Beeldgeneratie

import numpy as np
import torch
import torch.nn.functional as F
import torchvision
from datasets import load_dataset
from diffusers import DDPMScheduler, UNet2DModel
from matplotlib import pyplot as plt
from PIL import Image
from torchvision import transforms

device = torch.device("cuda" if torch.cuda.is_available() else "cpu")

dataset = load_dataset("huggan/smithsonian_butterflies_subset", split="train")

image_size = 32
batch_size = 32

preprocess = transforms.Compose(
    [
        transforms.Resize((image_size, image_size)),  # Resize
        transforms.RandomHorizontalFlip(),  # Randomly flip (data augmentation)
        transforms.ToTensor(),  # Convert to tensor (0, 1)
        transforms.Normalize([0.5], [0.5]),  # Map to (-1, 1)
    ]
)


def transform(examples):
    images = [preprocess(image.convert("RGB")) for image in examples["image"]]
    return {"images": images}


dataset.set_transform(transform)

# Create a dataloader from the dataset to serve up the transformed images in batches
train_dataloader = torch.utils.data.DataLoader(dataset, batch_size=batch_size, shuffle=True)

def show_images(x):
    """Given a batch of images x, make a grid and convert to PIL."""
    x = x * 0.5 + 0.5  # Map from (-1, 1) back to (0, 1)
    grid = torchvision.utils.make_grid(x)
    grid_im = grid.detach().cpu().permute(1, 2, 0).clip(0, 1) * 255
    grid_im = Image.fromarray(np.array(grid_im).astype(np.uint8))
    return grid_im

xb = next(iter(train_dataloader))["images"].to(device)[:8]
print("X shape:", xb.shape)
show_images(xb).resize((8 * 64, 64), resample=Image.NEAREST)

noise_scheduler = DDPMScheduler(num_train_timesteps=1000)

plt.plot(noise_scheduler.alphas_cumprod.cpu() ** 0.5, label=r"${\sqrt{\bar{\alpha}_t}}$")
plt.plot((1 - noise_scheduler.alphas_cumprod.cpu()) ** 0.5, label=r"$\sqrt{(1 - \bar{\alpha}_t)}$")
plt.legend(fontsize="x-large");

# One with too little noise added:
# noise_scheduler = DDPMScheduler(num_train_timesteps=1000, beta_start=0.001, beta_end=0.004)
# The 'cosine' schedule, which may be better for small image sizes:
# noise_scheduler = DDPMScheduler(num_train_timesteps=1000, beta_schedule='squaredcos_cap_v2')

timesteps = torch.linspace(0, 999, 8).long().to(device)
noise = torch.randn_like(xb)
noisy_xb = noise_scheduler.add_noise(xb, noise, timesteps)
print("Noisy X shape", noisy_xb.shape)
show_images(noisy_xb).resize((8 * 64, 64), resample=Image.NEAREST)

# Create a model
model = UNet2DModel(
    sample_size=image_size,  # the target image resolution
    in_channels=3,  # the number of input channels, 3 for RGB images
    out_channels=3,  # the number of output channels
    layers_per_block=2,  # how many ResNet layers to use per UNet block
    block_out_channels=(64, 128, 128, 256),  # More channels -> more parameters
    down_block_types=(
        "DownBlock2D",  # a regular ResNet downsampling block
        "DownBlock2D",
        "AttnDownBlock2D",  # a ResNet downsampling block with spatial self-attention
        "AttnDownBlock2D",
    ),
    up_block_types=(
        "AttnUpBlock2D",
        "AttnUpBlock2D",  # a ResNet upsampling block with spatial self-attention
        "UpBlock2D",
        "UpBlock2D",  # a regular ResNet upsampling block
    ),
)
model.to(device);

with torch.no_grad():
    model_prediction = model(noisy_xb, timesteps).sample
model_prediction.shape

# Set the noise scheduler
noise_scheduler = DDPMScheduler(num_train_timesteps=1000, beta_schedule="squaredcos_cap_v2")

# Training loop
optimizer = torch.optim.AdamW(model.parameters(), lr=4e-4)

losses = []

for epoch in range(30):
    for step, batch in enumerate(train_dataloader):
        clean_images = batch["images"].to(device)
        # Sample noise to add to the images
        noise = torch.randn(clean_images.shape).to(clean_images.device)
        bs = clean_images.shape[0]

        # Sample a random timestep for each image
        timesteps = torch.randint(
            0, noise_scheduler.num_train_timesteps, (bs,), device=clean_images.device
        ).long()

        # Add noise to the clean images according to the noise magnitude at each timestep
        noisy_images = noise_scheduler.add_noise(clean_images, noise, timesteps)

        # Get the model prediction
        noise_pred = model(noisy_images, timesteps, return_dict=False)[0]

        # Calculate the loss
        loss = F.mse_loss(noise_pred, noise)
        loss.backward(loss)
        losses.append(loss.item())

        # Update the model parameters with the optimizer
        optimizer.step()
        optimizer.zero_grad()

    if (epoch + 1) % 5 == 0:
        loss_last_epoch = sum(losses[-len(train_dataloader) :]) / len(train_dataloader)
        print(f"Epoch:{epoch + 1}, loss: {loss_last_epoch}")

fig, axs = plt.subplots(1, 2, figsize=(12, 4))
axs[0].plot(losses)
axs[1].plot(np.log(losses))
plt.show()

# Random starting point (8 random images):
sample = torch.randn(8, 3, 32, 32).to(device)

for i, t in enumerate(noise_scheduler.timesteps):
    # Get model pred
    with torch.no_grad():
        residual = model(sample, t).sample

    # Update sample with step
    sample = noise_scheduler.step(residual, t, sample).prev_sample

show_images(sample)