CODEWITHSUNDEEP
pythontensorflowdeep-learningtensorflow.js
Shawn
Shawn

Reputation: 331

What is the difference between Tensorflow.js Layers model and Graph model?

Wanted to know what are the differences between this and this? Is it just the ways the inputs vary?

Upvotes: 5

Views: 2118

Answers (2)

Shanqing Cai
Shanqing Cai

Reputation: 3876

The main differences between LayersModel and GraphModels are:

  1. LayersModel can only be imported from tf.keras or keras HDF5 format model types. GraphModels can be imported from either the aforementioned model types, or TensorFlow SavedModels.

  2. LayersModels support further training in JavaScript (through its fit() method). GraphModel supports only inference.

  3. GraphModel usually gives you higher inference speed (10-20%) than LayersModel, due to its graph optimization, which is possible thanks to the inference-only support.

Hope this helps.

Upvotes: 14

user2693313
user2693313

Reputation: 379

Both are doing the same task i.e. converting a NN model to tfjs format. It's just that in the 1st link model stored in h5 format (typically format in which keras model are saved) is used, while in another it's TF saved model.

Upvotes: 2

Related Questions