Skip to content
Part one in a series of tutorials about creating a model for predicting house prices using Keras / Tensorflow in Python and preparing all the necessary data for importing the model in a javascript application using tensorflow.js. Let me know what do you think about it!
Branch: master
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
dataset
model
shared
.editorconfig
.gitignore
LICENSE
README.md
common.py
common_categorical.py
common_file.py
common_pre_post_processing.py
common_scaler.py
common_visualization.py
dockerfile
environment.yml
predict.py
share_preprocessing_tfjs.py
train_model.py

README.md

Python Real Estate

This project shows how to create a model for predicting house prices and exporting some data for later use inside a Tensorflow.js application

You can read/see more about this in:

Important files to run

  • predict.py
  • train_model.py
  • share_preprocessing_tfjs.py

Tensorflowjs Converter

Building the image using docker

    docker build -t tf-converter .

Running the converter using docker

    docker run -it --rm --name tf-converter -v "$(pwd)":/workdir tf-converter --input_format keras ./model/-inputsscaled-outputsscaled-categorical/model.h5 ./shared/model

Install the converter and run it without docker

    pip install tensorflowjs

    tensorflowjs_converter --input_format keras \
                        ./model/-inputsscaled-outputsscaled-categorical/model.h5 \
                        ./shared/model

More resources

You can’t perform that action at this time.