...
Name | Institution | Mail Address | Social Contacts |
---|---|---|---|
Alessandro Bombini | Cultural Heritage Network (CHNet), INFN, Firenze on behalf of European Science Cloud (EOSC) - Pillar | bombini@fi.infn.it | Skype: ; Linkedin: https://it.linkedin.com/in/alessandro-bombini-7929a2133; Twitter: ; Hangouts: |
Skype: ; Linkedin: ; Twitter: ; Hangouts: |
...
We will build a network this form:
0. Input Layer
- Conv2D x2 + MaxPool2D
- Conv2D x2 + MaxPool2D
- Conv2D x2 + MaxPool2D
- Conv2D x2 + MaxPool2D
- Conv2D x2 + Upsampling + Concatenate (4,5)
- Conv2D x2 + Upsampling + Concatenate (3,6)
- Conv2D x2 + Upsampling + Concatenate (2,7)
- Conv2D x2 + Upsampling + Concatenate (1,8)
- OutPut Layer to RGB
For the training of the 32x32 case we will use the CIFAR dataset ( https://www.cs.toronto.edu/~kriz/cifar.html ). It consists in 50.000 RGB 32 x 32 images.
...