This is in part to the medium blog

Set up the environment with requirements.txt(pip) or environment.yml(conda)

Use npm or yarn to install node dependencies.

Download dataset and extract:

Run in following order.

python create_model.py
./to_tfjs.sh
node train_on_cpus.js
node convert_tfjs_to_keras.js
python client_fed_average.py

--------------- TEAM ---------------

Name		Name	Last commit message	Last commit date
Latest commit History 15 Commits
.devcontainer		.devcontainer
tensorflowjs-mnist-miniapp		tensorflowjs-mnist-miniapp
.gitignore		.gitignore
Dockerfile		Dockerfile
README.md		README.md
browser_loader.js		browser_loader.js
client_fed_average.py		client_fed_average.py
convert_tfjs_to_keras.js		convert_tfjs_to_keras.js
create_model.py		create_model.py
data_loader.js		data_loader.js
docker.sh		docker.sh
environment.yml		environment.yml
model.js		model.js
package-lock.json		package-lock.json
package.json		package.json
requirements.txt		requirements.txt
runner.sh		runner.sh
tfjs.Dockerfile		tfjs.Dockerfile
to_h5.sh		to_h5.sh
to_tfjs.sh		to_tfjs.sh
train-images-idx3-ubyte		train-images-idx3-ubyte
train-labels-idx1-ubyte		train-labels-idx1-ubyte
train_on_cpus.js		train_on_cpus.js

Provide feedback