【Python深度学习】Tensorflow对半环形数据分类、手写数字识别、猫狗识别实战（附源码）

拼搏现实的明天。 2023-09-30 18:26 20阅读 0赞

> **需要源码和数据集请点赞关注收藏后评论区留言私信~~~**

## 一、半环形数据分类 ##

Tensorflow是常见流行的深度学习平台，下面利用它来对半环形数据集进行分类

首先产生半环形数据集

![021e4a86af334c3095d5fb139eb06af4.png][]

接着开始训练模型 总共训练三十次 可以看到损失在逐渐降低，精确度在逐渐提高

![27c67b372ad34a51b6653c22dfe9697d.png][]

结果展示如下， 可以看出大致可以拟合出一条折线将数据集分为两个区域 类似于kmeans算法

![b0c2351e4beb4f47af1a3b74f7d7e8d2.png][]

部分代码如下

# encoding: utf-8
    import numpy as np
    from sklearn.datasets import make_moons
    import tensorflow as tf
    from sklearn.model_selection import train_test_split
    from tensorflow.keras import layers, Sequential, optimizers, losses, metrics
    from tensorflow.keras.layers import Dense
    import matplotlib.pyplot as plt
     
    # 产生一个半环形数据集
    X, y = make_moons(200, noise=0.25, random_state=100)  
    # 划分训练集和测试集
    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.25, random_state=2)
    print(X.shape, y.shape)
    
    def make_plot(X, y, plot_name, XX=None, YY=None, preds=None):
        plt.figure()
        axes = plt.gca()
        x_min = X[:, 0].min() - 1
        x_max = X[:, 0].max() + 1
        y_min = X[:, 1].min() - 1
        y_max = X[:, 1].max() + 1
        axes.set_xlim([x_min, x_max])
        axes.set_ylim([y_min, y_max])
        axes.set(xlabel="$x_l$", ylabel="$x_2$")
    
        if XX is None and YY is None and preds is None:
            yr = y.ravel()
            for step in range(X[:, 0].size):
                if yr[step] == 1:
                    plt.scatter(X[step, 0], X[step, 1], c='b', s=20,  edgecolors='none', marker='x')
                else:
                    plt.scatter(X[step, 0], X[step, 1], c='r', s=30, edgecolors='none', marker='o')
            plt.show()
        else:
            plt.contour(XX, YY, preds, cmap=plt.cm.spring, alpha=0.8)
            plt.scatter(X[:, 0], X[:, 1], c=y, s=20, cmap=plt.cm.Greens, edgecolors='k')
            plt.rcParams['font.sans-serif'] = ['SimHei']  
            plt.rcParams['axes.unicode_minus'] = False
            plt.title(plot_name)
            plt.show()
    make_plot(X, y, None)
    
    #创建容器 
    model = Sequential()  
    #创建第一层
    model.add(Dense(8, input_dim=2, activation='relu'))  
    for _ in range(3):
        model.add(Dense(32, activation='relu'))
    #创建最后一层，激活
    model
    y_min = X[:, 1].min() - 1
    y_max = X[:, 1].max() + 1
    
    XX, YY = np.meshgrid(np.arange(x_min, x_max, 0.01), np.arange(y_min, y_max, 0.01)) 
    Z = model.predict_classes(np.c_[XX.ravel(), YY.ravel()])
    preds = Z.reshape(XX.shape)
    title = "分类结果"
    make_plot(X_train, y_train, title, XX, YY, preds)

## 二、手写数字识别 ##

下面使用深度学习进行一个简单的手写数字识别

输出结果如下 精度大概在百分之九十七

![68b78bc97fcd4573aa27a3a24e916832.png][]

代码如下

import tensorflow as tf
    
    #载入MNIST 数据集。
    mnist = tf.keras.datasets.mnist
    #拆分数据集
    (x_train, y_train), (x_test, y_test) = mnist.load_data()
    #将样本进行预处理，并从整数转换为浮点数
    x_train, x_test = x_train / 255.0, x_test / 255.0
    
    #使用tf.keras.Sequential将模型的各层堆叠，并设置参数
    model = tf.keras.models.Sequential([
      tf.keras.layers.Flatten(input_shape=(28, 28)),
      tf.keras.layers.Dense(128, activation='relu'),
      tf.keras.layers.Dropout(0.2),
      tf.keras.layers.Dense(10, activation='softmax')
    ])
    #设置模型的优化器和损失函数
    model.compile(optimizer='adam',
                  loss='sparse_categorical_crossentropy',
                  metrics=['accuracy'])
    #训练并验证模型
    model.fit(x_train, y_train, epochs=5)
    model.evaluate(x_test,  y_test, verbose=2)

## 三、猫狗识别 ##

下面利用tensorflow平台实现对猫狗品种的识别

原图片如下

![958e72c943ce42748acfc4c6e853ed9e.png][]

![5413891c1c3d4a3d9c45de32df55d499.png][]

![fa4612c4042a4308a18f6f00d8346149.png][]

识别结果如下 第二项是品种 第三项是预测的概率

![2d5ff95e6c2a46fca63b491d2f029c41.png][]

部分代码如下

from tensorflow.keras.applications.resnet50 import ResNet50 
    from tensorflow.keras.preprocessing import image 
    from tensorflow.keras.applications.resnet50 import preprocess_input, decode_predictions 
    import numpy as np 
    from PIL import ImageFont, ImageDraw, Image 
    import cv2
    img_path = 'dog.jpg'     #进行狗的判断
    #img_path = 'cat.jpg'     #进行猫的判断
    #img_path = 'deer.jpg'    #进行鹿的判断
    img = image.load_img(img_path, target_size=(224, 224)) 
    x = image.img_to_array(img) 
    x = np.expand_dims(x, axis=0) 
    x = preprocess_input(x)
    weights_path = 'resnet50_weights_tf_dim_ordering_tf_kernels.h5'
    def get_model(): 
        model = ResNet50(weights=weights_path) 
        # 导入模型以及预训练权重
        print(model.summary()) # 打印模型概况 
        return model
    model = get_model()

**创作不易 觉得有帮助请点赞关注收藏~~~**

[021e4a86af334c3095d5fb139eb06af4.png]: https://img-blog.csdnimg.cn/021e4a86af334c3095d5fb139eb06af4.png
[27c67b372ad34a51b6653c22dfe9697d.png]: https://img-blog.csdnimg.cn/27c67b372ad34a51b6653c22dfe9697d.png
[b0c2351e4beb4f47af1a3b74f7d7e8d2.png]: https://img-blog.csdnimg.cn/b0c2351e4beb4f47af1a3b74f7d7e8d2.png
[68b78bc97fcd4573aa27a3a24e916832.png]: https://img-blog.csdnimg.cn/68b78bc97fcd4573aa27a3a24e916832.png
[958e72c943ce42748acfc4c6e853ed9e.png]: https://img-blog.csdnimg.cn/958e72c943ce42748acfc4c6e853ed9e.png
[5413891c1c3d4a3d9c45de32df55d499.png]: https://img-blog.csdnimg.cn/5413891c1c3d4a3d9c45de32df55d499.png
[fa4612c4042a4308a18f6f00d8346149.png]: https://img-blog.csdnimg.cn/fa4612c4042a4308a18f6f00d8346149.png
[2d5ff95e6c2a46fca63b491d2f029c41.png]: https://img-blog.csdnimg.cn/2d5ff95e6c2a46fca63b491d2f029c41.png