From 8793724bc0e981ed64bff3c03e13bf37440ab2e0 Mon Sep 17 00:00:00 2001 From: TimNiklasWitte Date: Thu, 31 Mar 2022 10:09:33 +0200 Subject: [PATCH] expand readme --- Colorful_Image_Colorization/README.md | 10 ++++++++++ README.md | 8 ++++++-- 2 files changed, 16 insertions(+), 2 deletions(-) create mode 100644 Colorful_Image_Colorization/README.md diff --git a/Colorful_Image_Colorization/README.md b/Colorful_Image_Colorization/README.md new file mode 100644 index 0000000..2d7bac3 --- /dev/null +++ b/Colorful_Image_Colorization/README.md @@ -0,0 +1,10 @@ +# Colorful Image Colorization +## by Richard Zhang, Phillip Isola, Alexei A. Efros + +Link to the paper: https://arxiv.org/abs/1603.08511 + +For evaluation purpose, the entire code in this directory was copied from this repo: + +https://github.com/foamliu/Colorful-Image-Colorization + +We compared the results generated by the model form Richard Zhang et al. with the results of our model. \ No newline at end of file diff --git a/README.md b/README.md index 8e7a774..2260513 100644 --- a/README.md +++ b/README.md @@ -9,6 +9,10 @@ In total, 10 FPS can be archived on this embedded GPU. ![Example Video](videoPresentation.gif) +In entire documentation of this project in form of a paper can be find in +`./Paper/Main.pdf`. +This project was created as a part of the GPU programming course of Mario Porrmann in the winter term 2021/22 of the Osnabrück University. + ## Requirements - TensorFlow 2 @@ -35,7 +39,7 @@ _______________________________________________________________ ### Hyperparameters -```bash +```python3 optimizer = Adam learning rate = 0.0001 loss function = mean squared error @@ -49,7 +53,7 @@ batch size = 32 Run `Training.py` to start the training of the model on the `imagenet2012` dataset. Each epoch the weights are stored into `./saved_models`. Besides, in `./test_logs` are the corresponding trainings statistics (train and test loss and also a batch of colorized test images) logged. -Note that, the `imagenet2012` dataset is stored in `./imagenet` as described in this [blog article](https://towardsdatascience.com/preparing-the-imagenet-dataset-with-tensorflow-c681916014ee) +Note that, the `imagenet2012` dataset is stored in `./imagenet` as described in this [blog article](https://towardsdatascience.com/preparing-the-imagenet-dataset-with-tensorflow-c681916014ee). ```bash python3 Training.py