# 测试依赖包,TensorFlow版本
import tensorflow as tf
from tensorflow import keras
import numpy as np
print(tf.__version__)
1.12.0
# 下载数据集
imdb = keras.datasets.imdb
(train_data, train_labels), (test_data, test_labels) = imdb.load_data(num_words=10000)
print("Training entries: {}, labels: {}".format(len(train_data), len(train_labels)))
Training entries: 25000, labels: 25000
print(train_data[0])
[1, 14, 22, 16, 43, 530, 973, 1622, 1385, 65, 458, 4468, 66, 3941, 4, 173, 36, 256, 5, 25, 100, 43, 838, 112, 50, 670, 2, 9, 35, 480, 284, 5, 150, 4, 172, 112, 167, 2, 336, 385, 39, 4, 172, 4536, 1111, 17, 546, 38, 13, 447, 4, 192, 50, 16, 6, 147, 2025, 19, 14, 22, 4, 1920, 4613, 469, 4, 22, 71, 87, 12, 16, 43, 530, 38, 76, 15, 13, 1247, 4, 22, 17, 515, 17, 12, 16, 626, 18, 2, 5, 62, 386, 12, 8, 316, 8, 106, 5, 4, 2223, 5244, 16, 480, 66, 3785, 33, 4, 130, 12, 16, 38, 619, 5, 25, 124, 51, 36, 135, 48, 25, 1415, 33, 6, 22, 12, 215, 28, 77, 52, 5, 14, 407, 16, 82, 2, 8, 4, 107, 117, 5952, 15, 256, 4, 2, 7, 3766, 5, 723, 36, 71, 43, 530, 476, 26, 400, 317, 46, 7, 4, 2, 1029, 13, 104, 88, 4, 381, 15, 297, 98, 32, 2071, 56, 26, 141, 6, 194, 7486, 18, 4, 226, 22, 21, 134, 476, 26, 480, 5, 144, 30, 5535, 18, 51, 36, 28, 224, 92, 25, 104, 4, 226, 65, 16, 38, 1334, 88, 12, 16, 283, 5, 16, 4472, 113, 103, 32, 15, 16, 5345, 19, 178, 32]
len(train_data[0]), len(train_data[1])
(218, 189)
# A dictionary mapping words to an integer index
word_index = imdb.get_word_index()
# The first indices are reserved
word_index = {
k:(v+3) for k,v in word_index.items()}
word_index["<PAD>"] = 0
word_index["<START>"] = 1
word_index["<UNK>"] = 2 # unknown
word_index["<UNUSED>"] = 3
reverse_word_index = dict([(value, key) for (key, value) in word_index.items()])
def decode_review(text):
return ' '.join([reverse_word_index.get(i, '?') for i in text])
decode_review(train_data[0])
"<START> this film was just brilliant casting location scenery story direction everyone's really suited the part they played and you could just imagine being there robert <UNK> is an amazing actor and now the same being director <UNK> father came from the same scottish island as myself so i loved the fact there was a real connection with this film the witty remarks throughout the film were great it was just brilliant so much that i bought the film as soon as it was released for <UNK> and would recommend it to everyone to watch and the fly fishing was amazing really cried at the end it was so sad and you know what they say if you cry at a film it must have been good and this definitely was also <UNK> to the two little boy's that played the <UNK> of norman and paul they were just brilliant children are often left out of the <UNK> list i think because the stars that play them all grown up are such a big profile for the whole film but these children are amazing and should be praised for what they have done don't you think the whole story was so lovely because it was true and was someone's life after all that was shared with us all"
train_data = keras.preprocessing.sequence.pad_sequences(train_data,
value=word_index["<PAD>"],
padding='post',
maxlen=256)
test_data = keras.preprocessing.sequence.pad_sequences(test_data,
value=word_index["<PAD>"],
padding='post',
maxlen=256)
len(train_data[0]), len(train_data[1])
(256, 256)
print(train_data[0])
[ 1 14 22 16 43 530 973 1622 1385 65 458 4468 66 3941 4
173 36 256 5 25 100 43 838 112 50 670 2 9 35 480
284 5 150 4 172 112 167 2 336 385 39 4 172 4536 1111
17 546 38 13 447 4 192 50 16 6 147 2025 19 14 22
4 1920 4613 469 4 22 71 87 12 16 43 530 38 76 15
13 1247 4 22 17 515 17 12 16 626 18 2 5 62 386
12 8 316 8 106 5 4 2223 5244 16 480 66 3785 33 4
130 12 16 38 619 5 25 124 51 36 135 48 25 1415 33
6 22 12 215 28 77 52 5 14 407 16 82 2 8 4
107 117 5952 15 256 4 2 7 3766 5 723 36 71 43 530
476 26 400 317 46 7 4 2 1029 13 104 88 4 381 15
297 98 32 2071 56 26 141 6 194 7486 18 4 226 22 21
134 476 26 480 5 144 30 5535 18 51 36 28 224 92 25
104 4 226 65 16 38 1334 88 12 16 283 5 16 4472 113
103 32 15 16 5345 19 178 32 0 0 0 0 0 0 0
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
0]
# input shape is the vocabulary count used for the movie reviews (10,000 words)
vocab_size = 10000
model = keras.Sequential()
model.add(keras.layers.Embedding(vocab_size, 16))
model.add(keras.layers.GlobalAveragePooling1D())
model.add(keras.layers.Dense(16, activation=tf.nn.relu))
model.add(keras.layers.Dense(1, activation=tf.nn.sigmoid))
model.summary()
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
embedding (Embedding) (None, None, 16) 160000
_________________________________________________________________
global_average_pooling1d (Gl (None, 16) 0
_________________________________________________________________
dense (Dense) (None, 16) 272
_________________________________________________________________
dense_1 (Dense) (None, 1) 17
=================================================================
Total params: 160,289
Trainable params: 160,289
Non-trainable params: 0
_________________________________________________________________
使用 Keras Sequential 顺序模型,它由多个网络层线性堆叠,上面的模型,结构如下:
1、第一层是 Embedding 层。该层会在整数编码的词汇表中查找每个字词-索引的嵌入向量。模型在接受训练时会学习这些向量。这些向量会向输出数组添加一个维度。生成的维度为:(batch, sequence, embedding)。
2、接下来,一个 GlobalAveragePooling1D 层通过对序列维度求平均值,针对每个样本返回一个长度固定的输出向量。这样,模型便能够以尽可能简单的方式处理各种长度的输入。
3、该长度固定的输出向量会传入一个全连接 (Dense) 层(包含 16 个隐藏单元)。
4、最后一层与单个输出节点密集连接。应用 sigmoid 激活函数后,结果是介于 0 到 1 之间的浮点值,表示概率或置信水平。
model.compile(optimizer=tf.train.AdamOptimizer(),
loss='binary_crossentropy',
metrics=['accuracy'])
x_val = train_data[:10000]
partial_x_train = train_data[10000:]
y_val = train_labels[:10000]
partial_y_train = train_labels[10000:]
history = model.fit(partial_x_train,
partial_y_train,
epochs=40,
batch_size=512,
validation_data=(x_val, y_val),
verbose=1)
Train on 15000 samples, validate on 10000 samples
Epoch 1/40
15000/15000 [==============================] - 9s 622us/step - loss: 0.6918 - acc: 0.6397 - val_loss: 0.6898 - val_acc: 0.7141
Epoch 2/40
15000/15000 [==============================] - 2s 140us/step - loss: 0.6854 - acc: 0.6933 - val_loss: 0.6802 - val_acc: 0.7552
Epoch 3/40
15000/15000 [==============================] - 2s 152us/step - loss: 0.6703 - acc: 0.7735 - val_loss: 0.6611 - val_acc: 0.7557
Epoch 4/40
15000/15000 [==============================] - 2s 129us/step - loss: 0.6436 - acc: 0.7826 - val_loss: 0.6312 - val_acc: 0.7570
Epoch 5/40
15000/15000 [==============================] - 1s 94us/step - loss: 0.6048 - acc: 0.8029 - val_loss: 0.5909 - val_acc: 0.7942
Epoch 6/40
15000/15000 [==============================] - 1s 97us/step - loss: 0.5574 - acc: 0.8209 - val_loss: 0.5458 - val_acc: 0.8107
Epoch 7/40
15000/15000 [==============================] - 1s 92us/step - loss: 0.5065 - acc: 0.8401 - val_loss: 0.5007 - val_acc: 0.8279
Epoch 8/40
15000/15000 [==============================] - 2s 130us/step - loss: 0.4583 - acc: 0.8541 - val_loss: 0.4591 - val_acc: 0.8370
Epoch 9/40
15000/15000 [==============================] - 2s 114us/step - loss: 0.4141 - acc: 0.8675 - val_loss: 0.4234 - val_acc: 0.8490
Epoch 10/40
15000/15000 [==============================] - 2s 104us/step - loss: 0.3768 - acc: 0.8791 - val_loss: 0.3948 - val_acc: 0.8560
Epoch 11/40
15000/15000 [==============================] - 2s 100us/step - loss: 0.3454 - acc: 0.8875 - val_loss: 0.3730 - val_acc: 0.8608
Epoch 12/40
15000/15000 [==============================] - 1s 94us/step - loss: 0.3198 - acc: 0.8955 - val_loss: 0.3536 - val_acc: 0.8671
Epoch 13/40
15000/15000 [==============================] - 1s 89us/step - loss: 0.2979 - acc: 0.9001 - val_loss: 0.3394 - val_acc: 0.8709
Epoch 14/40
15000/15000 [==============================] - 2s 118us/step - loss: 0.2791 - acc: 0.9055 - val_loss: 0.3280 - val_acc: 0.8732
Epoch 15/40
15000/15000 [==============================] - 1s 95us/step - loss: 0.2625 - acc: 0.9105 - val_loss: 0.3181 - val_acc: 0.8780
Epoch 16/40
15000/15000 [==============================] - 1s 81us/step - loss: 0.2481 - acc: 0.9155 - val_loss: 0.3104 - val_acc: 0.8795
Epoch 17/40
15000/15000 [==============================] - 1s 88us/step - loss: 0.2354 - acc: 0.9192 - val_loss: 0.3059 - val_acc: 0.8775
Epoch 18/40
15000/15000 [==============================] - 1s 87us/step - loss: 0.2230 - acc: 0.9235 - val_loss: 0.2996 - val_acc: 0.8810
Epoch 19/40
15000/15000 [==============================] - 2s 120us/step - loss: 0.2126 - acc: 0.9272 - val_loss: 0.2955 - val_acc: 0.8823
Epoch 20/40
15000/15000 [==============================] - 1s 87us/step - loss: 0.2021 - acc: 0.9303 - val_loss: 0.2918 - val_acc: 0.8840
Epoch 21/40
15000/15000 [==============================] - 1s 89us/step - loss: 0.1927 - acc: 0.9350 - val_loss: 0.2891 - val_acc: 0.8852
Epoch 22/40
15000/15000 [==============================] - 1s 89us/step - loss: 0.1841 - acc: 0.9386 - val_loss: 0.2878 - val_acc: 0.8839
Epoch 23/40
15000/15000 [==============================] - 1s 87us/step - loss: 0.1761 - acc: 0.9420 - val_loss: 0.2867 - val_acc: 0.8857
Epoch 24/40
15000/15000 [==============================] - 1s 90us/step - loss: 0.1685 - acc: 0.9465 - val_loss: 0.2853 - val_acc: 0.8846
Epoch 25/40
15000/15000 [==============================] - 2s 115us/step - loss: 0.1613 - acc: 0.9487 - val_loss: 0.2846 - val_acc: 0.8855
Epoch 26/40
15000/15000 [==============================] - 2s 106us/step - loss: 0.1547 - acc: 0.9514 - val_loss: 0.2848 - val_acc: 0.8863
Epoch 27/40
15000/15000 [==============================] - 1s 81us/step - loss: 0.1480 - acc: 0.9543 - val_loss: 0.2856 - val_acc: 0.8863
Epoch 28/40
15000/15000 [==============================] - 1s 86us/step - loss: 0.1421 - acc: 0.9567 - val_loss: 0.2855 - val_acc: 0.8860
Epoch 29/40
15000/15000 [==============================] - 1s 84us/step - loss: 0.1361 - acc: 0.9596 - val_loss: 0.2868 - val_acc: 0.8872
Epoch 30/40
15000/15000 [==============================] - 1s 97us/step - loss: 0.1309 - acc: 0.9609 - val_loss: 0.2891 - val_acc: 0.8860
Epoch 31/40
15000/15000 [==============================] - 2s 111us/step - loss: 0.1258 - acc: 0.9631 - val_loss: 0.2920 - val_acc: 0.8843
Epoch 32/40
15000/15000 [==============================] - 1s 88us/step - loss: 0.1208 - acc: 0.9655 - val_loss: 0.2917 - val_acc: 0.8853
Epoch 33/40
15000/15000 [==============================] - 1s 84us/step - loss: 0.1160 - acc: 0.9684 - val_loss: 0.2937 - val_acc: 0.8860
Epoch 34/40
15000/15000 [==============================] - 1s 90us/step - loss: 0.1113 - acc: 0.9699 - val_loss: 0.2965 - val_acc: 0.8843
Epoch 35/40
15000/15000 [==============================] - 1s 87us/step - loss: 0.1069 - acc: 0.9711 - val_loss: 0.2994 - val_acc: 0.8842
Epoch 36/40
15000/15000 [==============================] - 1s 81us/step - loss: 0.1028 - acc: 0.9725 - val_loss: 0.3022 - val_acc: 0.8842
Epoch 37/40
15000/15000 [==============================] - 1s 87us/step - loss: 0.0994 - acc: 0.9735 - val_loss: 0.3044 - val_acc: 0.8845
Epoch 38/40
15000/15000 [==============================] - 1s 87us/step - loss: 0.0948 - acc: 0.9753 - val_loss: 0.3076 - val_acc: 0.8835
Epoch 39/40
15000/15000 [==============================] - 1s 83us/step - loss: 0.0911 - acc: 0.9766 - val_loss: 0.3112 - val_acc: 0.8839
Epoch 40/40
15000/15000 [==============================] - 1s 87us/step - loss: 0.0878 - acc: 0.9775 - val_loss: 0.3158 - val_acc: 0.8826
results = model.evaluate(test_data, test_labels)
print(results)
25000/25000 [==============================] - 4s 144us/step
[0.3395507445144653, 0.86964]
history_dict = history.history
history_dict.keys()
dict_keys(['val_loss', 'val_acc', 'loss', 'acc'])
import matplotlib.pyplot as plt
acc = history.history['acc']
val_acc = history.history['val_acc']
loss = history.history['loss']
val_loss = history.history['val_loss']
epochs = range(1, len(acc) + 1)
# "bo" is for "blue dot"
plt.plot(epochs, loss, 'bo', label='Training loss')
# b is for "solid blue line"
plt.plot(epochs, val_loss, 'b', label='Validation loss')
plt.title('Training and validation loss')
plt.xlabel('Epochs')
plt.ylabel('Loss')
plt.legend()
plt.show()
plt.clf() # clear figure
acc_values = history_dict['acc']
val_acc_values = history_dict['val_acc']
plt.plot(epochs, acc, 'bo', label='Training acc')
plt.plot(epochs, val_acc, 'b', label='Validation acc')
plt.title('Training and validation accuracy')
plt.xlabel('Epochs')
plt.ylabel('Accuracy')
plt.legend()
plt.show()
ROC曲线和PR(Precision - Recall)曲线皆为类别不平衡问题中常用的评估方法,二者既有相同也有不同点。
ROC曲线常用于二分类问题中的模型比较,主要表现为一种真正例率 (TPR) 和假正例率 (FPR) 的权衡。具体方法是在不同的分类阈值 (threshold) 设定下分别以TPR和FPR为纵、横轴作图。由ROC曲线的两个指标,TPR=TPP=TPTP+FNTPR=TPP=TPTP+FN,FPR=FPN=FPFP+TNFPR=FPN=FPFP+TN可以看出,当一个样本被分类器判为正例,若其本身是正例,则TPR增加;若其本身是负例,则FPR增加,因此ROC曲线可以看作是随着阈值的不断移动,所有样本中正例与负例之间的“对抗”。曲线越靠近左上角,意味着越多的正例优先于负例,模型的整体表现也就越好。
AUC 即ROC曲线围成的面积,可以理解为:从所有正例中随机选取一个样本A,再从所有负例中随机选取一个样本B,分类器将A判为正例的概率比将B判为正例的概率大的可能性。可以看到位于随机线上方的点(如图中的A点)被认为好于随机猜测。在这样的点上TPR总大于FPR,意为正例被判为正例的概率大于负例被判为正例的概率。
PR曲线展示的是Precision vs Recall的曲线,PR曲线与ROC曲线的相同点是都采用了TPR (Recall),都可以用AUC来衡量分类器的效果。不同点是ROC曲线使用了FPR,而PR曲线使用了Precision,因此PR曲线的两个指标都聚焦于正例。类别不平衡问题中由于主要关心正例,所以在此情况下PR曲线被广泛认为优于ROC曲线。
参考链接 : https://www.imooc.com/article/48072
https://tensorflow.google.cn/tutorials/keras/basic_text_classification
https://www.cnblogs.com/Zhi-Z/p/8728168.html
文章浏览阅读2w次,点赞7次,收藏51次。四个步骤1.创建C++ Win32项目动态库dll 2.在Win32项目动态库中添加 外部依赖项 lib头文件和lib库3.导出C接口4.c#调用c++动态库开始你的表演...①创建一个空白的解决方案,在解决方案中添加 Visual C++ , Win32 项目空白解决方案的创建:添加Visual C++ , Win32 项目这......_c#调用lib
文章浏览阅读4.6k次。苹方字体是苹果系统上的黑体,挺好看的。注重颜值的网站都会使用,例如知乎:font-family: -apple-system, BlinkMacSystemFont, Helvetica Neue, PingFang SC, Microsoft YaHei, Source Han Sans SC, Noto Sans CJK SC, W..._ubuntu pingfang
文章浏览阅读159次。表单表单概述表单标签表单域按钮控件demo表单标签表单标签基本语法结构<form action="处理数据程序的url地址“ method=”get|post“ name="表单名称”></form><!--action,当提交表单时,向何处发送表单中的数据,地址可以是相对地址也可以是绝对地址--><!--method将表单中的数据传送给服务器处理,get方式直接显示在url地址中,数据可以被缓存,且长度有限制;而post方式数据隐藏传输,_html表单的处理程序有那些
文章浏览阅读1.2k次。使用说明:开启Google的登陆二步验证(即Google Authenticator服务)后用户登陆时需要输入额外由手机客户端生成的一次性密码。实现Google Authenticator功能需要服务器端和客户端的支持。服务器端负责密钥的生成、验证一次性密码是否正确。客户端记录密钥后生成一次性密码。下载谷歌验证类库文件放到项目合适位置(我这边放在项目Vender下面)https://github.com/PHPGangsta/GoogleAuthenticatorPHP代码示例://引入谷_php otp 验证器
文章浏览阅读4.3k次,点赞5次,收藏11次。matplotlib.plot画图横坐标混乱及间隔处理_matplotlib更改横轴间距
文章浏览阅读2.2k次。①Storage driver 处理各镜像层及容器层的处理细节,实现了多层数据的堆叠,为用户 提供了多层数据合并后的统一视图②所有 Storage driver 都使用可堆叠图像层和写时复制(CoW)策略③docker info 命令可查看当系统上的 storage driver主要用于测试目的,不建议用于生成环境。_docker 保存容器
文章浏览阅读834次,点赞27次,收藏13次。网络拓扑结构是指计算机网络中各组件(如计算机、服务器、打印机、路由器、交换机等设备)及其连接线路在物理布局或逻辑构型上的排列形式。这种布局不仅描述了设备间的实际物理连接方式,也决定了数据在网络中流动的路径和方式。不同的网络拓扑结构影响着网络的性能、可靠性、可扩展性及管理维护的难易程度。_网络拓扑csdn
文章浏览阅读1.8k次,点赞5次,收藏8次。IOS系统Date的坑要创建一个指定时间的new Date对象时,通常的做法是:new Date("2020-09-21 11:11:00")这行代码在 PC 端和安卓端都是正常的,而在 iOS 端则会提示 Invalid Date 无效日期。在IOS年月日中间的横岗许换成斜杠,也就是new Date("2020/09/21 11:11:00")通常为了兼容IOS的这个坑,需要做一些额外的特殊处理,笔者在开发的时候经常会忘了兼容IOS系统。所以就想试着重写Date函数,一劳永逸,避免每次ne_date.prototype 将所有 ios
文章浏览阅读5.3k次。方法一:用PLSQL Developer工具。 1 在PLSQL Developer的sql window里输入select * from test for update; 2 按F8执行 3 打开锁, 再按一下加号. 鼠标点到第一列的列头,使全列成选中状态,然后粘贴,最后commit提交即可。(前提..._excel导入pl/sql
文章浏览阅读83次。Git常用命令速查手册1、初始化仓库git init2、将文件添加到仓库git add 文件名 # 将工作区的某个文件添加到暂存区 git add -u # 添加所有被tracked文件中被修改或删除的文件信息到暂存区,不处理untracked的文件git add -A # 添加所有被tracked文件中被修改或删除的文件信息到暂存区,包括untracked的文件...
文章浏览阅读202次。分享119个ASP.NET源码总有一个是你想要的_千博二手车源码v2023 build 1120
文章浏览阅读1.8k次。版权声明:转载请注明出处 http://blog.csdn.net/irean_lau。目录(?)[+]1、缺省构造函数。2、缺省拷贝构造函数。3、 缺省析构函数。4、缺省赋值运算符。5、缺省取址运算符。6、 缺省取址运算符 const。[cpp] view plain copy_空类默认产生哪些类成员函数