Tensorflow and the pre-trained model can be used to chain data augmentation, rescaling and base model by first defining the size of the input. Once this is done, the previously defined functions namely ‘data_augmentation’, ‘base_model’ are called by passing the relevant output.
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("Chaining together data augmentation, rescaling, base_model and feature extractor layers") inputs = tf.keras.Input(shape=(160, 160, 3)) x = data_augmentation(inputs) x = preprocess_input(x) x = base_model(x, training=False) x = global_average_layer(x) x = tf.keras.layers.Dropout(0.2)(x) outputs = prediction_layer(x) model = tf.keras.Model(inputs, outputs)
Chaining together data augmentation, rescaling, base_model and feature extractor layers
A model is built by chaining data augmentation, rescaling, base_model and feature extractor layers.
This is done with the help of the Keras Functional API.
The training=False is used since the model contains a BatchNormalization layer.