Tensorflow can be used with pre-trained model to build the training and validation dataset with the help of the ‘image_dataset_from_directory’ method. This method takes the batch size, image size, and whether to shuffle or not values as parameters, along with the training data or validation data respectively.
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("Training dataset") train_dataset = image_dataset_from_directory(train_dir, shuffle=True, batch_size=BATCH_SIZE, image_size=IMG_SIZE) print("Validation dataset") validation_dataset = image_dataset_from_directory(validation_dir, shuffle=True, batch_size=BATCH_SIZE, image_size=IMG_SIZE)
Training dataset Found 2000 files belonging to 2 classes. Validation dataset Found 1000 files belonging to 2 classes.
The training and validation dataset are built using the downloaded images of cats and dogs.