TensorFlow - Keras搭建神经网络（鸢尾花分类）

tf.keras.losses.SparseCategoricalCrossentropy(from_logits=False) 

有些函数经过softmax激活，输出的是概率分布，有些函数则是原始输出；

from_logits=False 是在询问受否是原始输出，即没有经过概率分布的输出

如果神经网络预测结果输出前经过了概率分布，则为False

如果神经网络预测结果输出前没有经过概率分布，则为True

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()  

"""
val_sparse_categorical_accuracy: 1.0000
Model: "sequential_1"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
dense_1 (Dense)              multiple                  15        
=================================================================
Total params: 15
Trainable params: 15
Non-trainable params: 0
_________________________________________________________________
"""

validation_freq=20

每迭代20次训练集，要在测试集中验证一次准确率

model.summary()  打印出网络结构和参数统计