Image classification problem with Convolutional Neural Networks application, Water Cleanliness with CNN Keras Tensorflow
Model is trained on Google's Teachable Machines platform.
After training the model with 200 epochs, with the batch size of 16 and 0.001 learning rate, model achieved to skyrocket a accuracy score of 99% of strictly clean and strictly dirty images samples collected by us. Data is augmented as well beofre fedding into the neural network in terms of its weight, height, zoom, etc.
Include: ML5.js PIL Image Imageops Tensorflow Keras Numpy TF Lite
- Image classification
- Dirty, clean image learning
- Accurate Machine Learning model
- Applied Convolutional Neural Networks model
- Applied ML5.js Javascript library for Machine Learning
- Applied Tensorflow Lite for mobile phone applications
If you have questions or need further guidance on using this template, please file an issue. I will do my best to respond to all issues in a timely manner.
All contributions and suggestions are welcome!
For suggested improvements, please file an issue.
For direct contributions, please fork the repository and file a pull request. If you never created a pull request before, welcome 🎉 😄 Here is a great tutorial on how to send one.
Examples pictures from about 100 image collection dataset includes: for clean and dirty model classes
In the interest of fostering an open and welcoming environment, we as contributors and maintainers pledge to making participation in our project and our community a harassment-free experience for everyone, regardless of age, body size, disability, ethnicity, gender identity and expression, level of experience, nationality, personal appearance, race, religion, or sexual identity and orientation.
This project pledges to follow the Contributor's Covenant.
This project is licensed under The Unlicense and released to the Public Domain. For more information see our LICENSE file.