vgg16模型进行图片预测

最新推荐文章于 2023-08-09 17:08:33 发布
最新推荐文章于 2023-08-09 17:08:33 发布
阅读量3.9k 收藏 1
点赞数
分类专栏： 机器学习

使用vgg16模型进行图片预测 #

前面我们学习了使用cifra10来判断图片的类别，今天我们使用更加强大的已经训练好的模型来预测图片的类别，那就是vgg16,对应的供keras使用的模型人家已经帮我们训练好，我可不想卖肾来买一个gpu。。。 
对应的模型在 ‘vgg16’ 可以下载。估计被墙了，附上链接(http://pan.baidu.com/s/1qX0CJSC) 
附上我的github(https://github.com/HadXu/machine-learning)

导入必要的库

<code class="language-python hljs  has-numbering" style="display: block; padding: 0px; color: inherit; box-sizing: border-box; font-family: "Source Code Pro", monospace;font-size:undefined; white-space: pre; border-radius: 0px; word-wrap: normal; background: transparent;"><span class="hljs-keyword" style="color: rgb(0, 0, 136); box-sizing: border-box;">from</span> keras.models <span class="hljs-keyword" style="color: rgb(0, 0, 136); box-sizing: border-box;">import</span> Sequential
<span class="hljs-keyword" style="color: rgb(0, 0, 136); box-sizing: border-box;">from</span> keras.layers.core <span class="hljs-keyword" style="color: rgb(0, 0, 136); box-sizing: border-box;">import</span> Flatten, Dense, Dropout
<span class="hljs-keyword" style="color: rgb(0, 0, 136); box-sizing: border-box;">from</span> keras.layers.convolutional <span class="hljs-keyword" style="color: rgb(0, 0, 136); box-sizing: border-box;">import</span> Convolution2D, MaxPooling2D, ZeroPadding2D
<span class="hljs-keyword" style="color: rgb(0, 0, 136); box-sizing: border-box;">from</span> keras.optimizers <span class="hljs-keyword" style="color: rgb(0, 0, 136); box-sizing: border-box;">import</span> SGD
<span class="hljs-keyword" style="color: rgb(0, 0, 136); box-sizing: border-box;">import</span> cv2, numpy <span class="hljs-keyword" style="color: rgb(0, 0, 136); box-sizing: border-box;">as</span> np</code><ul class="pre-numbering" style="box-sizing: border-box; position: absolute; width: 50px; top: 0px; left: 0px; margin: 0px; padding: 6px 0px 40px; border-right-width: 1px; border-right-style: solid; border-right-color: rgb(221, 221, 221); list-style: none; text-align: right; background-color: rgb(238, 238, 238);"><li style="box-sizing: border-box; padding: 0px 5px;">1</li><li style="box-sizing: border-box; padding: 0px 5px;">2</li><li style="box-sizing: border-box; padding: 0px 5px;">3</li><li style="box-sizing: border-box; padding: 0px 5px;">4</li><li style="box-sizing: border-box; padding: 0px 5px;">5</li></ul>
Using Theano backend.
D:\Anaconda\lib\site-packages\theano-0.8.0.dev0-py2.7.egg\theano\tensor\signal\downsample.py:5: UserWarning: downsample module has been moved to the pool module.
  warnings.warn("downsample module has been moved to the pool module.")

使用keras建立vgg16模型

<code class="language-python hljs  has-numbering" style="display: block; padding: 0px; color: inherit; box-sizing: border-box; font-family: "Source Code Pro", monospace;font-size:undefined; white-space: pre; border-radius: 0px; word-wrap: normal; background: transparent;"><span class="hljs-function" style="box-sizing: border-box;"><span class="hljs-keyword" style="color: rgb(0, 0, 136); box-sizing: border-box;">def</span> <span class="hljs-title" style="box-sizing: border-box;">VGG_16</span><span class="hljs-params" style="color: rgb(102, 0, 102); box-sizing: border-box;">(weights_path=None)</span>:</span>
    model = Sequential()
    model.add(ZeroPadding2D((<span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">1</span>,<span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">1</span>),input_shape=(<span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">3</span>,<span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">224</span>,<span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">224</span>)))
    model.add(Convolution2D(<span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">64</span>, <span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">3</span>, <span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">3</span>, activation=<span class="hljs-string" style="color: rgb(0, 136, 0); box-sizing: border-box;">'relu'</span>))
    model.add(ZeroPadding2D((<span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">1</span>,<span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">1</span>)))
    model.add(Convolution2D(<span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">64</span>, <span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">3</span>, <span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">3</span>, activation=<span class="hljs-string" style="color: rgb(0, 136, 0); box-sizing: border-box;">'relu'</span>))
    model.add(MaxPooling2D((<span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">2</span>,<span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">2</span>), strides=(<span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">2</span>,<span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">2</span>)))

    model.add(ZeroPadding2D((<span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">1</span>,<span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">1</span>)))
    model.add(Convolution2D(<span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">128</span>, <span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">3</span>, <span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">3</span>, activation=<span class="hljs-string" style="color: rgb(0, 136, 0); box-sizing: border-box;">'relu'</span>))
    model.add(ZeroPadding2D((<span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">1</span>,<span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">1</span>)))
    model.add(Convolution2D(<span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">128</span>, <span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">3</span>, <span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">3</span>, activation=<span class="hljs-string" style="color: rgb(0, 136, 0); box-sizing: border-box;">'relu'</span>))
    model.add(MaxPooling2D((<span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">2</span>,<span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">2</span>), strides=(<span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">2</span>,<span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">2</span>)))

    model.add(ZeroPadding2D((<span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">1</span>,<span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">1</span>)))
    model.add(Convolution2D(<span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">256</span>, <span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">3</span>, <span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">3</span>, activation=<span class="hljs-string" style="color: rgb(0, 136, 0); box-sizing: border-box;">'relu'</span>))
    model.add(ZeroPadding2D((<span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">1</span>,<span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">1</span>)))
    model.add(Convolution2D(<span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">256</span>, <span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">3</span>, <span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">3</span>, activation=<span class="hljs-string" style="color: rgb(0, 136, 0); box-sizing: border-box;">'relu'</span>))
    model.add(ZeroPadding2D((<span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">1</span>,<span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">1</span>)))
    model.add(Convolution2D(<span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">256</span>, <span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">3</span>, <span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">3</span>, activation=<span class="hljs-string" style="color: rgb(0, 136, 0); box-sizing: border-box;">'relu'</span>))
    model.add(MaxPooling2D((<span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">2</span>,<span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">2</span>), strides=(<span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">2</span>,<span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">2</span>)))

    model.add(ZeroPadding2D((<span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">1</span>,<span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">1</span>)))
    model.add(Convolution2D(<span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">512</span>, <span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">3</span>, <span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">3</span>, activation=<span class="hljs-string" style="color: rgb(0, 136, 0); box-sizing: border-box;">'relu'</span>))
    model.add(ZeroPadding2D((<span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">1</span>,<span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">1</span>)))
    model.add(Convolution2D(<span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">512</span>, <span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">3</span>, <span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">3</span>, activation=<span class="hljs-string" style="color: rgb(0, 136, 0); box-sizing: border-box;">'relu'</span>))
    model.add(ZeroPadding2D((<span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">1</span>,<span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">1</span>)))
    model.add(Convolution2D(<span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">512</span>, <span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">3</span>, <span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">3</span>, activation=<span class="hljs-string" style="color: rgb(0, 136, 0); box-sizing: border-box;">'relu'</span>))
    model.add(MaxPooling2D((<span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">2</span>,<span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">2</span>), strides=(<span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">2</span>,<span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">2</span>)))

    model.add(ZeroPadding2D((<span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">1</span>,<span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">1</span>)))
    model.add(Convolution2D(<span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">512</span>, <span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">3</span>, <span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">3</span>, activation=<span class="hljs-string" style="color: rgb(0, 136, 0); box-sizing: border-box;">'relu'</span>))
    model.add(ZeroPadding2D((<span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">1</span>,<span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">1</span>)))
    model.add(Convolution2D(<span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">512</span>, <span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">3</span>, <span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">3</span>, activation=<span class="hljs-string" style="color: rgb(0, 136, 0); box-sizing: border-box;">'relu'</span>))
    model.add(ZeroPadding2D((<span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">1</span>,<span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">1</span>)))
    model.add(Convolution2D(<span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">512</span>, <span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">3</span>, <span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">3</span>, activation=<span class="hljs-string" style="color: rgb(0, 136, 0); box-sizing: border-box;">'relu'</span>))
    model.add(MaxPooling2D((<span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">2</span>,<span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">2</span>), strides=(<span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">2</span>,<span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">2</span>)))

    model.add(Flatten())
    model.add(Dense(<span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">4096</span>, activation=<span class="hljs-string" style="color: rgb(0, 136, 0); box-sizing: border-box;">'relu'</span>))
    model.add(Dropout(<span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">0.5</span>))
    model.add(Dense(<span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">4096</span>, activation=<span class="hljs-string" style="color: rgb(0, 136, 0); box-sizing: border-box;">'relu'</span>))
    model.add(Dropout(<span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">0.5</span>))
    model.add(Dense(<span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">1000</span>, activation=<span class="hljs-string" style="color: rgb(0, 136, 0); box-sizing: border-box;">'softmax'</span>))

    <span class="hljs-keyword" style="color: rgb(0, 0, 136); box-sizing: border-box;">if</span> weights_path:
        model.load_weights(weights_path)

    <span class="hljs-keyword" style="color: rgb(0, 0, 136); box-sizing: border-box;">return</span> model</code><ul class="pre-numbering" style="box-sizing: border-box; position: absolute; width: 50px; top: 0px; left: 0px; margin: 0px; padding: 6px 0px 40px; border-right-width: 1px; border-right-style: solid; border-right-color: rgb(221, 221, 221); list-style: none; text-align: right; background-color: rgb(238, 238, 238);"><li style="box-sizing: border-box; padding: 0px 5px;">1</li><li style="box-sizing: border-box; padding: 0px 5px;">2</li><li style="box-sizing: border-box; padding: 0px 5px;">3</li><li style="box-sizing: border-box; padding: 0px 5px;">4</li><li style="box-sizing: border-box; padding: 0px 5px;">5</li><li style="box-sizing: border-box; padding: 0px 5px;">6</li><li style="box-sizing: border-box; padding: 0px 5px;">7</li><li style="box-sizing: border-box; padding: 0px 5px;">8</li><li style="box-sizing: border-box; padding: 0px 5px;">9</li><li style="box-sizing: border-box; padding: 0px 5px;">10</li><li style="box-sizing: border-box; padding: 0px 5px;">11</li><li style="box-sizing: border-box; padding: 0px 5px;">12</li><li style="box-sizing: border-box; padding: 0px 5px;">13</li><li style="box-sizing: border-box; padding: 0px 5px;">14</li><li style="box-sizing: border-box; padding: 0px 5px;">15</li><li style="box-sizing: border-box; padding: 0px 5px;">16</li><li style="box-sizing: border-box; padding: 0px 5px;">17</li><li style="box-sizing: border-box; padding: 0px 5px;">18</li><li style="box-sizing: border-box; padding: 0px 5px;">19</li><li style="box-sizing: border-box; padding: 0px 5px;">20</li><li style="box-sizing: border-box; padding: 0px 5px;">21</li><li style="box-sizing: border-box; padding: 0px 5px;">22</li><li style="box-sizing: border-box; padding: 0px 5px;">23</li><li style="box-sizing: border-box; padding: 0px 5px;">24</li><li style="box-sizing: border-box; padding: 0px 5px;">25</li><li style="box-sizing: border-box; padding: 0px 5px;">26</li><li style="box-sizing: border-box; padding: 0px 5px;">27</li><li style="box-sizing: border-box; padding: 0px 5px;">28</li><li style="box-sizing: border-box; padding: 0px 5px;">29</li><li style="box-sizing: border-box; padding: 0px 5px;">30</li><li style="box-sizing: border-box; padding: 0px 5px;">31</li><li style="box-sizing: border-box; padding: 0px 5px;">32</li><li style="box-sizing: border-box; padding: 0px 5px;">33</li><li style="box-sizing: border-box; padding: 0px 5px;">34</li><li style="box-sizing: border-box; padding: 0px 5px;">35</li><li style="box-sizing: border-box; padding: 0px 5px;">36</li><li style="box-sizing: border-box; padding: 0px 5px;">37</li><li style="box-sizing: border-box; padding: 0px 5px;">38</li><li style="box-sizing: border-box; padding: 0px 5px;">39</li><li style="box-sizing: border-box; padding: 0px 5px;">40</li><li style="box-sizing: border-box; padding: 0px 5px;">41</li><li style="box-sizing: border-box; padding: 0px 5px;">42</li><li style="box-sizing: border-box; padding: 0px 5px;">43</li><li style="box-sizing: border-box; padding: 0px 5px;">44</li><li style="box-sizing: border-box; padding: 0px 5px;">45</li><li style="box-sizing: border-box; padding: 0px 5px;">46</li><li style="box-sizing: border-box; padding: 0px 5px;">47</li><li style="box-sizing: border-box; padding: 0px 5px;">48</li><li style="box-sizing: border-box; padding: 0px 5px;">49</li></ul>
<code class="language-python hljs  has-numbering" style="display: block; padding: 0px; color: inherit; box-sizing: border-box; font-family: "Source Code Pro", monospace;font-size:undefined; white-space: pre; border-radius: 0px; word-wrap: normal; background: transparent;">model = VGG_16(<span class="hljs-string" style="color: rgb(0, 136, 0); box-sizing: border-box;">'vgg16_weights.h5'</span>)</code><ul class="pre-numbering" style="box-sizing: border-box; position: absolute; width: 50px; top: 0px; left: 0px; margin: 0px; padding: 6px 0px 40px; border-right-width: 1px; border-right-style: solid; border-right-color: rgb(221, 221, 221); list-style: none; text-align: right; background-color: rgb(238, 238, 238);"><li style="box-sizing: border-box; padding: 0px 5px;">1</li></ul>
<code class="language-python hljs  has-numbering" style="display: block; padding: 0px; color: inherit; box-sizing: border-box; font-family: "Source Code Pro", monospace;font-size:undefined; white-space: pre; border-radius: 0px; word-wrap: normal; background: transparent;">sgd = SGD(lr=<span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">0.1</span>, decay=<span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">1e-6</span>, momentum=<span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">0.9</span>, nesterov=<span class="hljs-keyword" style="color: rgb(0, 0, 136); box-sizing: border-box;">True</span>)
model.compile(optimizer=sgd, loss=<span class="hljs-string" style="color: rgb(0, 136, 0); box-sizing: border-box;">'categorical_crossentropy'</span>)</code><ul class="pre-numbering" style="box-sizing: border-box; position: absolute; width: 50px; top: 0px; left: 0px; margin: 0px; padding: 6px 0px 40px; border-right-width: 1px; border-right-style: solid; border-right-color: rgb(221, 221, 221); list-style: none; text-align: right; background-color: rgb(238, 238, 238);"><li style="box-sizing: border-box; padding: 0px 5px;">1</li><li style="box-sizing: border-box; padding: 0px 5px;">2</li></ul>

现在我们开始来预测了

首先写一个方法来加载并处理图片

<code class="language-python hljs  has-numbering" style="display: block; padding: 0px; color: inherit; box-sizing: border-box; font-family: "Source Code Pro", monospace;font-size:undefined; white-space: pre; border-radius: 0px; word-wrap: normal; background: transparent;"><span class="hljs-function" style="box-sizing: border-box;"><span class="hljs-keyword" style="color: rgb(0, 0, 136); box-sizing: border-box;">def</span> <span class="hljs-title" style="box-sizing: border-box;">load_image</span><span class="hljs-params" style="color: rgb(102, 0, 102); box-sizing: border-box;">(imageurl)</span>:</span>
    im = cv2.resize(cv2.imread(imageurl),(<span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">224</span>,<span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">224</span>)).astype(np.float32)
    im[:,:,<span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">0</span>] -= <span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">103.939</span>
    im[:,:,<span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">1</span>] -= <span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">116.779</span>
    im[:,:,<span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">2</span>] -= <span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">123.68</span>
    im = im.transpose((<span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">2</span>,<span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">0</span>,<span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">1</span>))
    im = np.expand_dims(im,axis=<span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">0</span>)
    <span class="hljs-keyword" style="color: rgb(0, 0, 136); box-sizing: border-box;">return</span> im</code><ul class="pre-numbering" style="box-sizing: border-box; position: absolute; width: 50px; top: 0px; left: 0px; margin: 0px; padding: 6px 0px 40px; border-right-width: 1px; border-right-style: solid; border-right-color: rgb(221, 221, 221); list-style: none; text-align: right; background-color: rgb(238, 238, 238);"><li style="box-sizing: border-box; padding: 0px 5px;">1</li><li style="box-sizing: border-box; padding: 0px 5px;">2</li><li style="box-sizing: border-box; padding: 0px 5px;">3</li><li style="box-sizing: border-box; padding: 0px 5px;">4</li><li style="box-sizing: border-box; padding: 0px 5px;">5</li><li style="box-sizing: border-box; padding: 0px 5px;">6</li><li style="box-sizing: border-box; padding: 0px 5px;">7</li><li style="box-sizing: border-box; padding: 0px 5px;">8</li></ul>

读取vgg16的类别文件

<code class="language-python hljs  has-numbering" style="display: block; padding: 0px; color: inherit; box-sizing: border-box; font-family: "Source Code Pro", monospace;font-size:undefined; white-space: pre; border-radius: 0px; word-wrap: normal; background: transparent;">f = open(<span class="hljs-string" style="color: rgb(0, 136, 0); box-sizing: border-box;">'synset_words.txt'</span>,<span class="hljs-string" style="color: rgb(0, 136, 0); box-sizing: border-box;">'r'</span>)
lines = f.readlines()
f.close()</code><ul class="pre-numbering" style="box-sizing: border-box; position: absolute; width: 50px; top: 0px; left: 0px; margin: 0px; padding: 6px 0px 40px; border-right-width: 1px; border-right-style: solid; border-right-color: rgb(221, 221, 221); list-style: none; text-align: right; background-color: rgb(238, 238, 238);"><li style="box-sizing: border-box; padding: 0px 5px;">1</li><li style="box-sizing: border-box; padding: 0px 5px;">2</li><li style="box-sizing: border-box; padding: 0px 5px;">3</li></ul>
<code class="language-python hljs  has-numbering" style="display: block; padding: 0px; color: inherit; box-sizing: border-box; font-family: "Source Code Pro", monospace;font-size:undefined; white-space: pre; border-radius: 0px; word-wrap: normal; background: transparent;"><span class="hljs-function" style="box-sizing: border-box;"><span class="hljs-keyword" style="color: rgb(0, 0, 136); box-sizing: border-box;">def</span> <span class="hljs-title" style="box-sizing: border-box;">predict</span><span class="hljs-params" style="color: rgb(102, 0, 102); box-sizing: border-box;">(url)</span>:</span>
    im = load_image(url)
    pre = np.argmax(model.predict(im))
    <span class="hljs-keyword" style="color: rgb(0, 0, 136); box-sizing: border-box;">print</span> lines[pre]</code><ul class="pre-numbering" style="box-sizing: border-box; position: absolute; width: 50px; top: 0px; left: 0px; margin: 0px; padding: 6px 0px 40px; border-right-width: 1px; border-right-style: solid; border-right-color: rgb(221, 221, 221); list-style: none; text-align: right; background-color: rgb(238, 238, 238);"><li style="box-sizing: border-box; padding: 0px 5px;">1</li><li style="box-sizing: border-box; padding: 0px 5px;">2</li><li style="box-sizing: border-box; padding: 0px 5px;">3</li><li style="box-sizing: border-box; padding: 0px 5px;">4</li></ul>
<code class="language-python hljs  has-numbering" style="display: block; padding: 0px; color: inherit; box-sizing: border-box; font-family: "Source Code Pro", monospace;font-size:undefined; white-space: pre; border-radius: 0px; word-wrap: normal; background: transparent;">%pylab inline</code><ul class="pre-numbering" style="box-sizing: border-box; position: absolute; width: 50px; top: 0px; left: 0px; margin: 0px; padding: 6px 0px 40px; border-right-width: 1px; border-right-style: solid; border-right-color: rgb(221, 221, 221); list-style: none; text-align: right; background-color: rgb(238, 238, 238);"><li style="box-sizing: border-box; padding: 0px 5px;">1</li></ul>
Populating the interactive namespace from numpy and matplotlib

<code class="language-python hljs  has-numbering" style="display: block; padding: 0px; color: inherit; box-sizing: border-box; font-family: "Source Code Pro", monospace;font-size:undefined; white-space: pre; border-radius: 0px; word-wrap: normal; background: transparent;"><span class="hljs-keyword" style="color: rgb(0, 0, 136); box-sizing: border-box;">from</span> IPython.display <span class="hljs-keyword" style="color: rgb(0, 0, 136); box-sizing: border-box;">import</span> Image</code><ul class="pre-numbering" style="box-sizing: border-box; position: absolute; width: 50px; top: 0px; left: 0px; margin: 0px; padding: 6px 0px 40px; border-right-width: 1px; border-right-style: solid; border-right-color: rgb(221, 221, 221); list-style: none; text-align: right; background-color: rgb(238, 238, 238);"><li style="box-sizing: border-box; padding: 0px 5px;">1</li></ul>
<code class="language-python hljs  has-numbering" style="display: block; padding: 0px; color: inherit; box-sizing: border-box; font-family: "Source Code Pro", monospace;font-size:undefined; white-space: pre; border-radius: 0px; word-wrap: normal; background: transparent;">Image(<span class="hljs-string" style="color: rgb(0, 136, 0); box-sizing: border-box;">'cat1.jpg'</span>)</code><ul class="pre-numbering" style="box-sizing: border-box; position: absolute; width: 50px; top: 0px; left: 0px; margin: 0px; padding: 6px 0px 40px; border-right-width: 1px; border-right-style: solid; border-right-color: rgb(221, 221, 221); list-style: none; text-align: right; background-color: rgb(238, 238, 238);"><li style="box-sizing: border-box; padding: 0px 5px;">1</li></ul>

开始预测

<code class="language-python hljs  has-numbering" style="display: block; padding: 0px; color: inherit; box-sizing: border-box; font-family: "Source Code Pro", monospace;font-size:undefined; white-space: pre; border-radius: 0px; word-wrap: normal; background: transparent;">predict(<span class="hljs-string" style="color: rgb(0, 136, 0); box-sizing: border-box;">'cat1.jpg'</span>)</code><ul class="pre-numbering" style="box-sizing: border-box; position: absolute; width: 50px; top: 0px; left: 0px; margin: 0px; padding: 6px 0px 40px; border-right-width: 1px; border-right-style: solid; border-right-color: rgb(221, 221, 221); list-style: none; text-align: right; background-color: rgb(238, 238, 238);"><li style="box-sizing: border-box; padding: 0px 5px;">1</li></ul>
n02123045 tabby, tabby cat

<code class="language-python hljs  has-numbering" style="display: block; padding: 0px; color: inherit; box-sizing: border-box; font-family: "Source Code Pro", monospace;font-size:undefined; white-space: pre; border-radius: 0px; word-wrap: normal; background: transparent;">Image(<span class="hljs-string" style="color: rgb(0, 136, 0); box-sizing: border-box;">'zebra.jpg'</span>)</code><ul class="pre-numbering" style="box-sizing: border-box; position: absolute; width: 50px; top: 0px; left: 0px; margin: 0px; padding: 6px 0px 40px; border-right-width: 1px; border-right-style: solid; border-right-color: rgb(221, 221, 221); list-style: none; text-align: right; background-color: rgb(238, 238, 238);"><li style="box-sizing: border-box; padding: 0px 5px;">1</li></ul>

<code class="language-python hljs  has-numbering" style="display: block; padding: 0px; color: inherit; box-sizing: border-box; font-family: "Source Code Pro", monospace;font-size:undefined; white-space: pre; border-radius: 0px; word-wrap: normal; background: transparent;">predict(<span class="hljs-string" style="color: rgb(0, 136, 0); box-sizing: border-box;">'zebra.jpg'</span>)</code><ul class="pre-numbering" style="box-sizing: border-box; position: absolute; width: 50px; top: 0px; left: 0px; margin: 0px; padding: 6px 0px 40px; border-right-width: 1px; border-right-style: solid; border-right-color: rgb(221, 221, 221); list-style: none; text-align: right; background-color: rgb(238, 238, 238);"><li style="box-sizing: border-box; padding: 0px 5px;">1</li></ul>
n02391049 zebra

<code class="language-python hljs  has-numbering" style="display: block; padding: 0px; color: inherit; box-sizing: border-box; font-family: "Source Code Pro", monospace;font-size:undefined; white-space: pre; border-radius: 0px; word-wrap: normal; background: transparent;">Image(<span class="hljs-string" style="color: rgb(0, 136, 0); box-sizing: border-box;">'airplane.jpg'</span>)</code><ul class="pre-numbering" style="box-sizing: border-box; position: absolute; width: 50px; top: 0px; left: 0px; margin: 0px; padding: 6px 0px 40px; border-right-width: 1px; border-right-style: solid; border-right-color: rgb(221, 221, 221); list-style: none; text-align: right; background-color: rgb(238, 238, 238);"><li style="box-sizing: border-box; padding: 0px 5px;">1</li></ul>

<code class="language-python hljs  has-numbering" style="display: block; padding: 0px; color: inherit; box-sizing: border-box; font-family: "Source Code Pro", monospace;font-size:undefined; white-space: pre; border-radius: 0px; word-wrap: normal; background: transparent;">predict(<span class="hljs-string" style="color: rgb(0, 136, 0); box-sizing: border-box;">'airplane.jpg'</span>)</code><ul class="pre-numbering" style="box-sizing: border-box; position: absolute; width: 50px; top: 0px; left: 0px; margin: 0px; padding: 6px 0px 40px; border-right-width: 1px; border-right-style: solid; border-right-color: rgb(221, 221, 221); list-style: none; text-align: right; background-color: rgb(238, 238, 238);"><li style="box-sizing: border-box; padding: 0px 5px;">1</li></ul>
n02690373 airliner

<code class="language-python hljs  has-numbering" style="display: block; padding: 0px; color: inherit; box-sizing: border-box; font-family: "Source Code Pro", monospace;font-size:undefined; white-space: pre; border-radius: 0px; word-wrap: normal; background: transparent;">Image(<span class="hljs-string" style="color: rgb(0, 136, 0); box-sizing: border-box;">'pig.jpg'</span>)</code><ul class="pre-numbering" style="box-sizing: border-box; position: absolute; width: 50px; top: 0px; left: 0px; margin: 0px; padding: 6px 0px 40px; border-right-width: 1px; border-right-style: solid; border-right-color: rgb(221, 221, 221); list-style: none; text-align: right; background-color: rgb(238, 238, 238);"><li style="box-sizing: border-box; padding: 0px 5px;">1</li></ul>

<code class="language-python hljs  has-numbering" style="display: block; padding: 0px; color: inherit; box-sizing: border-box; font-family: "Source Code Pro", monospace;font-size:undefined; white-space: pre; border-radius: 0px; word-wrap: normal; background: transparent;">predict(<span class="hljs-string" style="color: rgb(0, 136, 0); box-sizing: border-box;">'pig.jpg'</span>)</code><ul class="pre-numbering" style="box-sizing: border-box; position: absolute; width: 50px; top: 0px; left: 0px; margin: 0px; padding: 6px 0px 40px; border-right-width: 1px; border-right-style: solid; border-right-color: rgb(221, 221, 221); list-style: none; text-align: right; background-color: rgb(238, 238, 238);"><li style="box-sizing: border-box; padding: 0px 5px;">1</li></ul>
n02395406 hog, pig, grunter, squealer, Sus scrofa

可见，判断率还是很高的。。。。

总结

通过这次学习，学会了使用keras来搭建模型，使用vgg16这个模型。

07H_JH
关注
专栏目录
使用vgg16模型进行图片预测
hadxu的博客
02-24 6万+
使用vgg16模型进行图片预测
使用VGG16模型测试图片识别，基于CNN卷积神经网络
java_raylu的博客
03-16 2493
首先网上找了7张图 打算对这7张图片进行识别，直接上代码： from tensorflow.keras import applications #decode_predictions 对预测结果进行处理，解码 from tensorflow.keras.applications.vgg16 import decode_predictions #preprocess_input处理输入图片 from tensorflow.keras.applications.vgg16 import preproc
Vgg16 model
03-25
vgg16 模型 用于初始训练，准确率非常高，可以直接将其封装到云平台中！
Keras使用VGG16模型预测自己的图片
^_^
11-19 6356
from keras.applications.vgg16 import VGG16 from keras.preprocessing.image import load_img from keras.preprocessing.image import img_to_array from keras.applications.vgg16 import preprocess_input from ...
VGG16模型参数
m0_64748541的博客
03-18 3095
VGG16模型参数的初步用法
tensorflow卷积层可视化的实现。基于VGG-19.
donkey_1993的博客
04-16 6377
#导入包 import scipy.io import numpy as np import os import scipy.misc import matplotlib.pyplot as plt import tensorflow as tf #import seaborn as sns #用来画热度图 #定义网络结构，本文用的是VGG-19 def _conv_layer(inp...
keras实现VGG16方式(预测一张图片)
09-16
在本文中，我们将深入探讨如何使用Keras库实现VGG16模型来预测一张图片的类别。VGG16是一种深度卷积神经网络（CNN），由牛津大学的Visual Geometry Group（VGG）提出，因其16层的深度而得名。这个模型在ImageNet数据...
VGG16模型
热门推荐
王小波的博客
03-03 2万+
VGG16模型很好的适用于分类和定位任务 其名称来源于作者所在的牛津大学视觉几何组(Visual Geometry Group)的缩写。 1、结构简洁 VGG由5层卷积层、3层全连接层、softmax输出层构成，层与层之间使用max-pooling（最大化池）分开，所有隐层的激活单元都采用ReLU函数。2、小卷积核和多卷积子层 VGG使用多个较小卷积核（3x3）的卷积层代替一个卷积核...
使用VGG模型进行预测
菜鸟要爱学习
09-13 1374
使用VGG模型进行预测 VGG整个模型已经写好了，我们直接用一张图片来进行预测，查看预测的类别是否正确和准确率是否很高。 我们用tf.keras.applications.vgg16中引用VGG16模型、preprocess_input、decode_predictions。VGG16模型中包括整个网络，preprocess_input对四维数组进行预处理，decode_predictions对预测结果进行解码得到标签。 1.导入相关的库 from tensorflow.keras.applicati
tensorflow使用训练好的VGG模型进行测试
欢迎来到关关雎鸠儿的博客
03-06 625
import scipy.io import numpy as np import os import scipy.misc import matplotlib.pyplot as plt import tensorflow as tf def _conv_layer(input, weights, bias): conv = tf.nn.conv2d(input, tf.con...
VGG16网络参数列表
03-09
文档中包含VGG16的参数结构，以及各网络层的参数数目多少
跟我学算法- tensorflow VGG模型进行测试
weixin_34283445的博客
09-01 136
我们使用的VGG模型是别人已经训练好的一个19层的参数所做的一个模型 第一步：定义卷积分部操作函数 mport scipy.io import numpy as np import os import scipy.misc import matplotlib.pyplot as plt import tensorflow as tf # 进行卷积操作 def _conv_...
VGG16模型详解
最新发布
m0_62919535的博客
08-09 4667
VGG16作为深度学习发展历程中的重要里程碑，强调了通过增加网络深度和一致性设计来提取图像特征。它的成功启发了后续更复杂的网络架构和方法，并在图像分类等任务中取得了重要成就。通过研究和实践，我们可以更好地理解VGG16的原理，并将其应用于实际问题中。VGG16是一种深度卷积神经网络，由牛津大学的研究团队于2014年开发。
Pytorch 基于VGG-16的服饰识别（使用Fashion-MNIST数据集）
小嗷犬的博客
11-05 2260
VGG-16 网络是14年牛津大学计算机视觉组和 Google DeepMind 公司研究员一起研发的深度网络模型。该网络一共有16个训练参数的网络，它的兄弟版本如下图所示，清晰的展示了每一级别的参数量，从11层的网络一直到19层的网络。VGG-16 网络取得了 ILSVRC 2014 比赛分类项目的第2名，定位项目的第1名。VGGNet 网络结构简洁，迁移到其他图片数据上的泛化性能非常好。VGGNet 现在依然经常被用来提取图像特征，该网络训练后的模型参数在其官网上开源了，可以用来在图像分类任务上进行在训
VGG16模型训练+测试
王小波的博客
03-21 3569
tf.keras.applications 中有一些预定义好的经典卷积神经网络结构，如 VGG16 、 VGG19 、 ResNet 、 MobileNet、InceptionV3 等。我们可以直接调用这些经典的卷积神经网络结构（甚至载入预训练的参数），而无需手动定义网络结构。 导入需要的包 from keras.models import Model from keras.layers i...
vgg16卷积层的计算量_vgg16模型参数量和使用的的内存计算
weixin_39892447的博客
12-20 2664
关于VGG-16模型的内存和参数的计算过程如下。INPUT: [224x224x3] memory: 224*224*3=150K weights: 0CONV3-64: [224x224x64] memory: 224*224*64=3.2M weights: (3*3*3)*64 = 1,728CONV3-64: [224x224x64] memory: 224*224*64=3.2M wei...
使用VGG16进行CIFAR10分类的猫狗大战实例
qq_36710197的博客
11-19 1778
##原始代码的运行及结果截图 因为代码在colab上执行，所以要确保在运行时使用的是GPU 此处下载适合在colab上使用的训练集 分别加载训练集和测试集，并把图片进行分类，每五张图片一组，作为一个batchsize（这个batchsize可以在后续进行修改，以达到优化算法的目的） 下载训练模型 将网络的结构打印出来 开始第一次的训练，并保存模型 训练的准确率并不是很高，所以后续的优化空间很大 这是测试函数及过程 测试函数的成功率出奇的高，想来可能是跟特定的数据集有关 ##代码的改进 （1）
TensorFlow-VGG16模型复现
码农爱学习的博客
06-08 1208
VGG介绍 VGG全称是指牛津大学的Oxford Visual Geometry Group，该小组在2014年的ImageNet挑战赛中，设计的VGG神经网络模型在定位和分类跟踪比赛中分别取得了第一名和第二名的成绩。 VGG论文 VERY DEEP CONVOLUTIONAL NETWORKS FOR LARGE-SCALE IMAGE RECOGNITION 论文指出其主要贡献在于：利用3*3小卷积核的网络结构对逐渐加深的网络进行全面的评估，结果表明加深网络深度到16至19层可极大超越前人的网络
迁移学习，载入自己数据训练好的模型并测试
子小程
04-03 1788
vgg16的载入自己训练模型测试代码如下，resnet以及inceptionV可以替换掉vgg import numpy as np from keras.applications.imagenet_utils import decode_predictions from keras.preprocessing import image from keras.applications.vgg...
Keras内置模型图像预测实战：VGG16, VGG19, ResNet50等
"本文主要介绍如何使用Keras内置的预训练模型进行图片预测，包括VGG16、VGG19、ResNet50、InceptionV3和InceptionResNetV2等模型的使用方法，并提供了代码示例。" 在深度学习领域，Keras是一个非常流行的高级神经...
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