4 Image Generation with GANs

This chapter covers

Designing a generator by mirroring steps in the discriminator network.
Understanding how a 2D convolutional operation works on an image.
Learning how a 2D transposed convolutional operation inserts gaps between the output values and generates feature maps of a higher resolution.
Building and training GANs to generate grayscale and color images.

You have successfully generated an exponential growth curve and a sequence of integers that are all multiples of five in Chapter 3. Now that you understand how GANs work, you are ready to apply the same skillsets to generate many other forms of content such as high-resolution color images and realistic-sounding music. However, this may be easier said than done (you know what they say, the devil is in the details). For example, exactly how can we make the generator conjure up realistic images out of thin air? That’s the question we’re going to tackle in this chapter.

4.1 GANs to Generate Grayscale Images of Clothing Items

4.1.1 Training Samples and the Discriminator

4.1.2 A Generator to Create Grayscale Images

4.1.3 Train GANs to Generate Images of Clothing Items

4.2 Convolutional Layers

4.2.1 How do convolutional operations work?

4.2.2 How do stride and padding affect convolutional operations?

4.3 Transposed Convolution and Batch Normalization

4.3.1 How do transposed convolutional layers work?

4.3.2 Batch Normalization

4.4 Color Images of Anime Faces

4.4.1 Download Anime Faces

4.4.2 Channels-First Color Images in PyTorch

4.5 Deep Convolutional GAN (DCGAN)

4.5.1 Build A DCGAN

4.5.2 Train and Use DCGAN

4.6 Summary