Summary

We started our journey in this chapter with an introduction to computer vision and image processing, where we learned the different applications of such technology, how digital images are represented, and analyzed this with filters.

Then, we dived into the basic elements of CNN. We learned what a convolution operation is, how filters work in detecting patterns, and what stride and padding are used for. After understanding these building blocks, we learned how to use TensorFlow to design CNN models. We built our own CNN architecture to recognize handwritten digits.

After this, we went through data generators and learned how they can feed our model with batches of images rather than loading the entire dataset. We also learned how they can perform data augmentation transformations to expand the variety of images and help the model generalize better.

Finally, we learned about saving a model and its configuration, but also about how to apply transfer learning and fine-tuning...