Converting models using tfjs-converter

Unfortunately, models such as SavedModel of HDF5 created by TensorFlow cannot be used in the world of TensorFlow.js directly. It is inevitable that you will have to convert the model into a format readable by the web platform.

Converting a TensorFlow SavedModel

Once the SavedModel is created, you can convert the SavedModel into TensorFlow.js format as follows:

$ tensorflowjs_converter \
   --output_node_names=output \
   --input_format=tf_saved_model \
  ./my_saved_model ./my_tfjs_model

The input path and output path are required as positional arguments. (my_saved_model and my_tfjs_model). The model will be generated in the my_tfjs_model directory. The options specified in the preceding...