How can Tensorflow and pre-trained model be used to convert features into single prediction per image?

Tensorflow and the pre-trained model can be used to convert features into single prediction per image by creating a ‘Dense’ layer and applying it to every image in the sequential model.

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("Converting features into single prediction per image")
prediction_layer = tf.keras.layers.Dense(1)
prediction_batch = prediction_layer(feature_batch_average)

Code credit −


Converting features into single prediction per image
(32, 1)


  • A tf.keras.layers.Dense layer is applied.

  • This helps convert features into a single prediction per image.

  • An activation function is not needed since this prediction would be treated as a logit, or a raw prediction value.

  • Positive numbers predict class 1, negative numbers predict class 0.