val_loss = val_loss / len(val_dataloader)
all_val_loss.append(val_loss)
# Print Metrics
print(
f"\nEpoch: {epoch+1}/{epochs}:\
\nTrain Loss = {train_loss}\
\nVal Loss = {val_loss}"
)
################################################################################
################################## Save & Test #################################
################################################################################
# Generate Loss Graph
graphics.draw_loss(all_train_loss, all_val_loss, output_prefix, mode="autoencoder")
# Save Model
torch.save(
{
"epoch": epoch,
"model_state_dict": model.state_dict(),
"optimizer_state_dict": optimizer.state_dict(),
"train_loss": all_train_loss,
"val_loss": all_val_loss,
"label_encoder": label_encoder,
},
model_output_path,
)
# Evaluation Time
train_loss = train_loss / len(train_dataloader)
all_train_loss.append(train_loss)
val_loss = val_loss / len(val_dataloader)
all_val_loss.append(val_loss)
# Print Metrics
print(f"\nEpoch: {epoch+1}/{epochs}:\
\nTrain Loss = {train_loss}\
\nVal Loss = {val_loss}")
################################################################################
################################## Save & Test #################################
################################################################################
# Generate Loss Graph
graphics.draw_loss(all_train_loss, all_val_loss, loss_output_path, mode="ae")
# Save Model
torch.save(model.state_dict(), model_output_path)
# Plot Animation Sample
fig, axis = graphics.make_grid(("Sample", sample), 4, 4)
plt.savefig(animation_sample_image_name)
# Create & Save Animation
Writer = animation.writers["ffmpeg"]
writer = Writer()
anim = graphics.make_animation(graphics.make_grid, all_samples)
anim.save(animation_output_path, writer=writer)
model.eval()
netD.eval()
# Generate a batch of fake images
with torch.no_grad():
# Generate batch of latent vectors
noise = torch.randn(batch_size, latent_dim, 1, 1, device=device)
# Generate fake image batch with G
generated = netG(noise).detach().cpu()
# Plot fake images
fig, axis = graphics.make_grid(("Test Sample", generated), 4, 4)
plt.savefig(os.path.join(output_dir, f"epoch_{epoch}_test_sample_output.jpg"))
################################################################################
################################## Save & Test #################################
################################################################################
# Save output graphs
graphics.draw_loss(
all_generator_loss, all_discriminator_loss, loss_output_path, mode="gan"
)
# Create & Save Animation
anim = graphics.make_gan_animation(training_samples)
anim.save(animation_output_path)
# Pick a couple of sample images for an Input v Output comparison
sample = data.get_samples_from_data(dataset, 16)
# Plot A Set of Test Images
fig, axis = graphics.make_grid(("Test Sample", sample), 4, 4)
plt.savefig(test_sample_input_name)
