Skip to content
Snippets Groups Projects
Commit 350c6b56 authored by Samer-kh's avatar Samer-kh
Browse files

correcting ReadMe

parent 0dfa7620
No related branches found
No related tags found
No related merge requests found
Show whitespace changes
Inline Side-by-side
Showing
with 8 additions and 8 deletions
README.md
+ 8
− 8
View file @ 350c6b56
...@@ -25,11 +25,11 @@ Discover GANs, understand how they are implemented and then explore one specific ...@@ -25,11 +25,11 @@ Discover GANs, understand how they are implemented and then explore one specific
The data used in this project, we used two datasets : <br> The data used in this project, we used two datasets : <br>
**MINST Dataset :** Modified National Institute of Standards and Technology database is a large dataset of handwritten digits that is commonly used for training various image processing systems. The database is also widely used for training and testing in the field of machine learning.<br> **MINST Dataset :** Modified National Institute of Standards and Technology database is a large dataset of handwritten digits that is commonly used for training various image processing systems. The database is also widely used for training and testing in the field of machine learning.<br>
![MINST dataset](Images/MINST.jpg) ![MINST dataset](images/MINST.jpg)
**CMP Facade Dataset :** A dataset of facade images assembled at the Center for Machine Perception, which includes 606 rectified images of facades from various sources, which have been manually annotated. The facades are from different cities around the world and diverse architectural styles.<br> **CMP Facade Dataset :** A dataset of facade images assembled at the Center for Machine Perception, which includes 606 rectified images of facades from various sources, which have been manually annotated. The facades are from different cities around the world and diverse architectural styles.<br>
![facade dataset](Images/facade_dataset.jpg) ![facade dataset](images/facade_dataset.jpg)
## DC-GAN ## DC-GAN
...@@ -41,11 +41,11 @@ After implementing and testiong the model, i obtained the following result plots ...@@ -41,11 +41,11 @@ After implementing and testiong the model, i obtained the following result plots
* The Loss : * The Loss :
![Loss](Images/loss.png) ![Loss](images/loss.png)
* The images generated : * The images generated :
![fake images](Images/real_fake.png) ![fake images](images/real_fake.png)
# Conditional GAN (cGAN) : # Conditional GAN (cGAN) :
...@@ -56,11 +56,11 @@ In cGAN, the generator is conditioned on some input data, which allows it to gen ...@@ -56,11 +56,11 @@ In cGAN, the generator is conditioned on some input data, which allows it to gen
After implementing the generator and the descriminator, the testing of the model on the valisation dataset gave the following results: After implementing the generator and the descriminator, the testing of the model on the valisation dataset gave the following results:
* training loss of the generator and descriminator : * training loss of the generator and descriminator :
![Training loss](Images/loss_2.png) ![Training loss](images/loss_2.png)
* Model trained for 100 epochs : * Model trained for 100 epochs :
![image generated](Images/100_val.png) ![image generated](images/100_val.png)
* Model trained for 200 epochs : * Model trained for 200 epochs :
![image generated](Images/200_val.png) ![image generated](images/200_val.png)
All the code and results are provided in the notebook BE_GAN_and_cGAN.ipynb All the code and results are provided in the notebook BE_GAN_and_cGAN.ipynb
# Libraries # Libraries
......
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Please register or to comment