Input size of converted lite model doesn't match the original model input size

[hahmad2008]

System information

• COLAB:
• TensorFlow version 2.4.0-dev20200805:

Command used to run the converter or code if you’re using the Python API this Link for code I used in converting the saved model to TensorFlow lite

!pip install tf-nightly
model_dir=saved_model'
converter = tf.lite.TFLiteConverter.from_saved_model(model_dir,signature_keys=['serving_default'],)

converter.optimizations = [tf.lite.Optimize.DEFAULT]
converter.experimental_new_converter = True
converter.target_spec.supported_ops = [tf.lite.OpsSet.TFLITE_BUILTINS, tf.lite.OpsSet.SELECT_TF_OPS]

tflite_model = converter.convert()

#open("saved_model/converted_model.tflite", "wb").write(tflite_model)
open('tflite_model.tflite','wb').write(tflite_model)

The output from the converter invocation

• successfully generate the model.tflite
• But When I checked the input for both the original and converted model, I found the following mismatching:
• • checked the input for the model I got it as [1,1,1,3] instead of [1,300,300,3] -- in my config file to train the object detection model, I have the following image resize:

    image_resizer {
    fixed_shape_resizer {
    height: 300
    width: 300
    }
    }

The original model I used is saved model, It is the same as all models in the model zoo.

I was training the object detection API and run it successfully with original .pb saved model (using this backbone model)

Any recommendations here? Thanks.

[MeghnaNatraj]

I was able to get this working by running the following code:

!pip install tf-nightly
import tensorflow as tf

## TFLite Conversion
# Before conversion, fix the model input size
model = tf.saved_model.load("saved_model")
model.signatures[tf.saved_model.DEFAULT_SERVING_SIGNATURE_DEF_KEY].inputs[0].set_shape([1, 300, 300, 3])
tf.saved_model.save(model, "saved_model_updated", signatures=model.signatures[tf.saved_model.DEFAULT_SERVING_SIGNATURE_DEF_KEY])
# Convert
converter = tf.lite.TFLiteConverter.from_saved_model(saved_model_dir='saved_model_updated', signature_keys=['serving_default'])
converter.optimizations = [tf.lite.Optimize.DEFAULT]
converter.target_spec.supported_ops = [tf.lite.OpsSet.TFLITE_BUILTINS, tf.lite.OpsSet.SELECT_TF_OPS]
tflite_model = converter.convert()

## TFLite Interpreter to check input shape
interpreter = tf.lite.Interpreter(model_content=tflite_model)
interpreter.allocate_tensors()

# Get input and output tensors.
input_details = interpreter.get_input_details()
output_details = interpreter.get_output_details()

# Test the model on random input data.
input_shape = input_details[0]['shape']
print(input_shape)

[  1 300 300   3]

Feel free to re-open this if you still face an issue.

[google-ml-butler[bot]]

Are you satisfied with the resolution of your issue? Yes No

[hahmad2008]

@MeghnaNatraj Thank you so much :) I really appreciate it. it works now 👯

[utkrist-karky]

Try this: model = tf.saved_model.load("dir/to/model") concrete_func = model.signatures[ tf.saved_model.DEFAULT_SERVING_SIGNATURE_DEF_KEY] concrete_func.inputs[0].set_shape([None, 224, 224, 3]) #your input size converter = tf.lite.TFLiteConverter.from_concrete_functions([concrete_func]) tflite_model = converter.convert() with open('model.tflite', 'wb') as f: f.write(tflite_model)

[creativesh]

@utkrist-karky Thanks, your approach worked for me.

[patrickjdarrow]

@MeghnaNatraj When saving the updated SavedModel, the input shape is not retained for me:

model = tf.saved_model.load("saved_model") model.signatures[tf.saved_model.DEFAULT_SERVING_SIGNATURE_DEF_KEY].inputs[0].set_shape([1, 300, 300, 3]) tf.saved_model.save(model, "saved_model_updated", signatures=model.signatures[tf.saved_model.DEFAULT_SERVING_SIGNATURE_DEF_KEY]) ... model = tf.saved_model.load("saved_model_updated") model.signatures[tf.saved_model.DEFAULT_SERVING_SIGNATURE_DEF_KEY].inputs[0].shape

TensorShape([None, None, None, 3])

Update, I found the issue:

In from_concrete_functions I was passing model to avoid a scope issue when instantiating converter inside of a function.

concrete_func.inputs[0].set_shape(SHAPE)
converter = tf2.lite.TFLiteConverter.from_concrete_functions([concrete_func], model)

The workaround is to create a backref to the model using

 concrete_func._backref_to_saved_model = model

[karthik87s]

@utkrist-karky Your suggestion worked for me. Thanks.

[Monaco12138]

I was able to get this working by running the following code:

!pip install tf-nightly
import tensorflow as tf

## TFLite Conversion
# Before conversion, fix the model input size
model = tf.saved_model.load("saved_model")
model.signatures[tf.saved_model.DEFAULT_SERVING_SIGNATURE_DEF_KEY].inputs[0].set_shape([1, 300, 300, 3])
tf.saved_model.save(model, "saved_model_updated", signatures=model.signatures[tf.saved_model.DEFAULT_SERVING_SIGNATURE_DEF_KEY])
# Convert
converter = tf.lite.TFLiteConverter.from_saved_model(saved_model_dir='saved_model_updated', signature_keys=['serving_default'])
converter.optimizations = [tf.lite.Optimize.DEFAULT]
converter.target_spec.supported_ops = [tf.lite.OpsSet.TFLITE_BUILTINS, tf.lite.OpsSet.SELECT_TF_OPS]
tflite_model = converter.convert()

## TFLite Interpreter to check input shape
interpreter = tf.lite.Interpreter(model_content=tflite_model)
interpreter.allocate_tensors()

# Get input and output tensors.
input_details = interpreter.get_input_details()
output_details = interpreter.get_output_details()

# Test the model on random input data.
input_shape = input_details[0]['shape']
print(input_shape)

[  1 300 300   3]

Feel free to re-open this if you still face an issue.

Thanks, it works for me in tensorflow2.3 . Other verion of tensorflow like 2.8 failed to do that. However, it seems that using 'model = tf.saved_model.load()' is necessary, the model can not be load like keras.models.Model().