ConvTranspose2d VS Bilinear upsample

1

Hi,

I was wondering if someone could tell me what’re the differences between

ConvTranspose2d(group=in_channel) and Upsample(mode='bilinear')

Thanks

2

Upsample will use the mode to “mathematically” upsample the activation (no training), while ConvTranspose2d will use trainable filter kernels.

3

That make sense. Is there any possible to convert ConvTranspose2d to Upsample?

4

You could replace the layer and try to make sure to keep the same output shape.