deeplizard demonstrates how to use data augmentation on images using TensorFlow’s Keras API.
VIDEO SECTIONS
Yannic Kilcher explains why transformers are ruining convolutions.
This paper, under review at ICLR, shows that given enough data, a standard Transformer can outperform Convolutional Neural Networks in image recognition tasks, which are classically tasks where CNNs excel. In this Video, I explain the architecture of the Vision Transformer (ViT), the reason why it works better and rant about why double-bline peer review is broken.
OUTLINE:
Related resources:
In this episode, Mandy from deeplizard will be building on what we’ve learned about MobileNet combined with the techniques we’ve used for fine-tuning to fine-tune MobileNet for a custom image data set using TensorFlow’s Keras API.
In this deeplizard episode, learn how to prepare and process our own custom data set of sign language digits, which will be used to train our fine-tuned MobileNet model in a future episode.
VIDEO SECTIONS
deeplizard introduces MobileNets, a class of light weight deep convolutional neural networks that are vastly smaller in size and faster in performance than many other popular models.
VIDEO SECTIONS
vcubingx provides a visual introduction to the structure of an artificial neural network.
The Neural Network, A Visual Introduction | Visualizing Deep Learning, Chapter 1
In this video, Mandy from deeplizard demonstrates how to use the fine-tuned VGG16 Keras model that we trained in the last episode to predict on images of cats and dogs in our test set.
Index:
In this video, Mandy from deeplizard demonstrate how to fine-tune a pre-trained model called VGG16 to classify images as cats and dogs.
In this episode, deeplizard demonstrates the various ways of saving and loading a Sequential model using TensorFlow’s Keras API.
deeplizard demonstrates how to create a confusion matrix, which will aid us in being able to visually observe how well a neural network is predicting during inference.
VIDEO SECTIONS
