Comments (1)
Class labels are not needed for colorization, in a way the pixel colors represent the training target.
You should be able to set up your own training by following the report and all papers we reference in it. The main steps are:
- collect colored images (if your dataset is small, consider downloading more images)
- process the images to extract a black and white image that will be used as input and color information that will be used as target
- set up your architecture, anything that looks like a U-net could work, features extracted using a pre-trained inception model can be added to improve the colorization
- train your network by feeding in the grayscale version of an image and comparing the output with the colored version of the image
Please note, this is project is based on an outdated version of tensorflow, so it's fine for taking inspiration for the general pipeline, but when it comes to the code itself I suggest reimplementing everything from scratch.
from deep-koalarization.
Related Issues (14)
- Training HOT 1
- train on multiple gpu HOT 1
- train.py? HOT 3
- from resizeimage import resizeimage HOT 1
- queue_single_images_from_folder HOT 1
- Labels from Inception at the beginning of training seem incorrect
- [REQ] Colab version
- koalarization.dataset.lab_batch issue HOT 5
- How do you train your neural network? HOT 1
- TypeError: Can not convert a LabImageRecordReader into a Tensor or Operation. HOT 3
- Pre-trained model HOT 1
- Lab_Batch file is not creating Tf-records
- Inception output size HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from deep-koalarization.