Hello, I'm a classifier. 🤗
I can tell you whether an image you indicate is a mountain ⛰️ or a beach 🏖️ or their related things 🌊 🌳 (ocean, sea, forest, mainland,...).
- An interview test of Ideta company.
- Performed by Anh-Thi DINH.
- Date: 13-Jan-2021.
- 2 Classes: "moutain" (and its related: mainland, forest, moutain path,...) and "beach" (and its related: sea, ocean, beach house,...)
- Dataset: extracted (~369MB) from MIT's places dataset. It contains ~15K images for each category.
- Method: using transfer learning and CNN.
- Deploy: a web-app at dinhanhthi.github.io/mountain-vs-beach using TensorFlow.js.
- Jupyter notebook: view in HTML format.
- Documentation: read this.
- Result: 94.29% accuracy.
# Serve locally (if you use python)
python3 -m http.server 9999
# Browse: http://0.0.0.0:9999/# Serve locally (if you use nodejs)
npm install # install http-server
http-server --port 9999
# Browse: http://127.0.0.1:9999/# For converting css/custom.scss to css/custom.css
npm run css-watch