风格迁移 系列创作如下
- ???? 声明: 作为全网 AI 领域 干货最多的博主之一,❤️ 不负光阴不负卿 ❤️
- StyleMapGAN、有趣的风格迁移——评测【一】
- StyleMapGAN之celeba_hq 风格迁移 - 图像编辑、实验测评【二】
styleGAN环境搭建 | 动漫模型效果测试流程简记如下:
环境搭建:
- 服务器:ubuntu1~18.04 Quadro RTX 5000 16G (做测试11G的卡可以胜任)
- CUDA版本 V10.0.130
conda create -n tf15 python=3.6.6
conda activate tf15
pip install tensorflow-gpu==1.15 (1.15 测试时会有一些 WARNING,不影响测试)
或者
pip install tensorflow-gpu==1.13
pip install pillow
pip install requests
动漫模型效果测试开启:
所使用代码: GitHub styleGAN 官方实现
styleGAN论文: A Style-Based Generator Architecture for Generative Adversarial Networks
项目目录结构如下:

模型下载(百度网盘):
已训练好的动漫头像模型(动漫头像为主,512x512)
链接:https://pan.baidu.com/s/1_N2y1F4BpwsufNK6xOqaig
提取码:2022
新建 pretrained_example-dongman.py 内容如下:
# Copyright (c) 2019, NVIDIA CORPORATION. All rights reserved.
#
# This work is licensed under the Creative Commons Attribution-NonCommercial
# 4.0 International License. To view a copy of this license, visit
# http://creativecommons.org/licenses/by-nc/4.0/ or send a letter to
# Creative Commons, PO Box 1866, Mountain View, CA 94042, USA.
"""Minimal script for generating an image using pre-trained StyleGAN generator."""
import os
import pickle
import numpy as np
import PIL.Image
import dnnlib
import dnnlib.tflib as tflib
import config
import glob
import random
import os
os.environ["CUDA_VISIBLE_DEVICES"] = "3"
PREFIX = 'Anime'
#PREFIX = 'Animation'
TIMES_LOOP = 100
def main():
# Initialize TensorFlow.
tflib.init_tf()
# Load pre-trained network.
Model = 'cache/2019-03-08-stylegan-animefaces-network-02051-021980.pkl'
model_file = glob.glob(Model)
if len(model_file) == 1:
model_file = open(model_file[0], "rb")
else:
raise Exception('Failed to find the model')
_G, _D, Gs = pickle.load(model_file)
# _G = Instantaneous snapshot of the generator. Mainly useful for resuming a previous training run.
# _D = Instantaneous snapshot of the discriminator. Mainly useful for resuming a previous training run.
# Gs = Long-term average of the generator. Yields higher-quality results than the instantaneous snapshot.
# Print network details.
Gs.print_layers()
for i in range(TIMES_LOOP):
# Pick latent vector.
SEED = random.randint(0, 18000)
rnd = np.random.RandomState(SEED)
latents = rnd.randn(1, Gs.input_shape[1])
# Generate image.
fmt = dict(func=tflib.convert_images_to_uint8, nchw_to_nhwc=True)
images = Gs.run(latents, None, truncation_psi=0.7, randomize_noise=True, output_transform=fmt)
# Generate and Save image.
os.makedirs(config.result_dir, exist_ok=True)
save_name = PREFIX + '_' + str(random.getrandbits(64)) + '.png'
save_path = os.path.join(config.result_dir, save_name)
PIL.Image.fromarray(images[0], 'RGB').save(save_path)
if __name__ == "__main__":
main()
测试运行命令如下:
python pretrained_example-dongman.py
注意事项:
一定要设置使用的卡,不然它默认会使用所有卡,把其他卡的程序干掉了(难受):
import os
os.environ["CUDA_VISIBLE_DEVICES"] = "1"
单卡 GPU占用
8271MiB
生成的动漫女生头像如下:
???????? 墨理学AI
- ???? 作为全网 AI 领域 干货最多的博主之一,❤️ 不负光阴不负卿 ❤️
- ❤️ 如果文章对你有帮助、点赞、评论鼓励博主的每一分认真创作
- ???? 目标检测、超分重建、图像修复、数据集整理 四大专栏持续更新、敬请关注