Mastering Computer Vision with TensorFlow 2.x

Separating the file by train and test folders

In this section, we will divide our dataset into train and test folders. This is needed as the train model uses the train dataset to generate the model and test dataset to validate. Note that sometimes the test and val names can be used interchangeably to mean the same thing. But in general, we need a third folder to also check our final model against some unknown images that the model has not seen before. The folder containing those images is called val—it will be discussed later.

Follow the steps listed here to separate images into train and test folders. Note that these tasks will be done on Google Colab:

1. If you follow the preceding steps, you have two folders—one for the image and one for ...