使用 PYTORCH 进行图像风格迁移

import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim

from PIL import Image
import matplotlib.pyplot as plt

import torchvision.transforms as transforms
import torchvision.models as models

import copy

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

# desired size of the output image
imsize = 512 if torch.cuda.is_available() else 128  # use small size if no GPU

loader = transforms.Compose([
    transforms.Resize(imsize),  # scale imported image
    transforms.ToTensor()])  # transform it into a torch tensor


def image_loader(image_name):
    image = Image.open(image_name)
    # fake batch dimension required to fit network's input dimensions
    image = loader(image).unsqueeze(0)
    return image.to(device, torch.float)


style_img = image_loader("./data/images/neural-style/picasso.jpg")
content_img = image_loader("./data/images/neural-style/dancing.jpg")

assert style_img.size() == content_img.size(), \
    "we need to import style and content images of the same size"

unloader = transforms.ToPILImage()  # reconvert into PIL image

plt.ion()

def imshow(tensor, title=None):
    image = tensor.cpu().clone()  # we clone the tensor to not do changes on it
    image = image.squeeze(0)      # remove the fake batch dimension
    image = unloader(image)
    plt.imshow(image)
    if title is not None:
        plt.title(title)
    plt.pause(0.001) # pause a bit so that plots are updated


plt.figure()
imshow(style_img, title='Style Image')

plt.figure()
imshow(content_img, title='Content Image')

笔记

        重要细节：虽然这个模块被命名ContentLoss，但它不是真正的 PyTorch Loss 函数。如果要将内容损失定义为 PyTorch Loss 函数，则必须创建 PyTorch autograd 函数以在方法中手动重新计算/实现梯度backward 。

cnn = models.vgg19(pretrained=True).features.eval()

/opt/conda/envs/py_3.10/lib/python3.10/site-packages/torchvision/models/_utils.py:208: UserWarning:

The parameter 'pretrained' is deprecated since 0.13 and may be removed in the future, please use 'weights' instead.

/opt/conda/envs/py_3.10/lib/python3.10/site-packages/torchvision/models/_utils.py:223: UserWarning:

Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and may be removed in the future. The current behavior is equivalent to passing `weights=VGG19_Weights.IMAGENET1K_V1`. You can also use `weights=VGG19_Weights.DEFAULT` to get the most up-to-date weights.

Downloading: "https://download.pytorch.org/models/vgg19-dcbb9e9d.pth" to /var/lib/jenkins/.cache/torch/hub/checkpoints/vgg19-dcbb9e9d.pth

  0%|          | 0.00/548M [00:00

cnn_normalization_mean = torch.tensor([0.485, 0.456, 0.406])
cnn_normalization_std = torch.tensor([0.229, 0.224, 0.225])

# create a module to normalize input image so we can easily put it in a
# ``nn.Sequential``
class Normalization(nn.Module):
    def __init__(self, mean, std):
        super(Normalization, self).__init__()
        # .view the mean and std to make them [C x 1 x 1] so that they can
        # directly work with image Tensor of shape [B x C x H x W].
        # B is batch size. C is number of channels. H is height and W is width.
        self.mean = torch.tensor(mean).view(-1, 1, 1)
        self.std = torch.tensor(std).view(-1, 1, 1)

    def forward(self, img):
        # normalize ``img``
        return (img - self.mean) / self.std

# desired depth layers to compute style/content losses :
content_layers_default = ['conv_4']
style_layers_default = ['conv_1', 'conv_2', 'conv_3', 'conv_4', 'conv_5']

def get_style_model_and_losses(cnn, normalization_mean, normalization_std,
                               style_img, content_img,
                               content_layers=content_layers_default,
                               style_layers=style_layers_default):
    # normalization module
    normalization = Normalization(normalization_mean, normalization_std)

    # just in order to have an iterable access to or list of content/style
    # losses
    content_losses = []
    style_losses = []

    # assuming that ``cnn`` is a ``nn.Sequential``, so we make a new ``nn.Sequential``
    # to put in modules that are supposed to be activated sequentially
    model = nn.Sequential(normalization)

    i = 0  # increment every time we see a conv
    for layer in cnn.children():
        if isinstance(layer, nn.Conv2d):
            i += 1
            name = 'conv_{}'.format(i)
        elif isinstance(layer, nn.ReLU):
            name = 'relu_{}'.format(i)
            # The in-place version doesn't play very nicely with the ``ContentLoss``
            # and ``StyleLoss`` we insert below. So we replace with out-of-place
            # ones here.
            layer = nn.ReLU(inplace=False)
        elif isinstance(layer, nn.MaxPool2d):
            name = 'pool_{}'.format(i)
        elif isinstance(layer, nn.BatchNorm2d):
            name = 'bn_{}'.format(i)
        else:
            raise RuntimeError('Unrecognized layer: {}'.format(layer.__class__.__name__))

        model.add_module(name, layer)

        if name in content_layers:
            # add content loss:
            target = model(content_img).detach()
            content_loss = ContentLoss(target)
            model.add_module("content_loss_{}".format(i), content_loss)
            content_losses.append(content_loss)

        if name in style_layers:
            # add style loss:
            target_feature = model(style_img).detach()
            style_loss = StyleLoss(target_feature)
            model.add_module("style_loss_{}".format(i), style_loss)
            style_losses.append(style_loss)

    # now we trim off the layers after the last content and style losses
    for i in range(len(model) - 1, -1, -1):
        if isinstance(model[i], ContentLoss) or isinstance(model[i], StyleLoss):
            break

    model = model[:(i + 1)]

    return model, style_losses, content_losses

input_img = content_img.clone()
# if you want to use white noise by using the following code:
#
# ::
#
# input_img = torch.randn(content_img.data.size())

# add the original input image to the figure:
plt.figure()
imshow(input_img, title='Input Image')

def get_input_optimizer(input_img):
    # this line to show that input is a parameter that requires a gradient
    optimizer = optim.LBFGS([input_img])
    return optimizer

def run_style_transfer(cnn, normalization_mean, normalization_std,
                       content_img, style_img, input_img, num_steps=300,
                       style_weight=1000000, content_weight=1):
    """Run the style transfer."""
    print('Building the style transfer model..')
    model, style_losses, content_losses = get_style_model_and_losses(cnn,
        normalization_mean, normalization_std, style_img, content_img)

    # We want to optimize the input and not the model parameters so we
    # update all the requires_grad fields accordingly
    input_img.requires_grad_(True)
    # We also put the model in evaluation mode, so that specific layers
    # such as dropout or batch normalization layers behave correctly.
    model.eval()
    model.requires_grad_(False)

    optimizer = get_input_optimizer(input_img)

    print('Optimizing..')
    run = [0]
    while run[0] <= num_steps:

        def closure():
            # correct the values of updated input image
            with torch.no_grad():
                input_img.clamp_(0, 1)

            optimizer.zero_grad()
            model(input_img)
            style_score = 0
            content_score = 0

            for sl in style_losses:
                style_score += sl.loss
            for cl in content_losses:
                content_score += cl.loss

            style_score *= style_weight
            content_score *= content_weight

            loss = style_score + content_score
            loss.backward()

            run[0] += 1
            if run[0] % 50 == 0:
                print("run {}:".format(run))
                print('Style Loss : {:4f} Content Loss: {:4f}'.format(
                    style_score.item(), content_score.item()))
                print()

            return style_score + content_score

        optimizer.step(closure)

    # a last correction...
    with torch.no_grad():
        input_img.clamp_(0, 1)

    return input_img

output = run_style_transfer(cnn, cnn_normalization_mean, cnn_normalization_std,
                            content_img, style_img, input_img)

plt.figure()
imshow(output, title='Output Image')

# sphinx_gallery_thumbnail_number = 4
plt.ioff()
plt.show()

Building the style transfer model..
/opt/conda/envs/py_3.10/lib/python3.10/site-packages/torch/utils/_device.py:77: UserWarning:

To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).

Optimizing..
run [50]:
Style Loss : 4.124115 Content Loss: 4.153235

run [100]:
Style Loss : 1.121803 Content Loss: 3.012928

run [150]:
Style Loss : 0.696039 Content Loss: 2.639936

run [200]:
Style Loss : 0.469292 Content Loss: 2.485867

run [250]:
Style Loss : 0.341620 Content Loss: 2.400899

run [300]:
Style Loss : 0.263747 Content Loss: 2.347282