CODEWITHSUNDEEP
tensorflowtensorflow-lite
John M.
John M.

Reputation: 2712

List operations of a TFLite model

I'm having trouble trying to list the operations of a TFLite model. I know operations can be listed given a frozen graph, but what about a TFLite .tflite model? Can operations be listed?

Upvotes: 4

Views: 4210

Answers (3)

Vasantha Ganesh
Vasantha Ganesh

Reputation: 5050

We can use netron to visualize the operators and the constants in a .tflite model. We can use it from web or install it with pip or install binaries and use it as a local app on windows, linux or mac. The netron app looks like this:

netron windows app

Upvotes: 0

Tom Stein
Tom Stein

Reputation: 365

You can get a list of all used Tensorflow Lite Operations with the visualization script.

wget -O tflite_visualize.py https://raw.githubusercontent.com/tensorflow/tensorflow/master/tensorflow/lite/tools/visualize.py

Assuming your model is saved in model.tflite create the html file using the downloaded script.

python tflite_visualize.py model.tflite model_visualization.html

Right in the section labled Ops.

Table of Tensorflow Lite Ops in html file

Upvotes: 4

Shubham Panchal
Shubham Panchal

Reputation: 4289

As mentioned in the TensorFlow Lite docs, you need to use a tf.lite.Interpreter to parse a .tflite model.

# Load TFLite model and allocate tensors.
interpreter = tf.lite.Interpreter(model_path="converted_model.tflite")
interpreter.allocate_tensors()

Then use the get_tensor_details method to get the list of Tensors.

interpreter.get_tensor_details()

As per the docs,

Gets tensor details for every tensor with valid tensor details. Tensors where required information about the tensor is not found are not added to the list. This includes temporary tensors without a name.

Returns: A list of dictionaries containing tensor information.

Upvotes: 2

Related Questions