reference:

GAN 讲解

https://blog.csdn.net/u010900574/article/details/53427544

命令行解析

https://blog.csdn.net/qq_24193303/article/details/80810892

命令行解析的坑

https://blog.csdn.net/qq_25964837/article/details/79077504

注意其内部参数

from __future__ import print_function
from keras.preprocessing.image import load_img, save_img, img_to_array
import numpy as np
from scipy.optimize import fmin_l_bfgs_b
import time
import argparse from keras.applications import vgg19
from keras import backend as K parser = argparse.ArgumentParser(description='Neural style transfer with Keras.')
parser.add_argument('base_image_path', metavar='base', type=str,
help='Path to the image to transform.')
parser.add_argument('style_reference_image_path', metavar='ref', type=str,
help='Path to the style reference image.')
parser.add_argument('result_prefix', metavar='res_prefix', type=str,
help='Prefix for the saved results.')
parser.add_argument('--iter', type=int, default=10, required=False,
help='Number of iterations to run.')
parser.add_argument('--content_weight', type=float, default=0.025, required=False,
help='Content weight.')
parser.add_argument('--style_weight', type=float, default=1.0, required=False,
help='Style weight.')
parser.add_argument('--tv_weight', type=float, default=1.0, required=False,
help='Total Variation weight.')
(base) C:\Users\lenovo>activate tf

(tf) C:\Users\lenovo>d
'd' 不是内部或外部命令,也不是可运行的程序
或批处理文件。 (tf) C:\Users\lenovo>d: (tf) D:\>D:\adevelop\keras\GAN\keras-master\examples
'D:\adevelop\keras\GAN\keras-master\examples' 不是内部或外部命令,也不是可运行的程序
或批处理文件。 (tf) D:\>cd D:\adevelop\keras\GAN\keras-master\examples (tf) D:\adevelop\keras\GAN\keras-master\examples>python neural_style_transfer.py "D:\\adevelop\\keras\\img\\tanm.jpg" "D:\\adevelop\\keras\\img\\vonga.jpg" "D:\\adevelop\\keras\\img\\tiananmen_fangao"
Using TensorFlow backend.
Downloading data from https://github.com/fchollet/deep-learning-models/releases/download/v0.1/vgg19_weights_tf_dim_ordering_tf_kernels_notop.h5
forrtl: error (): program aborting due to control-C event
Image PC Routine Line Source
libifcoremd.dll 00007FFBBCFB94C4 Unknown Unknown Unknown
KERNELBASE.dll 00007FFC07A656FD Unknown Unknown Unknown
KERNEL32.DLL 00007FFC089C3034 Unknown Unknown Unknown
ntdll.dll 00007FFC0AF93691 Unknown Unknown Unknown (tf) D:\adevelop\keras\GAN\keras-master\examples>python neural_style_transfer.py "D:\\adevelop\\keras\\img\\tanm.jpg" "D:\\adevelop\\keras\\img\\vonga.jpg" "D:\\adevelop\\keras\\img\\tiananmen_fangao"
Using TensorFlow backend.
Downloading data from https://github.com/fchollet/deep-learning-models/releases/download/v0.1/vgg19_weights_tf_dim_ordering_tf_kernels_notop.h5
/ [==============================] - 27s 0us/step
-- ::22.912925: I tensorflow/core/platform/cpu_feature_guard.cc:] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX AVX2
-- ::23.111711: I tensorflow/core/common_runtime/gpu/gpu_device.cc:] Found device with properties:
name: GeForce GTX 6GB major: minor: memoryClockRate(GHz): 1.7845
pciBusID: ::00.0
totalMemory: .00GiB freeMemory: .97GiB
-- ::23.115455: I tensorflow/core/common_runtime/gpu/gpu_device.cc:] Adding visible gpu devices:
-- ::23.474086: I tensorflow/core/common_runtime/gpu/gpu_device.cc:] Device interconnect StreamExecutor with strength edge matrix:
-- ::23.476305: I tensorflow/core/common_runtime/gpu/gpu_device.cc:]
-- ::23.477352: I tensorflow/core/common_runtime/gpu/gpu_device.cc:] : N
-- ::23.479132: I tensorflow/core/common_runtime/gpu/gpu_device.cc:] Created TensorFlow device (/job:localhost/replica:/task:/device:GPU: with MB memory) -> physical GPU (device: , name: GeForce GTX 6GB, pci bus id: ::00.0, compute capability: 6.1)
Model loaded.
WARNING:tensorflow:Variable += will be deprecated. Use variable.assign_add if you want assignment to the variable value or 'x = x + y' if you want a new python Tensor object.
Start of iteration
Current loss value: 4708729000.0
Image saved as D:\\adevelop\\keras\\img\\tiananmen_fangao_at_iteration_0.png
Iteration completed in 12s
Start of iteration
Current loss value: 2911683000.0
Image saved as D:\\adevelop\\keras\\img\\tiananmen_fangao_at_iteration_1.png
Iteration completed in 9s
Start of iteration
Current loss value: 2555891200.0
Image saved as D:\\adevelop\\keras\\img\\tiananmen_fangao_at_iteration_2.png
Iteration completed in 9s
Start of iteration
Current loss value: 2370041300.0
Image saved as D:\\adevelop\\keras\\img\\tiananmen_fangao_at_iteration_3.png
Iteration completed in 9s
Start of iteration
Current loss value: 2268962800.0
Image saved as D:\\adevelop\\keras\\img\\tiananmen_fangao_at_iteration_4.png
Iteration completed in 9s
Start of iteration
Current loss value: 2198608600.0
Image saved as D:\\adevelop\\keras\\img\\tiananmen_fangao_at_iteration_5.png
Iteration completed in 9s
Start of iteration
Current loss value: 2155104300.0
Image saved as D:\\adevelop\\keras\\img\\tiananmen_fangao_at_iteration_6.png
Iteration completed in 9s
Start of iteration
Current loss value: 2122974200.0
Image saved as D:\\adevelop\\keras\\img\\tiananmen_fangao_at_iteration_7.png
Iteration completed in 9s
Start of iteration
Current loss value: 2096054800.0
Image saved as D:\\adevelop\\keras\\img\\tiananmen_fangao_at_iteration_8.png
Iteration completed in 9s
Start of iteration
Current loss value: 2074734200.0
Image saved as D:\\adevelop\\keras\\img\\tiananmen_fangao_at_iteration_9.png
Iteration completed in 9s (tf) D:\adevelop\keras\GAN\keras-master\examples>

keras04 GAN simple的更多相关文章

  1. (转) Read-through: Wasserstein GAN

    Sorta Insightful Reviews Projects Archive Research About  In a world where everyone has opinions, on ...

  2. [转]GAN论文集

    really-awesome-gan A list of papers and other resources on General Adversarial (Neural) Networks. Th ...

  3. GAN实战笔记——第六章渐进式增长生成对抗网络(PGGAN)

    渐进式增长生成对抗网络(PGGAN) 使用 TensorFlow和 TensorFlow Hub( TFHUB)构建渐进式增长生成对抗网络( Progressive GAN, PGGAN或 PROGA ...

  4. PHP设计模式(一)简单工厂模式 (Simple Factory For PHP)

    最近天气变化无常,身为程序猿的寡人!~终究难耐天气的挑战,病倒了,果然,程序猿还需多保养自己的身体,有句话这么说:一生只有两件事能报复你:不够努力的辜负和过度消耗身体的后患.话不多说,开始吧. 一.什 ...

  5. Design Patterns Simplified - Part 3 (Simple Factory)【设计模式简述--第三部分(简单工厂)】

    原文链接:http://www.c-sharpcorner.com/UploadFile/19b1bd/design-patterns-simplified-part3-factory/ Design ...

  6. WATERHAMMER: A COMPLEX PHENOMENON WITH A SIMPLE SOLUTION

    开启阅读模式 WATERHAMMER A COMPLEX PHENOMENON WITH A SIMPLE SOLUTION Waterhammer is an impact load that is ...

  7. BZOJ 3489: A simple rmq problem

    3489: A simple rmq problem Time Limit: 40 Sec  Memory Limit: 600 MBSubmit: 1594  Solved: 520[Submit] ...

  8. Le lié à la légèreté semblait être et donc plus simple

    Il est toutefois vraiment à partir www.runmasterfr.com/free-40-flyknit-2015-hommes-c-1_58_59.html de ...

  9. ZOJ 3686 A Simple Tree Problem

    A Simple Tree Problem Time Limit: 3 Seconds      Memory Limit: 65536 KB Given a rooted tree, each no ...

随机推荐

  1. Hangfire源码解析-如何实现可扩展IOC的?

    一.官方描述 These projects simplify the integration between Hangfire and your favorite IoC Container. The ...

  2. 1. 容器化部署一套云服务 第一讲 Jenkins(Docker + Jenkins + Yii2 + 云服务器))

    容器化部署一套云服务系列 1. 容器化部署一套云服务之Jenkins 一.购买服务器 服务器

  3. AntZipUtils【基于Ant的Zip压缩解压缩工具类】

    版权声明:本文为HaiyuKing原创文章,转载请注明出处! 前言 Android 压缩解压zip文件一般分为两种方式: 基于JDK的Zip压缩工具类 该版本存在问题:压缩时如果目录或文件名含有中文, ...

  4. .NET Core 的缓存篇之MemoryCache

    前言 对于缓存我们都已经很熟悉了,缓存分为很多种,浏览器缓存.试图缓存.服务器缓存.数据库缓存等等一些,那今天我们先介绍一下视图缓存和MemoryCache内存缓存的概念和用法: 视图缓存 在老的版本 ...

  5. Python:fake-useragent 伪装请求头

    写爬虫的时候,在进行 request 请求的时候,多数情况下需要添加请求头,否则就不能正常请求. 添加请求头最常用的做法是修改 User-Agent 来伪装浏览器. 以前在写请求头的时候,都是通过 c ...

  6. 装箱问题的CPLEX求解

    装箱问题(Bin Packing Problem) 装箱问题即搬家公司问题.一个搬家公司有无限多的箱子,每个箱子的承重上限为W,当搬家公司进入一个房间时,所有物品都必须被装入箱子,每个物品的重量为wi ...

  7. 二分查找BinarySearch(Java)

    二分查找(折半查找)BinarySearch 二分查找  一组排好顺序的数,查找其中的一个数(value)的位置,按照数组(int[] a)存放这组数据,数组的索引所指的位置就是需要查找的数,用三个变 ...

  8. Android为TV端助力:RecyclerView更新数据时焦点丢失

    1.adapter的setHasStableIds设置成true 2.重写adapter的getItemId方法 @Override public long getItemId(int positio ...

  9. Android Fragment碎片

    什么是碎片? 碎片(Fragment)是一种可以嵌入在活动当中的UI片段,它能让程序更加合理和充分地利用大屏幕的空间,因而在平板上应用的非常广泛.可以把Fragment当成Activity一个界面的一 ...

  10. 【Spring Cloud笔记】 断路器-hystrix

    在微服务架构中,一个微服务的超时失败可能导致瀑布式连锁反映,Spring Cloud Netflix 的断路器Hystrix通过自主反馈,防止了这种情况发生.下面介绍简单的断路器使用方法. [step ...