Computer Vision News - January 2023

9 Feature Extraction Layers in ConvNets history_frame = pd.DataFrame(history.history) history_frame.loc[:, ['loss', 'val_loss']].plot() history_frame.loc[:, ['binary_accuracy', 'val_binary_accuracy']].plot(); This model is much smaller than the VGG16 model from Lesson 1 -- only 3 convolutional layers versus the 16 of VGG16. It was nevertheless able to fit this dataset fairly well. We might still be able to improve this simple model by adding more convolutional layers, hoping to create features which are better adapted to the dataset. This is what we'll try in the exercises. Conclusion In this tutorial, you saw how to build a custom convnet composed of many convolutional blocks and capable of complex feature engineering. Next month I’ve received two emails asking for articles but (if you missed my last review), I am writing a coding tutorial every second month. Don’t worry though; meanwhile you can enjoy the amazing work done by the magazine and my amazing colleague Marica! Take care and as always have a great time and always be curious! 