ISSUE : Sequential model 'sequential_1' has already been configured to use input shape (None, 224, 224, 3). You cannot build it with input_shape [None, 224, 224, 3]

[thayyilakul]

Currently learning tensorflow with keras and got this error while loading saved model which is saved in keras extension.
ValueError: Sequential model 'sequential_1' has already been configured to use input shape (None, 224, 224, 3). You cannot build it with input_shape [None, 224, 224, 3]

Below is my model creation function

def create_model(input_shape = INPUT_SHAPE, output_shape = OUTPUT_SHAPE, model_url = MODEL_URL):
  print('Building model with: ',MODEL_URL)

  hubs_layer = hub.KerasLayer(MODEL_URL)
  model = tf.keras.Sequential([
       tf.keras.layers.Lambda(lambda x: hubs_layer(x)), # Layer 1 (input layer)
      tf.keras.layers.Dense(units = OUTPUT_SHAPE,
                            activation = 'softmax') # Layer 2 (output layer)
  ])
  model.compile(
      loss = tf.keras.losses.CategoricalCrossentropy(),
      optimizer = tf.keras.optimizers.Adam(),
      metrics = ['accuracy']
  )
  model.build(INPUT_SHAPE)
  return model`

MODEL_URL is just a kaggle dataset mobilenet-v2

Below is my load model function

# Create a function to load a trained model
def load_model(model_path):
  '''
  Loads a saved model from a specified path
  '''
  print(f'Loading saved model from: {model_path}')

  # Enable unsafe deserialization
  # tf.keras.config.enable_unsafe_deserialization()

  # model = tf.keras.models.load_model(model_path, 
  #                                    custom_objects = {'KerasLayer' : hub.KerasLayer})
  model = tf.keras.models.load_model(model_path)
  return model

Below is how i am calling load function
loaded_1000_image_model = load_model('filename.keras')

[mehtamansi29]

Hi @thayyilakul -

Thanks for reporting this issue. Can you please let me know exactly at which line you are getting error ? I am not able to get error while running this function(create_model()). Attached gist for the reference.

[thayyilakul]

Hi, thank you for your reply, well it's happening when i call the function load_model() after i save the model.

[mehtamansi29]

Hi @thayyilakul -

Here in this gist you can find successfully load model with custom_objects and without custom_objects.

[github-actions]

This issue is stale because it has been open for 14 days with no activity. It will be closed if no further activity occurs. Thank you.

[github-actions]

This issue was closed because it has been inactive for 28 days. Please reopen if you'd like to work on this further.

[google-ml-butler]

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

[metnbyar]

çözebildiniz mi