model

Here is a generic function to increase the channels to 4 or more channels. One key point is that the additional channel weights can be initialized with one original channel rather than being randomized. new_in_channels = 4 model = models.resnet18(pretrained=True) layer = model.conv1 # Creating new Conv2d layer new_layer = nn.Conv2d(in_channels=new_in_channels, out_channels=layer.out_channels, kernel_size=layer.kernel_size, stri…