README for part 1 and 2 (including images)

README.md

@@ -2,8 +2,49 @@
 
 MSO 3.4 Apprentissage Automatique
 
+Thomas DESGREYS
+
 ---
+To compute all the trainings and evaluations, I had to use both Google Colab and Kaggle (in parallel because of the 
+slowness) because they offer free GPU use. That's why on the final notebook 
+[BE2_GAN_and_Diffusion.ipynb](BE2_GAN_and_Diffusion.ipynb), some cells or not correctly run.
+
+
+## Part 1: DC-GAN
+The aim of this part is to generate written numbers thanks to a Deep Convolutional Generative Adversarial Networks.
+
+![](written_numbers.png)
+
+For this purpose, we implement a generator and a discriminator : the generator is trained to generate fake numbers from noise, in order to 
+lure the discriminator and the discriminator is trained to differentiate true numbers from fakes.
+
+![](dcgan_results.png)
+
+We can see on the loss curves that the accuracy of the discriminator is quite constant as the generator get better so its hard for it to get better.
+The generator loss is decreasing. The variation of the losses is unstable as the two models are in competition.
+
+![](dc_gan_generation.png)
+
+We observe at the end of the training (5 epochs) that the generated images are really close to real written numbers.
+However, we note that the generator doesn't create specific numbers but "something" that looks like a number.
+
+
+## Part 2: Conditional GAN (cGAN)
+In this part we aim at to generating facades from a template image.
+![](cgan_training.png)
+For this purpose, we use a UNET architecture for the generator and a patch GAN for the discriminator.
+
+![](cgan_losses.png)
+We can see the same unstable behavior as for the DC-GAN. The GAN is getting better on average so that's satisfying.
+
+### Comparison of the model for 100 and 200 epochs
+With the training data, we observe that the model use its memory to recreate quite the same facades. The model with 200 epochs generates less blurry images.
+
+![](comparison_train.png)
+
+With the validation data, the model is creating more original images. Its sticks to the template to create realistic images with still a lot of artefacts. The images are quite fare from the original but that's normal given the sole information of the template.
+The model with 200 epochs show a bit more details but also mor noise so we can't conclude its better.
 
-# How to submit your Work ?
+![](comparison_val.png)
 
-This work must be done individually. The expected output is a private repository named gan-diffusion 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. Don't forget to add your teacher as developer member of the project. The last commit is due before 11:59 pm on Wednesday, April 9th, 2025. Subsequent commits will not be considered.
+## Part 3: Diffusion
\ No newline at end of file