every blog every motto: What doesn’t kill you makes you stronger.
0. 前言
本节实战回调函数,以及关于tensorboard的使用。
1. 代码部分
1. 导入模块
import matplotlib as mpl
import matplotlib.pyplot as plt
%matplotlib inline
import numpy as np
import sklearn
import pandas as pd
import os
import sys
import time
import tensorflow as tf
from tensorflow import keras
print(tf.__version__)
print(sys.version_info)
for module in mpl,np,pd,sklearn,tf,keras:
print(module.__name__,module.__version__)
2. 读取数据
fashion_mnist = keras.datasets.fashion_mnist
# print(fashion_mnist)
(x_train_all,y_train_all),(x_test,y_test) = fashion_mnist.load_data()
x_valid,x_train = x_train_all[:5000],x_train_all[5000:]
y_valid,y_train = y_train_all[:5000],y_train_all[5000:]
# 打印格式
print(x_valid.shape,y_valid.shape)
print(x_train.shape,y_train.shape)
print(x_test.shape,y_test.shape)
3. 数据归一化
# 数据归一化
from sklearn.preprocessing import StandardScaler
scaler = StandardScaler()
# x_train:[None,28,28] -> [None,784]
x_train_scaled = scaler.fit_transform(x_train.astype(np.float32).reshape(-1,1)).reshape(-1,28,28)
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)
4. 构建模型
# tf.keras.models.Sequential()
# 构建模型
# 创建对象
"""model = keras.models.Sequential()
model.add(keras.layers.Flatten(input_shape=[28,28]))
model.add(keras.layers.Dense(300,activation='sigmoid'))
model.add(keras.layers.Dense(100,activation='sigmoid'))
model.add(keras.layers.Dense(10,activation='softmax'))"""
# 另一种写法
model = keras.models.Sequential([
keras.layers.Flatten(input_shape=[28,28]),
keras.layers.Dense(300,activation='sigmoid'),
keras.layers.Dense(100,activation='sigmoid'),
keras.layers.Dense(10,activation='softmax')
])
#
model.compile(loss='sparse_categorical_crossentropy',optimizer='sgd',metrics=['accuracy'])
5. 回调函数
# 回调函数 Tensorboard(文件夹)\earylystopping\ModelCheckpoint(文件名)
logdir = os.path.join("callbacks")
print(logdir)
if not os.path.exists(logdir):
os.mkdir(logdir)
# 文件名
output_model_file = os.path.join(logdir,"fashion_mnist_model.h5")
callbacks = [
keras.callbacks.TensorBoard(logdir),
keras.callbacks.ModelCheckpoint(output_model_file,save_best_only=True),
keras.callbacks.EarlyStopping(patience=5,min_delta=1e-3),
]
6. 训练
# 开始训练
history = model.fit(x_train_scaled,y_train,epochs=10,validation_data=(x_valid_scaled,y_valid),callbacks=callbacks)
6.2 学习曲线
# 画图
def plot_learning_curves(history):
pd.DataFrame(history.history).plot(figsize=(8,5))
plt.grid(True)
plt.gca().set_ylim(0,1)
plt.show()
plot_learning_curves(history)
7. 测试集上
model.evaluate(x_test_scaled,y_test)
8 tensorborad展示
8.1 查看callbacks文件结构
- 切换到代码所在路径下
tree
8.2 查看本地端口
- 在终端键入如下命令(注意是代码所在路径下)
tensorboard --logdir=callbacks
显示如下:
8.3 浏览器查看
- 键入本地地址http://localhost:6006/
完!