🐕 🐈 Classifier using Keras VGG16 transfer learning with kaggle dogs vs. cats dataset.
Further reading: 中文 Inference on the Browser with Tensorflow JS
| Input data type | Task type | Model type | Training | Inference | Save-load operations |
|---|---|---|---|---|---|
| Image | Multiclass classification (transfer learning) | Convolutional neural network | Python | Browser | Export trained model from Keras and load it in browser |
Use Jupyter Notebook to save Keras models as HDF5 file to ./python/output/model.h5
Use tfjs-converter to convert the model format via docker image under ./python/output/model-tfjs/:
$ docker run -it --rm \
-v "$PWD/python:/python" \
evenchange4/docker-tfjs-converter \
tensorflowjs_converter --input_format=keras model.h5 python/output/model-tfjsPython 3.6.8 Tensorflowjs 1.2.6 keras 2.2.4-tf tensorflow 1.14.0
yarn install --pure-lockfile
# move model to static folder
# cp -r python/output/model-tfjs static- node 12.10.0
- yarn 1.17.3
Any commits pushed to master branch.
npm run changelog$ yarn run format
$ yarn run eslint
$ yarn run type-check
$ yarn run test:watch- ⇄ Pull requests and ★ Stars are always welcome.
- For bugs and feature requests, please create an issue.
- Pull requests must be accompanied by passing automated tests (
$ yarn run test).
- Keras CNN Dog or Cat Classification
- VGG16-with-TensorflowJs
- TensorFlow.JS — Using JavaScript Web Worker to Run ML Predict Function
- AI 如何找出你的喵
- TensorFlow.js Example: MNIST CNN Transfer Learning Demo
- TensorFlow.js - Explore tensor operations through VGG16 preprocessing
- Classifying images using Keras MobileNet and TensorFlow.js in Google Chrome
- Building a blood cell classification model using Keras and tfjs
- Keras 框架中的 epoch、bacth、batch size、iteration
- https://github.com/Elwing-Chou/TibameDL
- https://github.com/leemengtaiwan/cat-recognition-train
- Data Augmentation 資料增強
- [機器學習 ML NOTE] CNN 演化史(AlexNet、VGG、Inception、ResNet)+Keras Coding