1. Learn
    2. /
  2. Courses
    3. /
  3. Intermediate Deep Learning with PyTorch
  • 1

    Training Robust Neural Networks

    Free

    Learn how to train neural networks in a robust way. In this chapter, you will use object-oriented programming to define PyTorch datasets and models and refresh your knowledge of training and evaluating neural networks. You will also get familiar with different optimizers and, finally, get to grips with various techniques that help mitigate the problems of unstable gradients so ubiquitous in neural nets training.

  • 2

    Images & Convolutional Neural Networks

    Train neural networks to solve image classification tasks. In this chapter, you will learn how to handle image data in PyTorch and get to grips with convolutional neural networks (CNNs). You will practice training and evaluating an image classifier while learning about how to improve the model performance with data augmentation.

  • 3

    Sequences & Recurrent Neural Networks

    Build and train recurrent neural networks (RNNs) for processing sequential data such as time series, text, or audio. You will learn about the two most popular recurrent architectures, Long-Short Term Memory (LSTM) and Gated Recurrent Unit (GRU) networks, as well as how to prepare sequential data for model training. You will practice your skills by training and evaluating a recurrent model for predicting electricity consumption.

  • 4

    Multi-Input & Multi-Output Architectures

    Build multi-input and multi-output models, demonstrating how they can handle tasks requiring more than one input or generating multiple outputs. You will explore how to design and train these models using PyTorch and delve into the crucial topic of loss weighting in multi-output models. This involves understanding how to balance the importance of different tasks when training a model to perform multiple tasks simultaneously.

Initializing

Exercise

Two-output model architecture

In this exercise, you will construct a multi-output neural network architecture capable of predicting the character and the alphabet.

Recall the general structure: in the .__init__() method, you define layers to be used in the forward pass later. In the forward() method, you will first pass the input image through a couple of layers to obtain its embedding, which in turn is fed into two separate classifier layers, one for each output.

torch.nn is already imported under its usual alias, so let's build a model!

Instructions 1/2

undefined XP
    1
    2
  • Define self.classifier_alpha and self.classifier_char as linear layers with input shapes matching the output of image_layer, and output shapes corresponding to the number of alphabets (30) and the number of characters (964), respectively.