盗墓笔记小说,管理书籍排行榜,盗墓笔记小说全集

主頁(yè) > 知識(shí)庫(kù) > 由淺入深學(xué)習(xí)TensorFlow MNIST 數(shù)據(jù)集

由淺入深學(xué)習(xí)TensorFlow MNIST 數(shù)據(jù)集

MNIST 數(shù)據(jù)集介紹

MNIST 包含 0~9 的手寫數(shù)字, 共有 60000 個(gè)訓(xùn)練集和 10000 個(gè)測(cè)試集. 數(shù)據(jù)的格式為單通道 28*28 的灰度圖.

LeNet 模型介紹

LeNet 網(wǎng)絡(luò)最早由紐約大學(xué)的 Yann LeCun 等人于 1998 年提出, 也稱 LeNet5. LeNet 是神經(jīng)網(wǎng)絡(luò)的鼻祖, 被譽(yù)為卷積神經(jīng)網(wǎng)絡(luò)的 “Hello World”.

卷積

池化 (下采樣)

激活函數(shù) (ReLU)

LeNet 逐層分析

1. 第一個(gè)卷積層

2. 第一個(gè)池化層

3. 第二個(gè)卷積層

4. 第二個(gè)池化層

5. 全連接卷積層

6. 全連接層

7. 全連接層 (輸出層)

代碼實(shí)現(xiàn)

導(dǎo)包

from tensorflow.keras.datasets import mnist
from matplotlib import pyplot as plt
import numpy as np
import tensorflow as tf

讀取查看數(shù)據(jù)

# ------------------1. 讀取  查看數(shù)據(jù)------------------

# 讀取數(shù)據(jù)
(X_train, y_train), (X_test, y_test) = mnist.load_data()

# 數(shù)據(jù)集查看
print(X_train.shape)  # (60000, 28, 28)
print(y_train.shape)  # (60000,)
print(X_test.shape)  # (10000, 28, 28)
print(y_test.shape)  # (10000,)
print(type(X_train))  # class 'numpy.ndarray'>

# 圖片顯示
plt.imshow(X_train[0], cmap="Greys")  # 查看第一張圖片
plt.show()

數(shù)據(jù)預(yù)處理

# ------------------2. 數(shù)據(jù)預(yù)處理------------------

# 格式轉(zhuǎn)換 (將圖片從28*28擴(kuò)充為32*32)
X_train = np.pad(X_train, ((0, 0), (2, 2), (2, 2)), "constant", constant_values=0)
X_test = np.pad(X_test, ((0, 0), (2, 2), (2, 2)), "constant", constant_values=0)
print(X_train.shape)  # (60000, 32, 32)
print(X_test.shape)  # (10000, 32, 32)

# 數(shù)據(jù)集格式變換
X_train = X_train.astype(np.float32)
X_test = X_test.astype(np.float32)

# 數(shù)據(jù)正則化
X_train /= 255
X_test /= 255

# 數(shù)據(jù)維度轉(zhuǎn)換
X_train = np.expand_dims(X_train, axis=-1)
X_test = np.expand_dims(X_test, axis=-1)
print(X_train.shape)  # (60000, 32, 32, 1)
print(X_test.shape)  # (10000, 32, 32, 1)

模型建立

# 第一個(gè)卷積層
conv_layer_1 = tf.keras.layers.Conv2D(filters=6, kernel_size=(5, 5), padding="valid", activation=tf.nn.relu)
# 第一個(gè)池化層
pool_layer_1 = tf.keras.layers.MaxPool2D(pool_size=(2, 2), padding="same")
# 第二個(gè)卷積層
conv_layer_2 = tf.keras.layers.Conv2D(filters=16, kernel_size=(5, 5), padding="valid", activation=tf.nn.relu)
# 第二個(gè)池化層
pool_layer_2 = tf.keras.layers.MaxPool2D(padding="same")
# 扁平化
flatten = tf.keras.layers.Flatten()
# 第一個(gè)全連接層
fc_layer_1 = tf.keras.layers.Dense(units=120, activation=tf.nn.relu)
# 第二個(gè)全連接層
fc_layer_2 = tf.keras.layers.Dense(units=84, activation=tf.nn.softmax)
# 輸出層
output_layer = tf.keras.layers.Dense(units=10, activation=tf.nn.softmax)

卷積 Conv2D 的用法:

filters: 卷積核個(gè)數(shù)
kernel_size: 卷積核大小
strides = (1, 1): 步長(zhǎng)
padding = “vaild”: valid 為舍棄, same 為補(bǔ)齊
activation = tf.nn.relu: 激活函數(shù)
data_format = None: 默認(rèn) channels_last

池化 AveragePooling2D 的用法:

pool_size: 池的大小
strides = (1, 1): 步長(zhǎng)
padding = “vaild”: valid 為舍棄, same 為補(bǔ)齊
activation = tf.nn.relu: 激活函數(shù)
data_format = None: 默認(rèn) channels_last

全連接 Dense 的用法:

units: 輸出的維度
activation: 激活函數(shù)
strides = (1, 1): 步長(zhǎng)
padding = “vaild”: valid 為舍棄, same 為補(bǔ)齊
activation = tf.nn.relu: 激活函數(shù)
data_format = None: 默認(rèn) channels_last

# 模型實(shí)例化
model = tf.keras.models.Sequential([
    tf.keras.layers.Conv2D(filters=6, kernel_size=(5, 5), padding='valid', activation=tf.nn.relu,
                           input_shape=(32, 32, 1)),
    # relu
    tf.keras.layers.AveragePooling2D(pool_size=(2, 2), strides=(2, 2), padding='same'),
    tf.keras.layers.Conv2D(filters=16, kernel_size=(5, 5), padding='valid', activation=tf.nn.relu),
    tf.keras.layers.AveragePooling2D(pool_size=(2, 2), strides=(2, 2), padding='same'),
    tf.keras.layers.Flatten(),
    tf.keras.layers.Dense(units=120, activation=tf.nn.relu),

    tf.keras.layers.Dense(units=84, activation=tf.nn.relu),
    tf.keras.layers.Dense(units=10, activation=tf.nn.softmax)
])

# 模型展示
model.summary()

輸出結(jié)果:

訓(xùn)練模型

# ------------------4. 訓(xùn)練模型------------------

# 設(shè)置超參數(shù)
num_epochs = 10  # 訓(xùn)練輪數(shù)
batch_size = 1000  # 批次大小
learning_rate = 0.001  # 學(xué)習(xí)率

# 定義優(yōu)化器
adam_optimizer = tf.keras.optimizers.Adam(learning_rate)
model.compile(optimizer=adam_optimizer,loss=tf.keras.losses.sparse_categorical_crossentropy,metrics=['accuracy'])

complie 的用法:

optimizer: 優(yōu)化器
loss: 損失函數(shù)
metrics: 評(píng)價(jià)

with tf.Session() as sess:
    # 初始化所有變量
    init = tf.global_variables_initializer()
    sess.run(init)

    model.fit(x=X_train,y=y_train,batch_size=batch_size,epochs=num_epochs)

    # 評(píng)估指標(biāo)
    print(model.evaluate(X_test, y_test))  # loss value  metrics values

輸出結(jié)果:

fit 的用法:

x: 訓(xùn)練集
y: 測(cè)試集
batch_size: 批次大小
enpochs: 訓(xùn)練遍數(shù)

保存模型

# ------------------5. 保存模型------------------
model.save('lenet_model.h5')

流程總結(jié)

完整代碼

from tensorflow.keras.datasets import mnist
from matplotlib import pyplot as plt
import numpy as np
import tensorflow as tf

# ------------------1. 讀取  查看數(shù)據(jù)------------------

# 讀取數(shù)據(jù)
(X_train, y_train), (X_test, y_test) = mnist.load_data()

# 數(shù)據(jù)集查看
print(X_train.shape)  # (60000, 28, 28)
print(y_train.shape)  # (60000,)
print(X_test.shape)  # (10000, 28, 28)
print(y_test.shape)  # (10000,)
print(type(X_train))  # class 'numpy.ndarray'>

# 圖片顯示
plt.imshow(X_train[0], cmap="Greys")  # 查看第一張圖片
plt.show()

# ------------------2. 數(shù)據(jù)預(yù)處理------------------

# 格式轉(zhuǎn)換 (將圖片從28*28擴(kuò)充為32*32)
X_train = np.pad(X_train, ((0, 0), (2, 2), (2, 2)), "constant", constant_values=0)
X_test = np.pad(X_test, ((0, 0), (2, 2), (2, 2)), "constant", constant_values=0)
print(X_train.shape)  # (60000, 32, 32)
print(X_test.shape)  # (10000, 32, 32)

# 數(shù)據(jù)集格式變換
X_train = X_train.astype(np.float32)
X_test = X_test.astype(np.float32)

# 數(shù)據(jù)正則化
X_train /= 255
X_test /= 255

# 數(shù)據(jù)維度轉(zhuǎn)換
X_train = np.expand_dims(X_train, axis=-1)
X_test = np.expand_dims(X_test, axis=-1)
print(X_train.shape)  # (60000, 32, 32, 1)
print(X_test.shape)  # (10000, 32, 32, 1)

# ------------------3. 模型建立------------------

# 第一個(gè)卷積層
conv_layer_1 = tf.keras.layers.Conv2D(filters=6, kernel_size=(5, 5), padding="valid", activation=tf.nn.relu)
# 第一個(gè)池化層
pool_layer_1 = tf.keras.layers.MaxPool2D(pool_size=(2, 2), padding="same")
# 第二個(gè)卷積層
conv_layer_2 = tf.keras.layers.Conv2D(filters=16, kernel_size=(5, 5), padding="valid", activation=tf.nn.relu)
# 第二個(gè)池化層
pool_layer_2 = tf.keras.layers.MaxPool2D(padding="same")
# 扁平化
flatten = tf.keras.layers.Flatten()
# 第一個(gè)全連接層
fc_layer_1 = tf.keras.layers.Dense(units=120, activation=tf.nn.relu)
# 第二個(gè)全連接層
fc_layer_2 = tf.keras.layers.Dense(units=84, activation=tf.nn.softmax)
# 輸出層
output_layer = tf.keras.layers.Dense(units=10, activation=tf.nn.softmax)


# 模型實(shí)例化
model = tf.keras.models.Sequential([
    tf.keras.layers.Conv2D(filters=6, kernel_size=(5, 5), padding='valid', activation=tf.nn.relu,
                           input_shape=(32, 32, 1)),
    # relu
    tf.keras.layers.AveragePooling2D(pool_size=(2, 2), strides=(2, 2), padding='same'),
    tf.keras.layers.Conv2D(filters=16, kernel_size=(5, 5), padding='valid', activation=tf.nn.relu),
    tf.keras.layers.AveragePooling2D(pool_size=(2, 2), strides=(2, 2), padding='same'),
    tf.keras.layers.Flatten(),
    tf.keras.layers.Dense(units=120, activation=tf.nn.relu),

    tf.keras.layers.Dense(units=84, activation=tf.nn.relu),
    tf.keras.layers.Dense(units=10, activation=tf.nn.softmax)
])

# 模型展示
model.summary()

# ------------------4. 訓(xùn)練模型------------------

# 設(shè)置超參數(shù)
num_epochs = 10  # 訓(xùn)練輪數(shù)
batch_size = 1000  # 批次大小
learning_rate = 0.001  # 學(xué)習(xí)率

# 定義優(yōu)化器
adam_optimizer = tf.keras.optimizers.Adam(learning_rate)
model.compile(optimizer=adam_optimizer,loss=tf.keras.losses.sparse_categorical_crossentropy,metrics=['accuracy'])


with tf.Session() as sess:
    # 初始化所有變量
    init = tf.global_variables_initializer()
    sess.run(init)

    model.fit(x=X_train,y=y_train,batch_size=batch_size,epochs=num_epochs)

    # 評(píng)估指標(biāo)
    print(model.evaluate(X_test, y_test))  # loss value  metrics values

# ------------------5. 保存模型------------------
model.save('lenet_model.h5')

到此這篇關(guān)于由淺入深學(xué)習(xí)TensorFlow MNIST 數(shù)據(jù)集的文章就介紹到這了,更多相關(guān)TensorFlow MNIST 數(shù)據(jù)集內(nèi)容請(qǐng)搜索腳本之家以前的文章或繼續(xù)瀏覽下面的相關(guān)文章希望大家以后多多支持腳本之家！

您可能感興趣的文章:

TensorFlow 實(shí)戰(zhàn)之實(shí)現(xiàn)卷積神經(jīng)網(wǎng)絡(luò)的實(shí)例講解
PyTorch上實(shí)現(xiàn)卷積神經(jīng)網(wǎng)絡(luò)CNN的方法
CNN的Pytorch實(shí)現(xiàn)(LeNet)
Python深度學(xué)習(xí)pytorch卷積神經(jīng)網(wǎng)絡(luò)LeNet

標(biāo)簽：呂梁紹興蘭州安康吉安廣西懷化蕪湖

巨人網(wǎng)絡(luò)通訊聲明：本文標(biāo)題《由淺入深學(xué)習(xí)TensorFlow MNIST 數(shù)據(jù)集》，本文關(guān)鍵詞由淺入深,學(xué)習(xí),TensorFlow,；如發(fā)現(xiàn)本文內(nèi)容存在版權(quán)問(wèn)題，煩請(qǐng)?zhí)峁┫嚓P(guān)信息告之我們，我們將及時(shí)溝通與處理。本站內(nèi)容系統(tǒng)采集于網(wǎng)絡(luò)，涉及言論、版權(quán)與本站無(wú)關(guān)。