From 8cbaf3ebc3345dc89c070e18d98e0cc6cab7fb7e Mon Sep 17 00:00:00 2001 From: Aladdin Persson Date: Thu, 11 Mar 2021 15:55:27 +0100 Subject: [PATCH] progan cyclegan --- ML/Pytorch/GANs/CycleGAN/README.md | 2 +- ML/Pytorch/GANs/ProGAN/README.md | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/ML/Pytorch/GANs/CycleGAN/README.md b/ML/Pytorch/GANs/CycleGAN/README.md index f44ed92..90925e0 100644 --- a/ML/Pytorch/GANs/CycleGAN/README.md +++ b/ML/Pytorch/GANs/CycleGAN/README.md @@ -14,7 +14,7 @@ The model was trained on Zebra<->Horses dataset. The dataset can be downloaded from Kaggle: [link](https://www.kaggle.com/suyashdamle/cyclegan). ### Download pretrained weights -Pretrained weights [will upload soon](). +Pretrained weights [download](https://github.com/aladdinpersson/Machine-Learning-Collection/releases/download/1.0/CycleGAN_weights.zip). Extract the zip file and put the pth.tar files in the directory with all the python files. Make sure you put LOAD_MODEL=True in the config.py file. diff --git a/ML/Pytorch/GANs/ProGAN/README.md b/ML/Pytorch/GANs/ProGAN/README.md index b232701..af41d2a 100644 --- a/ML/Pytorch/GANs/ProGAN/README.md +++ b/ML/Pytorch/GANs/ProGAN/README.md @@ -2,9 +2,9 @@ A clean, simple and readable implementation of ProGAN in PyTorch. I've tried to replicate the original paper as closely as possible, so if you read the paper the implementation should be pretty much identical. The results from this implementation I would say is on par with the paper, I'll include some examples results below. ## Results -The model was trained on the Maps dataset and for fun I also tried using it to colorize anime. +The model was trained on the Celeb-HQ dataset up to 256x256 image size. After that point I felt it was enough as it would take quite a while to train to 1024^2. -|| +|First is 64 random examples (not cherry picked) and second is more cherry picked examples. | |:---:| |![](results/64_examples.png)| |![](results/result1.png)|