f93beff338925cc1bf1b3ff1b32a2c440a4c9427,tests/_tests_scripts/z_mvp_mnist_gan.py,CustomRunner,_handle_batch,#CustomRunner#Any#,18

Before Change

        // fake
        generated_labels_ = torch.zeros(bs, 1).to(self.device)
        generated_pred_ = self.model["discriminator"](
            generated_images.detach()
        )
        fake_loss = F.binary_cross_entropy(generated_pred_, generated_labels_)

        // loss
        loss_discriminator = (real_loss + fake_loss) / 2.0
        self.state.batch_metrics["loss_discriminator"] = loss_discriminator


def main():

After Change

class CustomRunner(dl.Runner):
    def _handle_batch(self, batch):
        real_images, _ = batch
        batch_metrics = {}

        // Sample random points in the latent space
        batch_size = real_images.shape[0]
        random_latent_vectors = torch.randn(batch_size, latent_dim).to(
            self.device
        )

        // Decode them to fake images
        generated_images = self.model["generator"](
            random_latent_vectors
        ).detach()
        // Combine them with real images
        combined_images = torch.cat([generated_images, real_images])

        // Assemble labels discriminating real from fake images
        labels = torch.cat(
            [torch.ones((batch_size, 1)), torch.zeros((batch_size, 1))]
        ).to(self.device)
        // Add random noise to the labels - important trick!
        labels += 0.05 * torch.rand(labels.shape).to(self.device)

        // Train the discriminator
        predictions = self.model["discriminator"](combined_images)
        batch_metrics[
            "loss_discriminator"
        ] = F.binary_cross_entropy_with_logits(predictions, labels)

        // Sample random points in the latent space
        random_latent_vectors = torch.randn(batch_size, latent_dim).to(
            self.device
        )
        // Assemble labels that say "all real images"
        misleading_labels = torch.zeros((batch_size, 1)).to(self.device)

        // Train the generator
        generated_images = self.model["generator"](random_latent_vectors)
        predictions = self.model["discriminator"](generated_images)
        batch_metrics["loss_generator"] = F.binary_cross_entropy_with_logits(
            predictions, misleading_labels
        )

Instances