Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Coloring black and white images with deep learning.
| Date | Stars |
|---|---|
| 2026-07-24 | 1053 |
| 2026-07-25 | 1053 |
| 2026-07-28 | 1053 |
| 2026-07-30 | 1053 |
| 2026-07-31 | 1053 |
| 2026-08-06 | 1053 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
 --- **A detailed tutorial covering the code in this repository:** [Coloring Black and White photos with Neural Networks](https://emilwallner.medium.com/colorize-b-w-photos-with-a-100-line-neural-network-53d9b4449f8d) 👉 Try the [Palette API](https://docs.palette.fm/) to test the latest advancements in AI colorization. The network is built in four parts and gradually becomes more complex. The first part is the bare minimum to understand the core parts of the network. It's built to color one image. Once I have something to experiment with, I find it easier to add the remaining 80% of the network. For the second stage, the Beta version, I start automating the training flow. In the full version, I add features from a pre-trained classifier. The GAN version is not covered in the tutorial. It's an experimental version using some of the emerging best practices in image colorization. ### 🍿 [Featured by Google >>>](https://www.youtube.com/watch?v=xKPk7tG2upc) **Note:** The display images below are cherry-picked. A large majority of the images are mostly black and white or are lightly colored in brown. A narrow and simple dataset often creates better results. ## Installation ``` pip install keras tensorflow pillow h5py jupyter scikit-image ``` ``` git clone https://github.com/emilwallner/Coloring-greyscale-images cd Coloring-greyscale-images/ jupyter notebook ``` Go do the desired notebook, files that end with '.ipynb'. To run the model, go to the menu then click on Cell > Run all For the GAN version, enter the GAN-version folder, and run: ``` python3 colorize_base.py ``` **Pre-trained weights:** Download the pre-trained weights for the GAN-version [here](https://drive.google.com/open?id=1Vpd-6CpF4pVzmkOPd7rqyYP1OOuZaRrd). Create a folder called 'resources' and put it inside of Coloring-greyscale-images/GAN-version/. It's trained on contemporary photography with different objects but not a lot of people. ## Alpha Version This is a great starting point to get a hang of the moving pieces. How an image is transformed into RGB pixel values and later translated into LAB pixel values, [changing the color space](https://ciechanow.ski/color-spaces/). It also builds a core intuition for how the network learns. How the network compares the input with the output and adjusts the network. <p align="center"><img src="/README_images/alpha.png?raw=true" width="747px"></p> In this version, you will see a result in a few minutes. Once you have trained the network, try coloring an image it was not trained on. This will build an intuition for the purpose of the later versions. ## Beta Version The network in the beta version is very similar to the alpha version. The difference is that we use more than one image to train the network. I'd recommend running ```top/htop``` and ```nvidia-smi``` to see how different batch sizes affect your computer's memory. <p align="center"><img src="/README_images/beta.png?raw=true" width="745px"></p> For this model, I'd go with a this [cropped celebrity dataset](https://github.com/2014mchidamb/DeepColorization/tree/master/face_images) or [Nvidia's StyleGAN dataset](https://github.com/NVlabs/stylegan). Because the images are very similar, the network can learn basic colorization despite being trivial. To get a feel for the limits of this network, you can try it on this dataset of [diverse images from Unsplash](https://www.floydhub.com/emilwallner/datasets/colornet). If you are on a laptop, I'd run it for a day. If you are using a GPU, train it at least 6 - 12h. ## Full Version The full version adds information from a pre-trained classifier. You can think of the information as 20% nature, 30% humans, 30% sky, and 20% brick buildings. It then learns to combine that information with the black and white photo. It gives the network more confidence to color the image. Otherwise,
Excerpt of 8,347 characters
Read on GitHub
166
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:5e87ff8ec02d41ff, topic:deep-learning, topic:tensorflow
matched fp:5e87ff8ec02d41ff, topic:tutorial, readme:tutorial