前言

接着我上一篇开源机器学习的使用：如何将照片变成卡通图，animegan2-pytorch机器学习项目使用 | 机器学习_阿良的博客-CSDN博客

我还是继续把项目稍微魔改一下，依然变为一个python文件就可以执行单一图片的处理。变为可以直接拿去使用的工具。

项目github地址：github地址

项目结构

samples目录里面有一些样例图片，可以测试用。weights目录放了原项目的4个模型。python环境需要安装一些依赖，主要是pytorch。pytorch的环境安装可以参考我的另一篇文章：机器学习基础环境部署 | 机器学习系列_阿良的博客-CSDN博客

核心代码

不废话，上核心代码了。

#!/usr/bin/env python
# -*- coding: utf-8 -*-
# @Time    : 2021/12/4 22:34
# @Author  : 剑客阿良_ALiang
# @Site    : 
# @File    : image_cartoon_tool.pyfrom PIL import Image
import torch
from torchvision.transforms.functional import to_tensor, to_pil_image
from torch import nn
import os
import torch.nn.functional as F
import uuid# -------------------------- hy add 01 --------------------------
class ConvNormLReLU(nn.Sequential):def __init__(self, in_ch, out_ch, kernel_size=3, stride=1, padding=1, pad_mode="reflect", groups=1, bias=False):pad_layer = {"zero": nn.ZeroPad2d,"same": nn.ReplicationPad2d,"reflect": nn.ReflectionPad2d,}if pad_mode not in pad_layer:raise NotImplementedErrorsuper(ConvNormLReLU, self).__init__(pad_layer[pad_mode](padding),nn.Conv2d(in_ch, out_ch, kernel_size=kernel_size, stride=stride, padding=0, groups=groups, bias=bias),nn.GroupNorm(num_groups=1, num_channels=out_ch, affine=True),nn.LeakyReLU(0.2, inplace=True))class InvertedResBlock(nn.Module):def __init__(self, in_ch, out_ch, expansion_ratio=2):super(InvertedResBlock, self).__init__()self.use_res_connect = in_ch == out_chbottleneck = int(round(in_ch * expansion_ratio))layers = []if expansion_ratio != 1:layers.append(ConvNormLReLU(in_ch, bottleneck, kernel_size=1, padding=0))# dwlayers.append(ConvNormLReLU(bottleneck, bottleneck, groups=bottleneck, bias=True))# pwlayers.append(nn.Conv2d(bottleneck, out_ch, kernel_size=1, padding=0, bias=False))layers.append(nn.GroupNorm(num_groups=1, num_channels=out_ch, affine=True))self.layers = nn.Sequential(*layers)def forward(self, input):out = self.layers(input)if self.use_res_connect:out = input + outreturn outclass Generator(nn.Module):def __init__(self, ):super().__init__()self.block_a = nn.Sequential(ConvNormLReLU(3, 32, kernel_size=7, padding=3),ConvNormLReLU(32, 64, stride=2, padding=(0, 1, 0, 1)),ConvNormLReLU(64, 64))self.block_b = nn.Sequential(ConvNormLReLU(64, 128, stride=2, padding=(0, 1, 0, 1)),ConvNormLReLU(128, 128))self.block_c = nn.Sequential(ConvNormLReLU(128, 128),InvertedResBlock(128, 256, 2),InvertedResBlock(256, 256, 2),InvertedResBlock(256, 256, 2),InvertedResBlock(256, 256, 2),ConvNormLReLU(256, 128),)self.block_d = nn.Sequential(ConvNormLReLU(128, 128),ConvNormLReLU(128, 128))self.block_e = nn.Sequential(ConvNormLReLU(128, 64),ConvNormLReLU(64, 64),ConvNormLReLU(64, 32, kernel_size=7, padding=3))self.out_layer = nn.Sequential(nn.Conv2d(32, 3, kernel_size=1, stride=1, padding=0, bias=False),nn.Tanh())def forward(self, input, align_corners=True):out = self.block_a(input)half_size = out.size()[-2:]out = self.block_b(out)out = self.block_c(out)if align_corners:out = F.interpolate(out, half_size, mode="bilinear", align_corners=True)else:out = F.interpolate(out, scale_factor=2, mode="bilinear", align_corners=False)out = self.block_d(out)if align_corners:out = F.interpolate(out, input.size()[-2:], mode="bilinear", align_corners=True)else:out = F.interpolate(out, scale_factor=2, mode="bilinear", align_corners=False)out = self.block_e(out)out = self.out_layer(out)return out# -------------------------- hy add 02 --------------------------def load_image(image_path, x32=False):img = Image.open(image_path).convert("RGB")if x32:def to_32s(x):return 256 if x < 256 else x - x % 32w, h = img.sizeimg = img.resize((to_32s(w), to_32s(h)))return imgdef handle(image_path: str, output_dir: str, type: int, device='cpu'):_ext = os.path.basename(image_path).strip().split('.')[-1]if type == 1:_checkpoint = './weights/paprika.pt'elif type == 2:_checkpoint = './weights/face_paint_512_v2.pt'else:raise Exception('type not support')os.makedirs(output_dir, exist_ok=True)net = Generator()net.load_state_dict(torch.load(_checkpoint, map_location="cpu"))net.to(device).eval()image = load_image(image_path)with torch.no_grad():image = to_tensor(image).unsqueeze(0) * 2 - 1out = net(image.to(device), False).cpu()out = out.squeeze(0).clip(-1, 1) * 0.5 + 0.5out = to_pil_image(out)result = os.path.join(output_dir, '{}.{}'.format(uuid.uuid1().hex, _ext))out.save(result)return resultif __name__ == '__main__':print(handle('samples/images/fengjing.jpg', 'samples/images_result/', 1))print(handle('samples/images/renxiang.jpg', 'samples/images_result/', 2))

代码说明

1、handle方法可以将一张图片变为卡通化图片，入参为：图片路径、输出目录、类型（1为景色类型图片、2为人物人像图片）、设备类型（默认cpu，可以选择cuda）

2、按照我上一篇文章的测试，适合风景的模型和适合人像的模型不太一样，所以做了区分。

3、输出结果图片名字为了不重复，使用uuid。

验证一下

先发一下准备的图片