tensorflow学习笔记4（神经网络八股）

2;train,test 告知要喂入网络的训练集和测试集是什么

3：在Sequential中搭建神经网络结构，逐层描述每层网络，相当于走了一边前向传播

4：在compile配置训练方法，选择何种优化器（更新网络参数使用），何种损失函数，何种评测指标

5：在fit中执行训练过程，告知训练特征和标签，告知每个batch是多少，以及迭代多少次训练集

6：summary打印出网络的结构和参数统计 

Flatten()将输入特征拉直，变为一维数组，Dense为全连接层

 

这里有个需要注意的地方 是 from_logit=False or True 的问题，如果神经网络输入经过了概率分布这里选择FALSE，不经过概率分布，直接输出这里选择True

不解释 

当时想为什么 Total params为15不应该为12嘛后来才想打是w1+b1总共15个可训练参数

import tensorflow as tf
from sklearn import datasets
import numpy as np

x_train = datasets.load_iris().data
y_train = datasets.load_iris().target

np.random.seed(116)
np.random.shuffle(x_train)
np.random.seed(116)
np.random.shuffle(y_train)
tf.random.set_seed(116)

model = tf.keras.models.Sequential([
    tf.keras.layers.Dense(3, activation='softmax', kernel_regularizer=tf.keras.regularizers.l2())
])

model.compile(optimizer=tf.keras.optimizers.SGD(lr=0.1),
             loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=False),
              metrics=['sparse_categorical_accuracy'])

model.fit(x_train, y_train, batch_size=32, epochs=500, validation_split=0.2, validation_freq=20)

model.summary()

神经元个数这里，因为神经元个数是不计算输入层的所以，鸢尾花只剩下输出层三个神经元

loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=False)这个数学上是个什么损失函数，我还不是特别清楚，所以暂时先不管，视频中说实践中常用这个函数为损失函数

import tensorflow as tf
from tensorflow.keras.layers import Dense
from tensorflow.keras import Model
from sklearn import datasets
import numpy as np

x_train = datasets.load_iris().data
y_train = datasets.load_iris().target

np.random.seed(116)
np.random.shuffle(x_train)
np.random.seed(116)
np.random.shuffle(y_train)
tf.random.set_seed(116)

class IrisModel(Model):
    def __init__(self):
        super(IrisModel, self).__init__()
        self.d1 = Dense(3, activation='softmax', kernel_regularizer=tf.keras.regularizers.l2())

    def call(self, x):
        y = self.d1(x)
        return y

model = IrisModel()

model.compile(optimizer=tf.keras.optimizers.SGD(lr=0.1),
              loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=False),
              metrics=['sparse_categorical_accuracy'])

model.fit(x_train, y_train, batch_size=32, epochs=500, validation_split=0.2, validation_freq=20)
model.summary()

import tensorflow as tf

mnist = tf.keras.datasets.mnist
(x_train, y_train), (x_test, y_test) = mnist.load_data()
x_train, x_test = x_train / 255.0, x_test / 255.0

model = tf.keras.models.Sequential([
    tf.keras.layers.Flatten(),
    tf.keras.layers.Dense(128, activation='relu'),
    tf.keras.layers.Dense(10, activation='softmax')
])

model.compile(optimizer='adam',
              loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=False),
              metrics=['sparse_categorical_accuracy'])

model.fit(x_train, y_train, batch_size=32, epochs=5, validation_data=(x_test, y_test), validation_freq=1)
model.summary()

import tensorflow as tf
from tensorflow.keras.layers import Dense, Flatten
from tensorflow.keras import Model

mnist = tf.keras.datasets.mnist
(x_train, y_train), (x_test, y_test) = mnist.load_data()
x_train, x_test = x_train / 255.0, x_test / 255.0


class MnistModel(Model):
    def __init__(self):
        super(MnistModel, self).__init__()
        self.flatten = Flatten()
        self.d1 = Dense(128, activation='relu')
        self.d2 = Dense(10, activation='softmax')

    def call(self, x):
        x = self.flatten(x)
        x = self.d1(x)
        y = self.d2(x)
        return y


model = MnistModel()

model.compile(optimizer='adam',
              loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=False),
              metrics=['sparse_categorical_accuracy'])

model.fit(x_train, y_train, batch_size=32, epochs=5, validation_data=(x_test, y_test), validation_freq=1)
model.summary()

self.d1,self.d2 d1是第一层的神经元个数，d2是第二层的神经元个数