From the course: Deep Learning: Image Recognition
Join today to access over 24,500 courses taught by industry experts.
Advanced CNN architectures - Python Tutorial
From the course: Deep Learning: Image Recognition
Advanced CNN architectures
- Now next, before we move on to the advanced convolutional neural networks, let's make a quick summary of what we have done so far. Well, we discussed the basic CNNs and their effectiveness in image recognition tasks. This session focuses on an enhanced CNN model incorporating advanced techniques like batch normalization and dropout to improve accuracy, and more importantly, generalization. Well, let's go ahead and summarize what we have done first. So we prepped the data. Remember we first imported the libraries, then we loaded the CIFAR-10 data set with just one line, which loaded 60,000 images, which are 32x32 color images in 10 classes such as airplane, horse, deer, et cetera. Then what we have done is we normalize the pixel values to be between zero and one, so that our model understands it better. Next, we did one-hot encoding, which was conversion of the class labels to one-hot encoded vectors. Well, we always display the images so that we see what we are working with. So we…
Download courses and learn on the go
Watch courses on your mobile device without an internet connection. Download courses using your iOS or Android LinkedIn Learning app.
