How can Tensorflow and pre-trained model be used to add classification head to the model?

Tensorflow and the pre-trained model can be used to add classification head to the model using the ‘GlobalAveragePooling2D’ method, which is assigned to a variable. This variable is used on the batch of features of the input data.

Read More: What is TensorFlow and how Keras work with TensorFlow to create Neural Networks?

A neural network that contains at least one layer is known as a convolutional layer. We can use the Convolutional Neural Network to build learning model. 

We will understand how to classify images of cats and dogs with the help of transfer learning from a pre-trained network. The intuition behind transfer learning for image classification is, if a model is trained on a large and general dataset, this model can be used to effectively serve as a generic model for the visual world. It would have learned the feature maps, which means the user won’t have to start from scratch by training a large model on a large dataset.

Read More: How can a customized model be pre-trained?

We are using the Google Colaboratory to run the below code. Google Colab or Colaboratory helps run Python code over the browser and requires zero configuration and free access to GPUs (Graphical Processing Units). Colaboratory has been built on top of Jupyter Notebook.


print("Adding a classification head")
global_average_layer = tf.keras.layers.GlobalAveragePooling2D()
feature_batch_average = global_average_layer(feature_batch)

Code credit −


Adding a classification head
(32, 1280)


  • Predictions are generated from blocks of features, average over 5x5 spatial locations.

  • This is done using tf.keras.layers.GlobalAveragePooling2D layer.

  • This layer helps convert features to a single 1280 element vector for every image.