CODEWITHSUNDEEP
tensorflowtransfer-learning
Entropie_13
Entropie_13

Reputation: 21

tensorflow - ValueError: Could not find matching function to call loaded from the SavedModel

I am trying to follow a guide for transfer learning from a textbook using the code below and get the error message above. I assume the input_shape does not match the IMAGE_SHAPE but I can't figure out the correct dimensions.

Code:

import tensorflow as tf
import tensorflow_hub as hub
import numpy as np
import matplotlib.pyplot as plt

module_url = "https://tfhub.dev/google/imagenet/mobilenet_v2_100_160/feature_vector/4"
my_model = hub.KerasLayer(module_url)

classifier_url = "https://tfhub.dev/google/imagenet/mobilenet_v2_100_160/feature_vector/4"
IMAGE_SHAPE = (224,224)

classifier = tf.keras.Sequential([hub.KerasLayer(classifier_url, input_shape = IMAGE_SHAPE+(3,))])

Error message:

    graph_function = self._create_graph_function(args, kwargs)
/usr/local/lib/python3.7/dist-packages/tensorflow/python/eager/function.py:3289 _create_graph_function
    capture_by_value=self._capture_by_value),
/usr/local/lib/python3.7/dist-packages/tensorflow/python/framework/func_graph.py:999 func_graph_from_py_func
    func_outputs = python_func(*func_args, **func_kwargs)
/usr/local/lib/python3.7/dist-packages/tensorflow/python/eager/def_function.py:672 wrapped_fn
    out = weak_wrapped_fn().__wrapped__(*args, **kwds)
/usr/local/lib/python3.7/dist-packages/tensorflow/python/saved_model/function_deserialization.py:291 restored_function_body
    "\n\n".join(signature_descriptions)))

ValueError: Could not find matching function to call loaded from the SavedModel. Got:
  Positional arguments (4 total):
    * Tensor("inputs:0", shape=(None, 224, 224, 3), dtype=float32)
    * False
    * False
    * 0.99
  Keyword arguments: {}

Expected these arguments to match one of the following 4 option(s):

Option 1:
  Positional arguments (4 total):
    * TensorSpec(shape=(None, 160, 160, 3), dtype=tf.float32, name='inputs')
    * False
    * False
    * TensorSpec(shape=(), dtype=tf.float32, name='batch_norm_momentum')
  Keyword arguments: {}

Option 2:
  Positional arguments (4 total):
    * TensorSpec(shape=(None, 160, 160, 3), dtype=tf.float32, name='inputs')
    * False
    * True
    * TensorSpec(shape=(), dtype=tf.float32, name='batch_norm_momentum')
  Keyword arguments: {}

Option 3:
  Positional arguments (4 total):
    * TensorSpec(shape=(None, 160, 160, 3), dtype=tf.float32, name='inputs')
    * True
    * True
    * TensorSpec(shape=(), dtype=tf.float32, name='batch_norm_momentum')
  Keyword arguments: {}

Option 4:
  Positional arguments (4 total):
    * TensorSpec(shape=(None, 160, 160, 3), dtype=tf.float32, name='inputs')
    * True
    * False
    * TensorSpec(shape=(), dtype=tf.float32, name='batch_norm_momentum')
  Keyword arguments: {}

Upvotes: 0

Views: 999

Answers (1)

WGierke
WGierke

Reputation: 603

You can find the documentation of the model you'd like to use at https://tfhub.dev/google/imagenet/mobilenet_v2_100_160/feature_vector/4. There and in the error message it says that the input image needs to be of shape (160, 160, 3):

classifier_url = "https://tfhub.dev/google/imagenet/mobilenet_v2_100_160/feature_vector/4"
IMAGE_SHAPE = (160, 160)
classifier = tf.keras.Sequential([hub.KerasLayer(classifier_url, input_shape = IMAGE_SHAPE+(3,))])

Upvotes: 1

Related Questions