Convertion of tflite model to ONNX model

Question

I have a tflite model and i want to convert it into tensorflow or keras or ONNX format. Is there a way?

I can import it using tf interpreter and run it on python. However i want to convert it into one of the above formats.

import tensorflow as tf
interpreter = tf.lite.Interpreter(model_path="conv_actions_frozen.tflite")
tensors = interpreter.get_tensor_details()

Did you ever figure out a solution? I have the same problem because I want to run a tflite model in tfjs. — NateW, Mar 05 '20 at 19:15

score 0 · Answer 1 · answered Mar 23 '21 at 10:09

Now there is converter to convert tflite models to onnx format. Install the tflite2onnx library. All you have to do is :

import tflite2onnx

tflite_path = "path/to/the/tflitemodel"
onnx_path = "path/where/you/want/to/save/your/model" #modelname.onnx


tflite2onnx.convert(tflite_path,onnx_path)

Convertion of tflite model to ONNX model

1 Answers1