A script to generate tensorboard embeddings visualization of a group of images.

• python
• tensorflow
• tensorboard

pip install -r requierments.txt

Replace tf1.8-gpu with tf1.8 and nvidia-docker with docker for CPU build.

docker pull rpidanny/tf1.8-gpu

Change directory to your project directory, than run in the interactive mode:

nvidia-docker run -it -p 9001:9001 -v=$(pwd):$(pwd) -v=local_path_to_image_dir:/data --workdir=$(pwd) --rm rpidanny/tf1.8-gpu

Use python3 while using docker.

python main.py --image_dir=path_to_image_dir

tensorboard --logdir=/tmp/tensorboard_logs --port=9001

Go to http://localhost:9001