tensorflow08-分类任务coding

import pickle
import gzip
from pathlib import Path
from matplotlib import pyplot


#  Pathlib 库来操作文件路径，用法如下所示：
filepath=Path("mnist.pkl.gz")#https://github.com/mnielsen/neural-networks-and-deep-learning/tree/master/data
with gzip.open(filepath.as_posix(),"rb") as f:
    ((x_t,y_t),(x_v,y_v),_)=pickle.load(f,encoding="latin_1")
pyplot.imshow(x_t[0].reshape((28,28)),cmap="gray")
print(x_t.shape)#(500

 输入为一个样本多少个特征  但是这个图像为28*28*1 的三维矩阵

所以先转换样本  

input    784pixel    像素点=》 输入神经网络

神经网络特征提取器 -》无论做分类还是回归都是一样的

 

import pickle
import gzip
from pathlib import Path
from matplotlib import pyplot


#  Pathlib 库来操作文件路径，用法如下所示：
filepath=Path("mnist.pkl.gz")#https://github.com/mnielsen/neural-networks-and-deep-learning/tree/master/data
with gzip.open(filepath.as_posix(),"rb") as f:
    ((x_t,y_t),(x_v,y_v),_)=pickle.load(f,encoding="latin_1")
pyplot.imshow(x_t[0].reshape((28,28)),cmap="gray")
print(x_t.shape)#(50000, 784)  784 为每个样本的像素点个数


import tensorflow as tf
# from tensorflow.keras import  layers  #2.0versiong
# import keras
# print(tf.version)
# print(tf.version.VERSION)
model = tf.keras.Sequential()
model.add(tf.keras.layers.Dense(32, activation='relu'))
model.add(tf.keras.layers.Dense(32, activation='relu'))
model.add(tf.keras.layers.Dense(10, activation='softmax'))
model.compile(optimizer=tf.keras.optimizers.Adam(0.01),
              loss=tf.keras.losses.sparse_categorical_crossentropy,
              metrics=[tf.keras.metrics.sparse_categorical_accuracy])
model.fit(x_t, y_t, epochs=5, batch_size=64, validation_data=(x_v, y_v))
　

 可以看到对比回归 模型

隐藏layer

 

 

  保存模型