Tensorflow实现图片StyleTransfer

最新推荐文章于 2023-10-09 15:29:29 发布

原创

最新推荐文章于 2023-10-09 15:29:29 发布 · 898 阅读

7 ·

CC 4.0 BY-SA版权

文章标签：

#图片StyleTransfer #Vgg+残差网络实战项目 #tensorflow #深度学习 #项目实战

本文介绍了一种基于深度学习的图像风格迁移技术，通过训练神经网络模型实现不同艺术风格的图像转换。文章提供了详细的代码实现，包括数据集准备、模型训练、测试阶段的图像生成，以及使用的神经网络结构。

1.效果展示：

原图：

风格图：

二. 数据集为8000多张图片，训练一个模型，指定一种训练风格的图片

数据集链接：训练数据，8W多 12G蛮大的
http://msvocds.blob.core.windows.net/coco2014/train2014.zip

训练代码：

from __future__ import print_function
import sys, os, pdb
import numpy as np
import scipy.misc
from src.optimize import optimize
from argparse import ArgumentParser
from src.utils import save_img, get_img, exists, list_files
import evaluate  # 迭代优化

CONTENT_WEIGHT = 7.5e0
STYLE_WEIGHT = 1e2
TV_WEIGHT = 2e2

LEARNING_RATE = 1e-3
NUM_EPOCHS = 2
CHECKPOINT_DIR = 'checkpoints'
CHECKPOINT_ITERATIONS = 2000
VGG_PATH = 'data/imagenet-vgg-verydeep-19.mat'
TRAIN_PATH = 'data/'  # 图片数据路径
BATCH_SIZE = 4
DEVICE = '/gpu:0'   # gpu 计算
FRAC_GPU = 1

# 检测模型中的各个 参数是否已设置好
def check_opts(opts):
    exists(opts.checkpoint_dir, "checkpoint dir not found!")
    exists(opts.style, "style path not found!")
    exists(opts.train_path, "train path not found!")
    if opts.test or opts.test_dir:
        exists(opts.test, "test img not found!")
        exists(opts.test_dir, "test directory not found!")
    exists(opts.vgg_path, "vgg network data not found!")
    assert opts.epochs > 0
    assert opts.batch_size > 0
    assert opts.checkpoint_iterations > 0
    assert os.path.exists(opts.vgg_path)
    assert opts.content_weight >= 0
    assert opts.style_weight >= 0
    assert opts.tv_weight >= 0
    assert opts.learning_rate >= 0

def _get_files(img_dir):
    files = list_files(img_dir)
    return [os.path.join(img_dir,x) for x in files]

    
def main():
    parser = build_parser()
    options = parser.parse_args()
    check_opts(options)

    style_target = get_img(options.style)
    if not options.slow:
        content_targets = _get_files(options.train_path)
    elif options.test:
        content_targets = [options.test]

    kwargs = {
        "slow":options.slow,
        "epochs":options.epochs,
        "print_iterations":options.checkpoint_iterations,
        "batch_size":options.batch_size,
        "save_path":os.path.join(options.checkpoint_dir,'fns.ckpt'),
        "learning_rate":options.learning_rate
    }

    if options.slow:
        if options.epochs < 10:
            kwargs['epochs'] = 1000
        if options.learning_rate < 1:
            kwargs['learning_rate'] = 1e1

    args = [
        content_targets,
        style_target,
        options.content_weight,
        options.style_weight,
        options.tv_weight,
        options.vgg_path
    ]

    for preds, losses, i, epoch in optimize(*args, **kwargs):
        style_loss, content_loss, tv_loss, los