How to create a tflite file from saved_model (SSD MobileNet)

Question

I want to create an object-detection app based on a retrained ssd_mobilenet model I've retrained like the guy on youtube.

I chose the model ssd_mobilenet_v2_coco from the Tensorflow Model Zoo. After the retraining process I've got the model with the following structure:

- saved_model
    - variables (empty folder)
    - saved_model.pb
- checkpoint
- frozen_inverence_graph.pb
- model.ckpt.data-00000-of-00001
- model.ckpt.index
- model.ckpt.meta
- pipeline.config

In the same folder, I have the python script with the following code:

import tensorflow as tf

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

After running this code, I got the following error:

ValueError: None is only supported in the 1st dimension. Tensor 'image_tensor' has invalid shape '[None, None, None, 3]'.

It seems, that the image width and hight is missing in the model. When I use the model like in the youtube video, it is working.

After lots of research and attempts I tried other ways, like running bazel/toco, but nothing helped me to create a tflite-file.

Answer 1

As it describes in documentation, you can pass different parameters in tf.lite.TFLiteConverter.from_saved_model.

For more complex SavedModels, the optional parameters that can be passed into TFLiteConverter.from_saved_model() are input_arrays, input_shapes, output_arrays, tag_set and signature_key. Details of each parameter are available by running help(tf.lite.TFLiteConverter).

You can pass this information as described here. You need to provide input tensor name and its shape, and also output tensor name and its shape. And for ssd_mobilenet_v2_coco, you need to define on which input shape you need to use the network like this:

tf.lite.TFLiteConverter.from_saved_model("saved_model", input_shapes={"image_tensor" : [1,300,300,3]})