Python CNN风格迁移

本文仅供学习交流使用，如侵立删！demo下载见文末

环境：
python：3.6.7
tensorflow=2.2.0
torch=1.5.1+cpu
torchvision=0.6.0+cpu
Pillow=8.1.2

效果：

输入原图和风格图生成迁移图片

# -*- coding: utf-8 -*-
import cv2
import timedef style_transfer(pathIn='',pathOut='',model='',width=None,jpg_quality=80):'''pathIn: 原始图片的路径pathOut: 风格化图片的保存路径model: 预训练模型的路径width: 设置风格化图片的宽度，默认为None, 即原始图片尺寸jpg_quality: 0-100，设置输出图片的质量，默认80，越大图片质量越好'''# 读入原始图片，调整图片至所需尺寸，然后获取图片的宽度和高度img = cv2.imread(pathIn)(h, w) = img.shape[:2]if width is not None:img = cv2.resize(img, (width, round(width * h / w)), interpolation=cv2.INTER_CUBIC)(h, w) = img.shape[:2]# 从本地加载预训练模型print('加载预训练模型......')net = cv2.dnn.readNetFromTorch(model)# 将图片构建成一个blob：设置图片尺寸，将各通道像素值减去平均值（比如ImageNet所有训练样本各通道统计平均值）# 然后执行一次前馈网络计算，并输出计算所需的时间blob = cv2.dnn.blobFromImage(img, 1.0, (w, h), (103.939, 116.779, 123.680), swapRB=False, crop=False)net.setInput(blob)start = time.time()output = net.forward()end = time.time()print("风格迁移花费：{:.2f}秒".format(end - start))# reshape输出结果, 将减去的平均值加回来，并交换各颜色通道output = output.reshape((3, output.shape[2], output.shape[3]))output[0] += 103.939output[1] += 116.779output[2] += 123.680output = output.transpose(1, 2, 0)# 输出风格化后的图片cv2.imwrite(pathOut, output, [int(cv2.IMWRITE_JPEG_QUALITY), jpg_quality])

CNN模型训练

import __future__
import torch
import torchvision.models as models
import torchvision.transforms as transforms
import time
import os
from PIL import Imagedevice = torch.device("cuda" if torch.cuda.is_available() else "cpu")
'''
环境：
python：3.6.7
tensorflow==2.2.0
torch==1.5.1+cpu
torchvision==0.6.0+cpu
Pillow==8.1.2
'''class GramMatrix(torch.nn.Module):def forward(self, input):b, n, h, w = input.size()features = input.view(b * n, h * w)G = torch.mm(features, features.t())return G.div(b * n * h * w)class StyleLoss(torch.nn.Module):def __init__(self, style_feature, weight):super(StyleLoss, self).__init__()self.style_feature = style_feature.detach()self.weight = weightself.gram = GramMatrix()self.criterion = torch.nn.MSELoss()def forward(self, combination):# output = combinationstyle_feature = self.gram(self.style_feature.clone() * self.weight)combination_features = self.gram(combination.clone() * self.weight)self.loss = self.criterion(combination_features, style_feature)return combinationclass StyleTransfer:def __init__(self, content_image, style_image, style_weight=5, content_weight=0.025):# Weights of the different loss componentsself.vgg19 = models.vgg19()self.vgg19.load_state_dict(torch.load('vgg19-dcbb9e9d.pth'))self.img_ncols = 1280self.img_nrows = 720self.style_weight = style_weightself.content_weight = content_weight# 处理原图和风格图片self.content_tensor, self.content_name = self.process_img(content_image)self.style_tensor, self.style_name = self.process_img(style_image)self.conbination_tensor = self.content_tensor.clone()def process_img(self, img_path):img = Image.open(img_path)img_name = img_path.split('/')[-1][:-4]loader = transforms.Compose([transforms.Resize((self.img_nrows, self.img_ncols)),transforms.ToTensor()])img_tensor = loader(img)img_tensor = img_tensor.unsqueeze(0)return img_tensor.to(device, torch.float), img_namedef deprocess_img(self, x, index):unloader = transforms.ToPILImage()x = x.cpu().clone()img_tensor = x.squeeze(0)img = unloader(img_tensor)result_folder = f'{self.content_name}_and_{self.style_name}'os.path.exists(result_folder) or os.mkdir(result_folder)filename = f'{result_folder}/rersult_{index}.png'img.save(filename)print(f'save {filename} successfully!')print()def get_loss_and_model(self, vgg_model, content_image, style_image):vgg_layers = vgg_model.features.to(device).eval()style_losses = []content_losses = []model = torch.nn.Sequential()style_layer_name_maping = {'0': "style_loss_1",'5': "style_loss_2",'10': "style_loss_3",'19': "style_loss_4",'28': "style_loss_5",}content_layer_name_maping = {'30': "content_loss"}for name, module in vgg_layers._modules.items():model.add_module(name, module)if name in content_layer_name_maping:content_feature = model(content_image).clone()content_loss = ContentLoss(content_feature, self.content_weight)model.add_module(f'{content_layer_name_maping[name]}', content_loss)content_losses.append(content_loss)if name in style_layer_name_maping:style_feature = model(style_image).clone()style_loss = StyleLoss(style_feature, self.style_weight)style_losses.append(style_loss)model.add_module(f'{style_layer_name_maping[name]}', style_loss)return content_losses, style_losses, modeldef get_input_param_optimizer(self, input_img):input_param = torch.nn.Parameter(input_img.data)optimizer = torch.optim.LBFGS([input_param])return input_param, optimizerdef main_train(self, epoch=10):print('Load model preprocessing')combination_param, optimizer = self.get_input_param_optimizer(self.conbination_tensor)content_losses, style_losses, model = self.get_loss_and_model(self.vgg19, self.content_tensor,self.style_tensor)cur, pre = 10, 10for i in range(1, epoch + 1):start = time.time()def closure():combination_param.data.clamp_(0, 1)optimizer.zero_grad()model(combination_param)style_score = 0content_score = 0for cl in content_losses:content_score += cl.lossfor sl in style_losses:style_score += sl.lossloss = content_score + style_scoreloss.backward()return style_score + content_scoreloss = optimizer.step(closure)cur, pre = loss, curend = time.time()print(f'|using:{int(end - start):2d}s |epoch:{i:2d} |loss:{loss.data}')if pre <= cur:print('Early stopping!')breakcombination_param.data.clamp_(0, 1)

本文仅供学习交流使用，如侵立删！

Python CNN风格迁移相关推荐

python图片风格迁移毕设_神经风格迁移是如何运作的概述及Python实现
神经风格迁移是如何运作的概述及Python实现作者:PHPYuan 时间:2019-03-26 03:40:37 深度学习可以捕获一个图像的内容并将其与另一个图像的风格相结合,这种技术称为神经风格迁 ...
python图片风格迁移毕设_Python简单实现图像风格迁移
下载W3Cschool手机App,0基础随时随地学编程导语 T_T之前似乎发过类似的文章,那时候是用Keras实现的,现在用的PyTorch,而且那时候发的内容感觉有些水,于是我决定... 好吧我确实 ...
cnn风格迁移_快速图像风格迁移思想在无线通信中的另类应用：算法拟合
在本文中,并不是介绍最新的一些论文,而是回顾自己在很早(半年前?)读过的几篇文章.[1]Learning to optimize: Training deep neural networks for ...
cnn风格迁移_愚蠢的CNN，换个马甲就认不出猫！但，这病能治 | ICLR Oral
鱼羊栗子发自凹非寺量子位报道 | 公众号 QbitAI "穿件马甲就不认识我了?" 如果把大象的纹理披在猫身上,CNN识别出的就是大象 (详见下文) . 图宾根大学的博 ...
cnn风格迁移_简述风格迁移Neural-Style细节
什么是风格迁移? 风格迁移是使用某些手段(合法的), 把图像从原风格转换到另外一个风格, 同时保证图像内容没有变化, 举个栗子, 下面的这类图片应该是很多人见过了可以看到在把画风变成梵高的星夜后, ...
【人工智能】python图像风格迁移，来欣赏梵高风格的石原里美吧！
图像的风格迁移,心心念念好久了啊! 简单几个步骤,就可以转换图片风格啦. 1. 在github下载模型,模型后缀名是 t7,新建 model 文件夹用来存放模型图像风格迁移模型链接 2. 新建 fe ...
python风格变换图片_【人工智能】python图片风格迁移，来欣赏梵高风格的石原里美吧！...
图像的风格迁移,心心念念好久了啊! 简单几个步骤,就可以转换图片风格啦. 1. 在github下载模型,模型后缀名是 t7,新建 model 文件夹用来存放模型 2. 新建 fengge.py 文件, ...
CNN 风格迁移模型原理简述
我们有了两张图片,分别是content图和style图风格迁移本质上是找到一个新的图片,使得风格上趋近于风格图,内容上趋近于内容图而"趋近"在深度学习中体现在loss函数中,所 ...
cnn风格迁移_深度学习能否对音乐进行风格迁移？
音色迁移.音乐流派迁移.音乐风格迁移都有做. 至少有两个可行的思路:增加condition,进行显式控制.THU九歌模型在诗歌生成中对风格进行了控制,利用infoGAN使用过的"mutual ...

Python CNN风格迁移

Python CNN风格迁移相关推荐

最新文章

热门文章