How to convert from .pb to .tflite?

Question

I have created a object detection model using Pytorch and then converted from .pth to .onnx and then .pb, but now I need to convert it into .tflite for android app! How to do it? It's my first time.

input_arrays  = [64, 3, 224, 224] 

output_arrays = ? 

for binary classification.

I have done it from pytorch but everything I find to look at was from keras or Tensorflow...

This is the code I have used to convert it from .pb to .tflie

converter = lite.TFLiteConverter.from_frozen_graph(
  model/model.pb , input_arrays, output arrays )
tflite_model = converter.convert()
open("converted_model.tflite", "wb").write(tflite_model)

!tflite_convert \
   --output_file= model/model.tflite \
   --graph_def_file= model/model.pb \
   --input_arrays= input_arrays \
   -- output_arrays= output_arrays

I think it has something to do with input arrays and output arrays, but not sure about it. Is graph_def_file supposed to store model.pb ?

Answer 1

No need to specify input and output array, when using the following code:

import tensorflow as tf

converter = tf.lite.TFLiteConverter.from_saved_model(saved_model_dir)
tflite_model = converter.convert()
open("converted_model.tflite", "wb").write(tflite_model)

Try this out.