https://github.com/dhth/restaurant-crowded-or-not
ResNet classifier predicting whether a restaurant is crowded or not.
https://github.com/dhth/restaurant-crowded-or-not
fastai resnet-34
Last synced: about 1 year ago
JSON representation
ResNet classifier predicting whether a restaurant is crowded or not.
- Host: GitHub
- URL: https://github.com/dhth/restaurant-crowded-or-not
- Owner: dhth
- Created: 2018-11-01T10:28:50.000Z (over 7 years ago)
- Default Branch: master
- Last Pushed: 2018-11-03T12:26:46.000Z (over 7 years ago)
- Last Synced: 2025-02-10T08:51:26.544Z (over 1 year ago)
- Topics: fastai, resnet-34
- Language: Jupyter Notebook
- Homepage:
- Size: 3.17 MB
- Stars: 0
- Watchers: 2
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
This is a simple image classifier based on Resnet-34 architecture, served as an API via Starlette.
This approach is based on learnings from a fast.ai MOOC that will be publicly available in Jan 2019.
Deployment approach is inspired by [@simonw](https://github.com/simonw)'s [repo](https://github.com/simonw/cougar-or-not).
The classifier uses a pre-trained resnet-34 (trained on imagenet) re-trained on a dataset of 500 images.