Hi I see that after expansion path, a Conv2D is applied to the output. (I mean right before applying the final Conv2D which ends to a tensor of num_classes channels. ) in the figure of the U-net architecture I don’t see such layer. I mean after expansion path, the final Conv2D is applied. So what…

Conv9 necessity in U-net implementation

balaji.ambresh June 4, 2022, 6:58am 2

Please see this post.

Topic		Replies	Views
Unet_model_ Conv9 Convolutional Neural Networks coursera-platform	1	574	May 18, 2022
Help with For U-Net Assignment Convolutional Neural Networks coursera-platform	4	616	September 23, 2021
Theoretical doubt Convolutional Neural Networks coursera-platform	1	490	February 22, 2022
Why conv9 in # UNQ_C3 in unet_model function Convolutional Neural Networks coursera-platform	5	423	July 15, 2023
U-Net Convolutions After Transpose Convolutions Convolutional Neural Networks week-module-3 , coursera-platform	4	434	January 22, 2024