> For the complete documentation index, see [llms.txt](https://bing-dong.gitbook.io/tensorflow/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://bing-dong.gitbook.io/tensorflow/tf.keras--clssification.md). # tf.keras--classification ```python import matplotlib.pyplot as plt %matplotlib inline import numpy as np import pandas as pd import sklearn import os import sys import time import tensorflow as tf from tensorflow import keras print(tf.__version__) ``` ``` 2.0.0 ``` ```python # 学习时可用第三方数据集进行联系，这里使用keras.datasets.fashion_mnist fashion_mnist = keras.datasets.fashion_mnist (x_train_all,y_train_all),(x_test,y_test) = fashion_mnist.load_data() # 将训练集拆分为训练集和验证集 共60000张图片，前5000张为验证集，后55000张为训练集 x_valid,x_train = x_train_all[:5000],x_train_all[5000:] y_valid,y_train = y_train_all[:5000],y_train_all[5000:] print(x_valid.shape,y_valid.shape) print(x_train.shape,y_train.shape) print(x_test.shape,y_test.shape) ``` ``` (5000, 28, 28) (5000,) (55000, 28, 28) (55000,) (10000, 28, 28) (10000,) ``` ```python # 显示一张图片，查看数据集 def show_single_image(img_arr): plt.imshow(img_arr,cmap="binary") plt.show() show_single_image(x_train[0]) ``` ![](/files/-M35emlipH01vjOGr_A_) ```python # 显示多张图片 def show_imgs(n_rows,n_cols,x_data,y_data,class_name): assert len(x_data) == len(y_data) assert n_rows * n_cols < len(x_data) # 用figure定义一张大图，其中可显示子图 # figsize以英寸为单位 1英寸为 2.54cm plt.figure(figsize = (n_cols * 1.4, n_rows * 1.6)) for row in range(n_rows): for col in range(n_cols): index = row * n_cols + col # 共分为n_rows行，n_rows列个子图，从左上到右下的编号，起始为1 plt.subplot(n_rows, n_cols, index+1) plt.imshow(x_data[index],cmap="binary",interpolation="nearest") # 不显示坐标轴 plt.axis('off') plt.title(class_name[y_data[index]]) plt.show() class_name = ['T-shirt', 'Trouser', 'Pullover', 'Dress', 'Coat', 'Sandal', 'Shirt', 'Sneaker', 'Bag', 'Ankle boot'] show_imgs(3, 5, x_train, y_train, class_name) ``` ![](/files/-M35ed47sAcfmZ59JDac) ``` # 数据标准化 # x = (x - u)/std u:均值 std:标准差 from sklearn.preprocessing import StandardScaler scaler = StandardScaler() # 进行转换： 只能对二位矩阵进行处理，所以要将三维矩阵先转为二维，之后再转换回去 # 又因为原数据为int型，因要做除法，所以先转为float型 x_train_scaled = scaler.fit_transform(x_train.astype(np.float32).reshape(-1,1)).reshape(-1,28,28) # scaler.fit_transform与scaler.transform的区别为前者会记录均值与标准差的值 # 当再用scaler.transform的时候就不用计算均值与标准差了 x_valid_scaled = scaler.transform(x_valid.astype(np.float32).reshape(1,-1)).reshape(-1,28,28) x_test_scaled = scaler.transform(x_test.astype(np.float32).reshape(1,-1)).reshape(-1,28,28) print(np.max(x_train_scaled), np.min(x_train_scaled)) ``` ```python #构建分类训练模型 # tf.keras.models.Sequential() # 定义一个顺序模型 model = keras.models.Sequential() ''' # 将输入矩阵[28,28]经过第一层后展平为[28*28,1] model.add(keras.layers.Flatten(input_shape=[28,28])) # 全连接层Dense,输出为300个节点 # relu: y = max(0, x) model.add(keras.layers.Dense(300,activation='relu')) model.add(keras.layers.Dense(100,activation='relu')) # 最后输出10个分类,softmax会将向量变为概率 model.add(keras.layers.Dense(10,activation='softmax')) ''' # 另一种构建模型的方式，传入一个列表，列表中为各层 model = keras.models.Sequential([ # 第一层要明确一下输入数据的shape，即input_shape=x_train.shape[1:] keras.layers.Flatten(input_shape=[28, 28]), keras.layers.Dense(300,activation='relu'), keras.layers.Dense(100,activation='relu'), keras.layers.Dense(10,activation='softmax') ]) # 损失函数loss:用sparse是因为每个y_train是一个值，而不是一个向量，需要将其转换为[10,1]的向量 # sparse以后就相当于对其进行了one-hot编码 # 若y_train本来就是向量的话，损失函数用categorical_crossentropy model.compile(loss='sparse_categorical_crossentropy', # 目标函数的优化算法，类似还有梯度下降、sgd等等 optimizer = 'adam', # 评价指标metrics 其和损失函数类似，只不过其结果并不会作用于训练过程，只是输出作为参考。其中accuracy为模型的精确度 metrics = ["accuracy"]) ``` ```python # 查看模型层次 model.layers ``` ``` [, , , ] ``` ```python # 查看模型概况 model.summary() # 之下的第二层参数23500是由784*300+300得来的 ``` ``` Model: "sequential_1" _________________________________________________________________ Layer (type) Output Shape Param # ================================================================= flatten (Flatten) (None, 784) 0 _________________________________________________________________ dense (Dense) (None, 300) 235500 _________________________________________________________________ dense_1 (Dense) (None, 100) 30100 _________________________________________________________________ dense_2 (Dense) (None, 10) 1010 ================================================================= Total params: 266,610 Trainable params: 266,610 Non-trainable params: 0 _________________________________________________________________ ``` ```python # 开始训练 返回值为训练过程中的历史数据, 可用于画图分析训练效果 history = model.fit(x_train_scaled, y_train, epochs=10, validation_data=(x_valid_scaled, y_valid)) ``` ``` Train on 55000 samples, validate on 5000 samples Epoch 1/10 55000/55000 [==============================] - 9s 155us/sample - loss: 2.4121 - accuracy: 0.7447 - val_loss: 0.6983 - val_accuracy: 0.7502 Epoch 2/10 55000/55000 [==============================] - 9s 159us/sample - loss: 0.5410 - accuracy: 0.8124 - val_loss: 0.5479 - val_accuracy: 0.8132 Epoch 3/10 55000/55000 [==============================] - 7s 127us/sample - loss: 0.4812 - accuracy: 0.8295 - val_loss: 0.4271 - val_accuracy: 0.8476 Epoch 4/10 55000/55000 [==============================] - 7s 131us/sample - loss: 0.4524 - accuracy: 0.8384 - val_loss: 0.4915 - val_accuracy: 0.8334 Epoch 5/10 55000/55000 [==============================] - 7s 124us/sample - loss: 0.4283 - accuracy: 0.8468 - val_loss: 0.4761 - val_accuracy: 0.8360 Epoch 6/10 55000/55000 [==============================] - 8s 141us/sample - loss: 0.4101 - accuracy: 0.8525 - val_loss: 0.4200 - val_accuracy: 0.8602 Epoch 7/10 55000/55000 [==============================] - 8s 137us/sample - loss: 0.3947 - accuracy: 0.8587 - val_loss: 0.3972 - val_accuracy: 0.8604 Epoch 8/10 55000/55000 [==============================] - 8s 149us/sample - loss: 0.3800 - accuracy: 0.8656 - val_loss: 0.4187 - val_accuracy: 0.8624 Epoch 9/10 55000/55000 [==============================] - 8s 149us/sample - loss: 0.3672 - accuracy: 0.8682 - val_loss: 0.4299 - val_accuracy: 0.8560 Epoch 10/10 55000/55000 [==============================] - 7s 125us/sample - loss: 0.3581 - accuracy: 0.8730 - val_loss: 0.4038 - val_accuracy: 0.8678 ``` ```python # history存储的是模型在训练过程中的每一次epoch后指标的数值 history为字典类型 history.history ``` ``` {'loss': [2.4120644999330696, 0.5410326600681652, 0.481207834982872, 0.45235550054203383, 0.428294502436031, 0.410146419041807, 0.3946501224777915, 0.3800405863350088, 0.3672192143873735, 0.3580564272761345], 'accuracy': [0.7447091, 0.81241816, 0.82952726, 0.8384, 0.8467818, 0.85252726, 0.8587091, 0.8656, 0.8681818, 0.8730364], 'val_loss': [0.6983262790679932, 0.5478786983251571, 0.42707746143341063, 0.4914981854915619, 0.47605090074539186, 0.41999548461437225, 0.39724087767601013, 0.4186679340481758, 0.4299297041296959, 0.4037889191329479], 'val_accuracy': [0.7502, 0.8132, 0.8476, 0.8334, 0.836, 0.8602, 0.8604, 0.8624, 0.856, 0.8678]} ``` ```python def plot_learning_curves(history): # DataFrame是一种二维表的类型，用来表示字典进行画图很合适 pd.DataFrame(history.history).plot(figsize=(8, 5)) plt.grid(True) # 当前的图表和子图可以使用plt.gcf()和plt.gca()获得，分别表示"Get Current Figure"和"Get Current Axes" # 设置y坐标的上下限 plt.gca().set_ylim(0, 1) plt.show() plot_learning_curves(history) ``` ![](/files/-M35ejBZD3Qc1yQH07Bp) ``` # 在测试集上验证效果 model.evaluate(x_test_scaled, y_test) ``` ``` - 1s 53us/sample - loss: 0.2133 - accuracy: 0.8810 [0.3733668773114681, 0.881] ```