摘要：这个 notebook 基于论文「Stylized Neural Painting, arXiv:2011.08114.」提供了最基本的「图片生成绘画」变换的可复现例子。
本文分享自华为云社区《基于ModelArts进行图像风格化绘画》，作者： HWCloudAI 。
ModelArts 项目地址：AI Gallery_Notebook详情_开发者_华为云
下载代码和模型
import os
import moxing as mox
mox.file.copy('obs://obs-aigallery-zc/clf/code/stylized-neural-painting.zip','stylized-neural-painting.zip')
os.system('unzip stylized-neural-painting.zip')
cd stylized-neural-painting
import argparse
import torch
torch.cuda.current_device()
import torch.optim as optim
from painter import *
# 检测运行设备
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
# 配置
parser = argparse.ArgumentParser(description='STYLIZED NEURAL PAINTING')
args = parser.parse_args(args=[])
args.img_path = './test_images/sunflowers.jpg' # 输入图片路径
args.renderer = 'oilpaintbrush' # 渲染器（水彩、马克笔、油画笔刷、矩形） [watercolor, markerpen, oilpaintbrush, rectangle]
args.canvas_color = 'black' # 画布底色 [black, white]
args.canvas_size = 512 # 画布渲染尺寸，单位像素
args.max_m_strokes = 500 # 最大笔划数量
args.m_grid = 5 # 将图片分割为 m_grid x m_grid 的尺寸
args.beta_L1 = 1.0 # L1 loss 权重
args.with_ot_loss = False # 设为 True 以通过 optimal transportation loss 提高收敛。但会降低生成速度
args.beta_ot = 0.1 # optimal transportation loss 权重
args.net_G = 'zou-fusion-net' # 渲染器架构
args.renderer_checkpoint_dir = './checkpoints_G_oilpaintbrush' # 预训练模型路径
args.lr = 0.005 # 笔划搜寻的学习率
args.output_dir = './output' # 输出路径Download pretrained neural renderer.
Define a helper funtion to check the drawing status.
def _drawing_step_states(pt):
acc = pt._compute_acc().item()
print('iteration step %d, G_loss: %.5f, step_psnr: %.5f, strokes: %d / %d'
% (pt.step_id, pt.G_loss.item(), acc,
(pt.anchor_id+1)*pt.m_grid*pt.m_grid,
pt.max_m_strokes))
vis2 = utils.patches2img(pt.G_final_pred_canvas, pt.m_grid).clip(min=0, max=1)定义优化循环
def optimize_x(pt):
pt._load_checkpoint()
pt.net_G.eval()
pt.initialize_params()
pt.x_ctt.requires_grad = True
pt.x_color.requires_grad = True
pt.x_alpha.requires_grad = True
utils.set_requires_grad(pt.net_G, False)
pt.optimizer_x = optim.RMSprop([pt.x_ctt, pt.x_color, pt.x_alpha], lr=pt.lr)
print('begin to draw...')
pt.step_id = 0
for pt.anchor_id in range(0, pt.m_strokes_per_block):
pt.stroke_sampler(pt.anchor_id)
iters_per_stroke = 20
if pt.anchor_id == pt.m_strokes_per_block - 1:
iters_per_stroke = 40
for i in range(iters_per_stroke):
pt.optimizer_x.zero_grad()
pt.x_ctt.data = torch.clamp(pt.x_ctt.data, 0.1, 1 - 0.1)
pt.x_color.data = torch.clamp(pt.x_color.data, 0, 1)
pt.x_alpha.data = torch.clamp(pt.x_alpha.data, 0, 1)
if args.canvas_color == 'white':
pt.G_pred_canvas = torch.ones([args.m_grid ** 2, 3, 128, 128]).to(device)
else:
pt.G_pred_canvas = torch.zeros(args.m_grid ** 2, 3, 128, 128).to(device)
pt._forward_pass()
_drawing_step_states(pt)
pt._backward_x()
pt.optimizer_x.step()
pt.x_ctt.data = torch.clamp(pt.x_ctt.data, 0.1, 1 - 0.1)
pt.x_color.data = torch.clamp(pt.x_color.data, 0, 1)
pt.x_alpha.data = torch.clamp(pt.x_alpha.data, 0, 1)
pt.step_id += 1
v = pt.x.detach().cpu().numpy()
pt._save_stroke_params(v)
v_n = pt._normalize_strokes(pt.x)
pt.final_rendered_images = pt._render_on_grids(v_n)
pt._save_rendered_images()处理图片，可能需要一些时间，建议使用 32 GB+ 显存
pt = Painter(args=args)
optimize_x(pt)Check out your results at args.output_dir. Before you download that folder, let’s first have a look at what the generated painting looks like.
plt.subplot(1,2,1)
plt.imshow(pt.img_), plt.title('input')
plt.subplot(1,2,2)
plt.imshow(pt.final_rendered_images[-1]), plt.title('generated')
plt.show()请下载 args.output_dir 目录到本地查看高分辨率的生成结果/
# 将渲染进度用动交互画形式展现
import matplotlib.animation as animation
from IPython.display import HTML
fig = plt.figure(figsize=(4,4))
plt.axis('off')
ims = [[plt.imshow(img, animated=True)] for img in pt.final_rendered_images[::10]]
ani = animation.ArtistAnimation(fig, ims, interval=50)
# HTML(ani.to_jshtml())
HTML(ani.to_html5_video())
Next, let’s play style-transfer. Since we frame our stroke prediction under a parameter searching paradigm, our method naturally fits the neural style transfer framework.
接下来，让我们尝试风格迁移，由于我们是在参数搜索范式下构建的笔画预测，因此我们的方法自然的适用于神经风格迁移框架
# 配置
args.content_img_path = './test_images/sunflowers.jpg' # 输入图片的路径（原始的输入图片）
args.style_img_path = './style_images/fire.jpg' # 风格图片路径
args.vector_file = './output/sunflowers_strokes.npz' # 预生成笔划向量文件的路径
args.transfer_mode = 1 # 风格迁移模式，0：颜色迁移，1：迁移颜色和纹理
args.beta_L1 = 1.0 # L1 loss 权重
args.beta_sty = 0.5 # vgg style loss 权重
args.net_G = 'zou-fusion-net' # 渲染器架构
args.renderer_checkpoint_dir = './checkpoints_G_oilpaintbrush' # 预训练模型路径
args.lr = 0.005 # 笔划搜寻的学习率
args.output_dir = './output' # 输出路径Again, Let’s define a helper funtion to check the style transfer status.
def _style_transfer_step_states(pt):
acc = pt._compute_acc().item()
print('running style transfer... iteration step %d, G_loss: %.5f, step_psnr: %.5f'
% (pt.step_id, pt.G_loss.item(), acc))
vis2 = utils.patches2img(pt.G_final_pred_canvas, pt.m_grid).clip(min=0, max=1)定义优化循环
def optimize_x(pt):
pt._load_checkpoint()
pt.net_G.eval()
if args.transfer_mode == 0: # transfer color only
pt.x_ctt.requires_grad = False
pt.x_color.requires_grad = True
pt.x_alpha.requires_grad = False
else: # transfer both color and texture
pt.x_ctt.requires_grad = True
pt.x_color.requires_grad = True
pt.x_alpha.requires_grad = True
pt.optimizer_x_sty = optim.RMSprop([pt.x_ctt, pt.x_color, pt.x_alpha], lr=pt.lr)
iters_per_stroke = 100
for i in range(iters_per_stroke):
pt.optimizer_x_sty.zero_grad()
pt.x_ctt.data = torch.clamp(pt.x_ctt.data, 0.1, 1 - 0.1)
pt.x_color.data = torch.clamp(pt.x_color.data, 0, 1)
pt.x_alpha.data = torch.clamp(pt.x_alpha.data, 0, 1)
if args.canvas_color == 'white':
pt.G_pred_canvas = torch.ones([pt.m_grid*pt.m_grid, 3, 128, 128]).to(device)
else:
pt.G_pred_canvas = torch.zeros(pt.m_grid*pt.m_grid, 3, 128, 128).to(device)
pt._forward_pass()
_style_transfer_step_states(pt)
pt._backward_x_sty()
pt.optimizer_x_sty.step()
pt.x_ctt.data = torch.clamp(pt.x_ctt.data, 0.1, 1 - 0.1)
pt.x_color.data = torch.clamp(pt.x_color.data, 0, 1)
pt.x_alpha.data = torch.clamp(pt.x_alpha.data, 0, 1)
pt.step_id += 1
print('saving style transfer result...')
v_n = pt._normalize_strokes(pt.x)
pt.final_rendered_images = pt._render_on_grids(v_n)
file_dir = os.path.join(
args.output_dir, args.content_img_path.split('/')[-1][:-4])
plt.imsave(file_dir + '_style_img_' +
args.style_img_path.split('/')[-1][:-4] + '.png', pt.style_img_)
plt.imsave(file_dir + '_style_transfer_' +
args.style_img_path.split('/')[-1][:-4] + '.png', pt.final_rendered_images[-1])运行风格迁移
pt = NeuralStyleTransfer(args=args)
optimize_x(pt)高分辨率生成文件保存在 args.output_dir。
让我们预览一下输出结果：
plt.subplot(1,3,1)
plt.imshow(pt.img_), plt.title('input')
plt.subplot(1,3,2)
plt.imshow(pt.style_img_), plt.title('style')
plt.subplot(1,3,3)
plt.imshow(pt.final_rendered_images[-1]), plt.title('generated')
plt.show()