Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/kylesayrs/sketchcnn-ae
https://github.com/kylesayrs/sketchcnn-ae
Last synced: 2 days ago
JSON representation
- Host: GitHub
- URL: https://github.com/kylesayrs/sketchcnn-ae
- Owner: kylesayrs
- Created: 2023-12-22T15:41:52.000Z (about 1 year ago)
- Default Branch: master
- Last Pushed: 2023-12-29T05:03:52.000Z (about 1 year ago)
- Last Synced: 2023-12-30T00:25:22.879Z (about 1 year ago)
- Language: Python
- Size: 71.3 KB
- Stars: 0
- Watchers: 2
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# SketchCNN AutoEncoder #
Train an autoencoder to encode partially drawn images from Google's [Quickdraw Dataset](https://quickdraw.withgoogle.com/data). This autoencoder can then be used to bootstrap downstream tasks such as image classification or stroke generation.
## Usage ##
```bash
python3 download_bitmaps.py drawings
python3 train.py
```
## TODO ##
Implement data augmentations for strokes