import sys import numpy import torch import torch.nn as nn from torch.autograd import Function from torch.optim.lr_scheduler import _LRScheduler import torchvision import torchvision.transforms as transforms import torchvision.utils as vutils from torch.utils.data import DataLoader from dataset import Dataset_FullImg, Dataset_DiscRegion import math import PIL import matplotlib.pyplot as plt import seaborn as sns import collections import logging import math import os import time from datetime import datetime import dateutil.tz from typing import Union, Optional, List, Tuple, Text, BinaryIO import pathlib import warnings import numpy as np from PIL import Image, ImageDraw, ImageFont, ImageColor from lucent.optvis.param.spatial import pixel_image, fft_image, init_image from lucent.optvis.param.color import to_valid_rgb from torchvision.models import vgg19 import torch.nn.functional as F import cfg import warnings from collections import OrderedDict import numpy as np from tqdm import tqdm from PIL import Image import torch args = cfg.parse_args() device = torch.device('cuda', args.gpu_device) cnn = vgg19(pretrained=True).features.to(device).eval() content_layers_default = ['conv_4'] style_layers_default = ['conv_1', 'conv_2', 'conv_3', 'conv_4', 'conv_5'] cnn_normalization_mean = torch.tensor([0.485, 0.456, 0.406]).to(device) cnn_normalization_std = torch.tensor([0.229, 0.224, 0.225]).to(device) class ContentLoss(nn.Module): def __init__(self, target,): super(ContentLoss, self).__init__() # we 'detach' the target content from the tree used # to dynamically compute the gradient: this is a stated value, # not a variable. Otherwise the forward method of the criterion # will throw an error. self.target = target.detach() def forward(self, input): self.loss = F.mse_loss(input, self.target) return input def gram_matrix(input): a, b, c, d = input.size() # a=batch size(=1) # b=number of feature maps # (c,d)=dimensions of a f. map (N=c*d) features = input.view(a * b, c * d) # resise F_XL into \hat F_XL G = torch.mm(features, features.t()) # compute the gram product # we 'normalize' the values of the gram matrix # by dividing by the number of element in each feature maps. return G.div(a * b * c * d) class StyleLoss(nn.Module): def __init__(self, target_feature): super(StyleLoss, self).__init__() self.target = gram_matrix(target_feature).detach() def forward(self, input): G = gram_matrix(input) self.loss = F.mse_loss(G, self.target) return input # 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 def run_precpt(cnn, normalization_mean, normalization_std, content_img, style_img, input_img, style_weight=1000000, content_weight=1): model, style_losses, content_losses = precpt_loss(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 model.requires_grad_(False) input_img.requires_grad_(True) 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 content_weight = 100 style_weight = 100000 style_score *= style_weight content_score *= content_weight loss = style_score + content_score # loss = content_score return loss def precpt_loss(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).to(device) # just in order to have an iterable access to or list of content/syle # 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: if style_img.size(1) == 1: style_img = style_img.expand(style_img.size(0),3, style_img.size(2),style_img.size(3)) 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