tutorial_vgg19.py

最新推荐文章于 2021-11-27 12:30:53 发布
最新推荐文章于 2021-11-27 12:30:53 发布
阅读量124 收藏
点赞数
原文链接：http://www.cnblogs.com/nanfangzhe/p/9715572.html
版权 
#最近要跑一个demo，需要用到tutorial_vgg19.py，原作者给的链接没有在github上，CSDN上找到了，但是格式是乱的，没办法只能自己把格式调了一下，结果还是好的，可以运行

# -*- coding: utf-8 -*-
"""
VGG-19 for ImageNet.

Pre-trained model in this example - VGG19 NPZ and
trainable examples of VGG16/19 in TensorFlow can be found here:
https://github.com/machrisaa/tensorflow-vgg

For simplified CNN layer see "Convolutional layer (Simplified)"
in read the docs website.

"""

import os
import time
import numpy as np
import skimage
import skimage.io
import skimage.transform
import tensorflow as tf
import tensorlayer as tl
from tensorlayer.layers import *

tf.logging.set_verbosity(tf.logging.DEBUG)
tl.logging.set_verbosity(tl.logging.DEBUG)

try:
    from tensorlayer.models.imagenet_classes import *
except Exception as e:
    raise Exception(
        "{} / download the file from: https://github.com/tensorlayer/tensorlayer/tree/master/example/data".format(e)
    )

VGG_MEAN = [103.939, 116.779, 123.68]

MODEL_DIR = "models"
MODEL_NAME = "vgg19.npy"
MODEL_PATH = os.path.join(MODEL_DIR, MODEL_NAME)


def load_image(path):

# load image
 img = skimage.io.imread(path)
 img = img / 255.0
 if ((0 <= img).all() and (img <= 1.0).all()) is False:
    raise Exception("image value should be [0, 1]")
# print "Original Image Shape: ", img.shape
# we crop image from center
 short_edge = min(img.shape[:2])
 yy = int((img.shape[0] - short_edge) / 2)
 xx = int((img.shape[1] - short_edge) / 2)
 crop_img = img[yy:yy + short_edge, xx:xx + short_edge]
# resize to 224, 224
 resized_img = skimage.transform.resize(crop_img, (224, 224), anti_aliasing=False)
 return resized_img


def print_prob(prob):
    synset = class_names


# print prob
    pred = np.argsort(prob)[::-1]
# Get top1 label
    top1 = synset[pred[0]]
    print("Top1: ", top1, prob[pred[0]])
# Get top5 label
    top5 = [(synset[pred[i]], prob[pred[i]]) for i in range(5)]
    print("Top5: ", top5)
    return top1


def Vgg19(rgb):
    """
    Build the VGG 19 Model

    Parameters
    -----------
    rgb : rgb image placeholder [batch, height, width, 3] values scaled [0, 1]
    """

    start_time = time.time()
    print("build model started")
    rgb_scaled = rgb * 255.0
# Convert RGB to BGR
    red, green, blue = tf.split(rgb_scaled, 3, 3)

    if red.get_shape().as_list()[1:] != [224, 224, 1]:
        raise Exception("image size unmatch")

    if green.get_shape().as_list()[1:] != [224, 224, 1]:
        raise Exception("image size unmatch")

    if blue.get_shape().as_list()[1:] != [224, 224, 1]:
        raise Exception("image size unmatch")

    bgr = tf.concat([
        blue - VGG_MEAN[0],
        green - VGG_MEAN[1],
        red - VGG_MEAN[2],
    ], axis=3)

    if bgr.get_shape().as_list()[1:] != [224, 224, 3]:
        raise Exception("image size unmatch")
# input layer
    net_in = InputLayer(bgr, name='input')
# conv1
    net = Conv2dLayer(net_in, act=tf.nn.relu, shape=[3, 3, 3, 64], strides=[1, 1, 1, 1], padding='SAME', name='conv1_1')
    net = Conv2dLayer(net, act=tf.nn.relu, shape=[3, 3, 64, 64], strides=[1, 1, 1, 1], padding='SAME', name='conv1_2')
    net = PoolLayer(net, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME', pool=tf.nn.max_pool, name='pool1')
# conv2
    net = Conv2dLayer(net, act=tf.nn.relu, shape=[3, 3, 64, 128], strides=[1, 1, 1, 1], padding='SAME', name='conv2_1')
    net = Conv2dLayer(net, act=tf.nn.relu, shape=[3, 3, 128, 128], strides=[1, 1, 1, 1], padding='SAME', name='conv2_2')
    net = PoolLayer(net, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME', pool=tf.nn.max_pool, name='pool2')
# conv3
    net = Conv2dLayer(net, act=tf.nn.relu, shape=[3, 3, 128, 256], strides=[1, 1, 1, 1], padding='SAME', name='conv3_1')
    net = Conv2dLayer(net, act=tf.nn.relu, shape=[3, 3, 256, 256], strides=[1, 1, 1, 1], padding='SAME', name='conv3_2')
    net = Conv2dLayer(net, act=tf.nn.relu, shape=[3, 3, 256, 256], strides=[1, 1, 1, 1], padding='SAME', name='conv3_3')
    net = Conv2dLayer(net, act=tf.nn.relu, shape=[3, 3, 256, 256], strides=[1, 1, 1, 1], padding='SAME', name='conv3_4')
    net = PoolLayer(net, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME', pool=tf.nn.max_pool, name='pool3')
# conv4
    net = Conv2dLayer(net, act=tf.nn.relu, shape=[3, 3, 256, 512], strides=[1, 1, 1, 1], padding='SAME', name='conv4_1')
    net = Conv2dLayer(net, act=tf.nn.relu, shape=[3, 3, 512, 512], strides=[1, 1, 1, 1], padding='SAME', name='conv4_2')
    net = Conv2dLayer(net, act=tf.nn.relu, shape=[3, 3, 512, 512], strides=[1, 1, 1, 1], padding='SAME', name='conv4_3')
    net = Conv2dLayer(net, act=tf.nn.relu, shape=[3, 3, 512, 512], strides=[1, 1, 1, 1], padding='SAME', name='conv4_4')
    net = PoolLayer(net, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME', pool=tf.nn.max_pool, name='pool4')
# conv5
    net = Conv2dLayer(net, act=tf.nn.relu, shape=[3, 3, 512, 512], strides=[1, 1, 1, 1], padding='SAME', name='conv5_1')
    net = Conv2dLayer(net, act=tf.nn.relu, shape=[3, 3, 512, 512], strides=[1, 1, 1, 1], padding='SAME', name='conv5_2')
    net = Conv2dLayer(net, act=tf.nn.relu, shape=[3, 3, 512, 512], strides=[1, 1, 1, 1], padding='SAME', name='conv5_3')
    net = Conv2dLayer(net, act=tf.nn.relu, shape=[3, 3, 512, 512], strides=[1, 1, 1, 1], padding='SAME', name='conv5_4')
    net = PoolLayer(net, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME', pool=tf.nn.max_pool, name='pool5')
# fc 6~8
    net = FlattenLayer(net, name='flatten')
    net = DenseLayer(net, n_units=4096, act=tf.nn.relu, name='fc6')
    net = DenseLayer(net, n_units=4096, act=tf.nn.relu, name='fc7')
    net = DenseLayer(net, n_units=1000, act=None, name='fc8')
    print("build model finished: %fs" % (time.time() - start_time))
    return net


def Vgg19_simple_api(rgb):
    """
    Build the VGG 19 Model

    Parameters
    -----------
    rgb : rgb image placeholder [batch, height, width, 3] values scaled [0, 1]
    """


    start_time = time.time()
    print("build model started")
    rgb_scaled = rgb * 255.0
# Convert RGB to BGR
    red, green, blue = tf.split(rgb_scaled, 3, 3)

    if red.get_shape().as_list()[1:] != [224, 224, 1]:
        raise Exception("image size unmatch")

    if green.get_shape().as_list()[1:] != [224, 224, 1]:
        raise Exception("image size unmatch")

    if blue.get_shape().as_list()[1:] != [224, 224, 1]:
        raise Exception("image size unmatch")

    bgr = tf.concat([
        blue - VGG_MEAN[0],
        green - VGG_MEAN[1],
        red - VGG_MEAN[2],
    ], axis=3)

    if bgr.get_shape().as_list()[1:] != [224, 224, 3]:
        raise Exception("image size unmatch")

# input layer
    net_in = InputLayer(bgr, name='input')
# conv1
    net = Conv2d(net_in, 64, filter_size=(3, 3), strides=(1, 1), act=tf.nn.relu, padding='SAME', name='conv1_1')
    net = Conv2d(net, n_filter=64, filter_size=(3, 3), strides=(1, 1), act=tf.nn.relu, padding='SAME', name='conv1_2')
    net = MaxPool2d(net, filter_size=(2, 2), strides=(2, 2), padding='SAME', name='pool1')
# conv2
    net = Conv2d(net, n_filter=128, filter_size=(3, 3), strides=(1, 1), act=tf.nn.relu, padding='SAME', name='conv2_1')
    net = Conv2d(net, n_filter=128, filter_size=(3, 3), strides=(1, 1), act=tf.nn.relu, padding='SAME', name='conv2_2')
    net = MaxPool2d(net, filter_size=(2, 2), strides=(2, 2), padding='SAME', name='pool2')
# conv3
    net = Conv2d(net, n_filter=256, filter_size=(3, 3), strides=(1, 1), act=tf.nn.relu, padding='SAME', name='conv3_1')
    net = Conv2d(net, n_filter=256, filter_size=(3, 3), strides=(1, 1), act=tf.nn.relu, padding='SAME', name='conv3_2')
    net = Conv2d(net, n_filter=256, filter_size=(3, 3), strides=(1, 1), act=tf.nn.relu, padding='SAME', name='conv3_3')
    net = Conv2d(net, n_filter=256, filter_size=(3, 3), strides=(1, 1), act=tf.nn.relu, padding='SAME', name='conv3_4')
    net = MaxPool2d(net, filter_size=(2, 2), strides=(2, 2), padding='SAME', name='pool3')
# conv4
    net = Conv2d(net, n_filter=512, filter_size=(3, 3), strides=(1, 1), act=tf.nn.relu, padding='SAME', name='conv4_1')
    net = Conv2d(net, n_filter=512, filter_size=(3, 3), strides=(1, 1), act=tf.nn.relu, padding='SAME', name='conv4_2')
    net = Conv2d(net, n_filter=512, filter_size=(3, 3), strides=(1, 1), act=tf.nn.relu, padding='SAME', name='conv4_3')
    net = Conv2d(net, n_filter=512, filter_size=(3, 3), strides=(1, 1), act=tf.nn.relu, padding='SAME', name='conv4_4')
    net = MaxPool2d(net, filter_size=(2, 2), strides=(2, 2), padding='SAME', name='pool4')
# conv5
    net = Conv2d(net, n_filter=512, filter_size=(3, 3), strides=(1, 1), act=tf.nn.relu, padding='SAME', name='conv5_1')
    net = Conv2d(net, n_filter=512, filter_size=(3, 3), strides=(1, 1), act=tf.nn.relu, padding='SAME', name='conv5_2')
    net = Conv2d(net, n_filter=512, filter_size=(3, 3), strides=(1, 1), act=tf.nn.relu, padding='SAME', name='conv5_3')
    net = Conv2d(net, n_filter=512, filter_size=(3, 3), strides=(1, 1), act=tf.nn.relu, padding='SAME', name='conv5_4')
    net = MaxPool2d(net, filter_size=(2, 2), strides=(2, 2), padding='SAME', name='pool5')
# fc 6~8
    net = FlattenLayer(net, name='flatten')
    net = DenseLayer(net, n_units=4096, act=tf.nn.relu, name='fc6')
    net = DenseLayer(net, n_units=4096, act=tf.nn.relu, name='fc7')
    net = DenseLayer(net, n_units=1000, act=None, name='fc8')
    print("build model finished: %fs" % (time.time() - start_time))
    return net

sess = tf.InteractiveSession()
x = tf.placeholder("float", [None, 224, 224, 3])
# net = Vgg19(x)
net = Vgg19_simple_api(x)
y = net.outputs
probs = tf.nn.softmax(y, name="prob")
tl.layers.initialize_global_variables(sess)

# You need to download the pre-trained model - VGG19 NPY
if not os.path.isfile(MODEL_PATH):
    print("Please download vgg19.npy from : https://github.com/machrisaa/tensorflow-vgg")
exit()

npy_file = np.load(MODEL_PATH, encoding='latin1').item()

params = []
for val in sorted(npy_file.items()):
    W = np.asarray(val[1][0])
b = np.asarray(val[1][1])
print(" Loading %s: %s, %s" % (val[0], W.shape, b.shape))
params.extend([W, b])

print("Restoring model from npy file")
tl.files.assign_params(sess, params, net)

img1 = load_image("data/tiger.jpeg")  # test data in github
img1 = img1.reshape((1, 224, 224, 3))
start_time = time.time()
prob = sess.run(probs, feed_dict={x: img1})
print("End time : %.5ss" % (time.time() - start_time))

print_prob(prob[0])

转载于:https://www.cnblogs.com/nanfangzhe/p/9715572.html

a6999148
关注
  • 0
    点赞
  • 踩
  • 0
    收藏
    觉得还不错? 一键收藏
  • 0
    评论
tensorlayer学习日志2_chapter2_2.6.1~2
weixin_42025210的博客
08-09 603
import numpy as np import tensorlayer as tl x = np.asarray([['a','a'],['b','b'],['c','c'],['d','d'],['e','e'],['f','f']]) y = np.asarray([0,1,2,3,4,5]) # x与y的元素个数要相同，否则会报错 for xx, yy in tl.iterate.m...
python-skimage.io,filters,transform
m0_55983410的博客
03-31 4217
python-skimage.io,filters,transform学习笔记
卷积神经网络vgg19.npy
12-13
VGGNet是牛津大学计算机视觉组（VisualGeometry Group）和GoogleDeepMind公司的研究员一起研发的的深度卷积神经网络。VGGNet探索了卷积神经网络的深度与其性能之间的关系，通过反复堆叠3*3的小型卷积核和2*2的最大池化层，VGGNet成功地构筑了16~19层深的卷积神经网络。VGGNet相比之前state-of-the-art的网络结构，错误率大幅下降，并取得了ILSVRC 2014比赛分类项目的第2名和定位项目的第1名。同时VGGNet的拓展性很强，迁移到其他图片数据上的泛化性非常好。VGGNet的结构非常简洁，整个网络都使用了同样大小的卷积核尺寸（3*3
skimage.io与skimage.data模块详解
热门推荐
大胡子的博客
07-27 1万+
skimage提供了io模块，这个模块是用来操作图片输入输出的。 同时为了方便练习，skimage还提供了data模块，里面嵌套了一些示例图供我们直接使用。 导入io与data模块可用： from skimage import io,data 一、读取并显示图片 io.imread（filename，as_grey=True）：读取图片 参数 filename：图片路径 as_g...
Tutorial8_CST2009148.py
05-25
Tutorial8_CST2009148.py
neural_style_tutorial.py
09-02
关于风格迁移的相关代码，适合初学者认识和了解风格迁移
Fluent_Tutorial_Package_r191.zip
03-30
Fluent_Tutorial_Package_r191：压缩文件包括ANSYS_Fluent_Tutorial_Guide_19.1.pdf以及各模型的压缩文件，次压缩文件包括.msh文件和.c文件等。上传此套资料，供广大仿真爱好者参考学习。
mathjax_tutorial_mdeditor.md
05-20
Cmd Markdown 公式指导手册（转载自：https://www.zybuluo.com/codeep/note/163962）
Column_Store_Tutorial_VLDB09.pdf
03-01
Column_Store_Tutorial_VLDB09.pdf
Tensorboard的注意事项
zqxdsy的博客
05-17 462
1.运行tensorboard命令： tensorboard ----logdir= 路径 2.返回一个链接，复制到浏览器显示拒绝，原因是端口错误，将地址改为“localhost：端口号”，例如localhost：6606. 3.Tensorboard 上显示不同训练模型曲线的方法 tensorboard --logdir=run1:"/home/.../summary",run2:"/home/.../summary" --port=6006 4. ...
简单易懂的PyTorch版VGG19复现代码
hlld__的博客
02-10 7281
VGG19网络结构 VGG的创新点包括使用3x3小核替换传统的5x5或7x7大核卷积，其整个网络除全连接层外，均采用步长为 1 填充为 1 的 3x3 卷积 + ReLU 和步长为 2 填充为 0 的 2x2 最大池化，网络结构非常简洁。VGG网络的输入维度为 3x224x224，在全连接层之前没有使用全局平均值池化压缩特征图的空间维度，而是直接将特征图的后 3 维 Flatten 后输入到全连接层中，这样导致第一个全连接层有较多的参数，且VGG包括 3 个全连接层，在训练时需要使用Dropout等正则化方
.npy文件_Day106:查看npy文件
weixin_39816260的博客
11-27 2214
npy文件.npy文件是numpy专用的二进制文件目的在训练自己神经网络的时候，经常会用到已经训练好的权重来初始化自己的网络。比如，我们总是download一个权重文件，后缀名是npy或者mat，虽然知道里面存的是相应网络层的权重，但一直没打开看过。举例用VGG19做style transfer的时候，会有一个vgg19.npy ， 训练网络的时候加载这个文件可以极大的提升网络速度。就是下图中红色...
【题目】了解skimage库
小C的博客
09-18 2050
【时间】2018.09.18 【题目】了解skimage库 【参考链接】https://www.jianshu.com/p/f2e88197e81d 【侵权删】   一、概述 skimage包的全称是scikit-image SciKit (toolkit for SciPy) ，它对scipy.ndimage进行了扩展，提供了更多的图片处理功能。它是由python语言编写的，由sci...
vgg19.npy下载
weixin_44676933的博客
02-24 1592
最近在写python实现图像风格迁移，用到了vgg19 网络，下载的特别慢，上传一下，希望别人不用这么麻烦。 链接：https://pan.baidu.com/s/1AiZogonom3sgoM6PUe29uA 提取码：w387 ...
python:图像的读入、显示与存储
qq_45916211的博客
11-27 4110
引入本文所用模块 import cv2 as cv from skimage import io import matplotlib.pyplot as plt 读入图像 OpenCV： img_bgr = cv.imread('./img.jpg',1) #BGR格式 img_gray = cv.imread('./img_gray',0) #灰度图 cv.imread(fname,0) cv.imread(fname,1) fname（ 即filename），表示文件名或者文件路径
VGG16/19 预训练模型参数下载地址
jushao1107的博客
12-06 1万+
VGG16/19 预训练模型参数下载地址 vgg16.npy和vgg19.npy下载 https://mega.nz/#!YU1FWJrA!O1ywiCS2IiOlUCtCpI6HTJOMrneN-Qdv3ywQP5poecM https://mega.nz/#!xZ8glS6J!MAnE91ND_WyfZ_8mvkuSa2YcA7q-1ehfSm-Q1fxOvvs 如果网速很慢可以使用百度云下载...
利用卷积神经网络(VGG19)实现火灾分类(附tensorflow代码及训练集)
weixin_34167819的博客
11-23 1333
源码地址 https://github.com/stephen-v/tensorflow_vgg_classify 1. VGG介绍 1.1. VGG模型结构 1.2. VGG19架构 2. 用Tensorflow搭建VGG19网络 3. 训练网络 参考文献 1. VGG介绍 1.1. VGG模型结构 VGG网络是牛津大学Visual Geometry Group团队研发搭...
神经网络下载资源整合
canpian7的博客
03-15 782
个人总结的资源下载地址 持续更新中 我整理的都是原地址，可能要翻墙。需要翻墙的我会单独贴出来 vgg16.npy 翻墙 https://mega.nz/#!YU1FWJrA!O1ywiCS2IiOlUCtCpI6HTJOMrneN-Qdv3ywQP5poecM vgg19.npy 翻墙 https://mega.nz/#!xZ8glS6J!MAnE91ND_WyfZ_8mvkuSa2YcA7q-1ehfSm-Q1fxOvvs ...
tutorial_nn.py，这是什么意思
最新发布
06-01
`tutorial_nn.py`可能是一个Python脚本的文件名，其中`nn`可能表示神经网络（Neural Network）的缩写。根据文件名来猜测，这个脚本可能是一个神经网络教程的示例代码，用于演示如何使用Python和PyTorch构建、训练和评估神经网络模型。在这个教程中，作者可能会介绍神经网络的基本概念、模型结构、激活函数、损失函数、优化器等方面的内容，并提供相应的代码示例和实验结果。总的来说，`tutorial_nn.py`很可能是一个用于学习神经网络的教程脚本。

“相关推荐”对你有帮助么？

  • 非常没帮助
  • 没帮助
  • 一般
  • 有帮助
  • 非常有帮助
提交
评论
添加红包

请填写红包祝福语或标题

个

红包个数最小为10个

元

红包金额最低5元

当前余额3.43元 前往充值 >
需支付：10.00元
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付元
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明：

1.余额是钱包充值的虚拟货币，按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载，可以购买VIP、付费专栏及课程。

余额充值