Skip to content
Snippets Groups Projects

Compare revisions

Changes are shown as if the source revision was being merged into the target revision. Learn more about comparing revisions.

Source

Select target project
No results found
Select Git revision
  • main
1 result

Target

Select target project
No results found
Select Git revision
  • main
1 result
Show changes

Commits on Source 3

3 files
+ 43308
− 30
Compare changes
  • Side-by-side
  • Inline

Files

.gitignore

+5 −0
Original line number Original line Diff line number Diff line
@@ -127,3 +127,8 @@ dmypy.json 




# Pyre type checker

# Pyre type checker

.pyre/

.pyre/



# Data

/data

/facades

*.zip

BE2_GAN_and_cGAN.ipynb

+43295 −27

File changed.

Preview size limit exceeded, changes collapsed.

README.md

+8 −3
Original line number Original line Diff line number Diff line 
# GAN & cGAN tutorial.

# GAN & cGAN tutorial.





We recommand to use the notebook (.ipynb) but the Python script (.py) is also provided if more convenient for you.

Filipe PENNA CERAVOLO SOARES





# How to submit your Work ?

## Part1: DC-GAN





This work must be done individually. The expected output is a repository named gan-cgan on https://gitlab.ec-lyon.fr. It must contain your notebook (or python files) and a README.md file that explains briefly the successive steps of the project. The last commit is due before 11:59 pm on Wednesday, March 29, 2023. Subsequent commits will not be considered.
 
- In this part,  generative adversarial network (GAN) has been trained to generate new handwritten digits, after feeding it with pictures from the [**MNIST database**](https://en.wikipedia.org/wiki/MNIST_database)

 No newline at end of file
 
- To do so, the [**DCGAN tutorial**](https://pytorch.org/tutorials/beginner/dcgan_faces_tutorial.html) of pytorch has been followed. This tutorial generate new celebrities after showing it pictures of many real celebrities. 

- To adapt this tutorial to the MNIST database, the most relevant change in its implematation reflects the change of number of channels in the training images (from 3 [*RGB*] to 1 [*Black and White*]).

- 



## Part2: Conditional GAN (cGAN)
 
 No newline at end of file