diff --git a/README.md b/README.md index ace09311e397fa83cd8fbe84f6c2e0c14804b87e..bba449ea84be8ac745f2ce34b63af575fd46d00a 100644 --- a/README.md +++ b/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. + + + +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. + + + +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. + + + +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. + +For this purpose, we use a UNET architecture for the generator and a patch GAN for the discriminator. + + +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. + + + +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 ? + -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 diff --git a/gan_results.png b/cgan_losses.png similarity index 100% rename from gan_results.png rename to cgan_losses.png diff --git a/cgan_results.png b/cgan_results.png new file mode 100644 index 0000000000000000000000000000000000000000..0d24eb4c8dade1c0fb114486bc35c812b4930cf9 Binary files /dev/null and b/cgan_results.png differ diff --git a/cgan_training.png b/cgan_training.png new file mode 100644 index 0000000000000000000000000000000000000000..59a945ec8732d02e3b48b74efe29bdf684e25899 Binary files /dev/null and b/cgan_training.png differ diff --git a/dc_gan_generation.png b/dc_gan_generation.png new file mode 100644 index 0000000000000000000000000000000000000000..f92d506ed1e3d55f6f3f2fdae7c7f96edb72d14d Binary files /dev/null and b/dc_gan_generation.png differ diff --git a/dcgan_results.png b/dcgan_results.png new file mode 100644 index 0000000000000000000000000000000000000000..cfa7665b5df2ee2c045af361961d548d14286995 Binary files /dev/null and b/dcgan_results.png differ diff --git a/diffuser_result_4.png b/diffuser_result_4.png new file mode 100644 index 0000000000000000000000000000000000000000..5feeabaac7c6f435e46fae987522a50bdcb95e12 Binary files /dev/null and b/diffuser_result_4.png differ diff --git a/diffuser_result_6.png b/diffuser_result_6.png new file mode 100644 index 0000000000000000000000000000000000000000..63290785f8624e6f58c8eb9bd8f8eee485f3759d Binary files /dev/null and b/diffuser_result_6.png differ diff --git a/written_numbers.png b/written_numbers.png new file mode 100644 index 0000000000000000000000000000000000000000..c3e277cbe08f67b063e2f587f5b0404e505d15c8 Binary files /dev/null and b/written_numbers.png differ