218 - Difference between UpSampling2D and Conv2DTranspose used in U-Net and GAN

Difference between UpSampling2D and Conv2DTranspose

These are the two common types of layers that can be used to increase the dimensions of arrays.

UpSampling2D is like the opposite of pooling where it repeats rows and columns of the input.

Conv2DTranspose performs up-sampling and convolution.

Conv2DTranspose has been reported to result in Checkerboard artifacts but
unfortunately not much information on the comparison of UpSampling2D vs Conv2DTranspose.

Code generated in the video can be downloaded from here:
https://github.com/bnsreenu/python_fo...

• #science_technology
• #microscopy
• #python
• #image_processing