tfmodel is the command-line tool to inspect TensorFlow models for statically and dynamically metrics.
Read more documentation in https://tfmodel.readthedocs.io.
Install with pip.
pip install tensorflow-modelInstall with docker.
docker run -it -v /:/host tobegit3hub/tfmodel bashInstall from source.
git clone https://github.com/tobegit3hub/tfmodel
cd ./tfmodel
python ./setup.py installUser can validate the model to check if is the deployable TensorFlow SavedModel.
tfmodel validate ./model
User can inspect the model to check the signature before deploying.
tfmodel inspect ./model
User can run benchmark locally and get the performance report with only model files.
tfmodel benchmark ./model
User can export the TensorBoard event files without re-training the models.
tfmodel tensorboard ./model