How to make embeddings projection on TensorBoard
The command below will build the docker image and run other installation steps
make install
This is already performed if you previously have run make install
docker build . -t mnist_projection
Enter container
docker run -it \
-v ${PWD}/projections:/projections/ \
-v ${PWD}/keras_datasets:/root/.keras/datasets \
-p 6006:6006 \
--rm --gpus all mnist_projection bash
python -m mnist_train \
--output_dir /projections\
--batch_size 16 \
--epochs 5
python -m mnist_project_embeddings \
--output_dir /projections/<timestamp>/ \
--ckpt_path /projections/<timestamp>/model.hdf5 \
--layer_name model_dense_1
tensorboard --logdir /projections/<timestamp>/tensorboard/projector/ --port 6006
Enter localhost:6006
at your browser