03-Tensorflow2.0使用callbacks参数和Tensorboard的使用

Tensorflow2.0使用callbacks参数和Tensorboard的使用

这篇文章是在上篇文章tensorflow2.0识别fashion_mnist数据集的基础上，在训练(model.fit())时，添加了callbacks参数,主要参数有三个：

• Tensorboard
• Earlystopping
• ModelCheckpoint

详细代码如下：
注：此代码的精确度和上一篇文章相同，这篇文章主要讲解一下Tensorboard

#-*- coding:utf-8 _*-
import matplotlib as mpl
import matplotlib.pyplot as plt
import numpy as np
import sklearn
import pandas as pd
import os
import sys
import time
import tensorflow as tf
from tensorflow import keras
# 输出库的名字和版本
print(sys.version_info)
for module in tf, mpl, np, pd, sklearn, tf, keras:
    print(module.__name__, module.__version__)

# 指定GPU
os.environ["CUDA_DEVICE_ORDER"] = "PCI_BUS_ID"
os.environ["CUDA_VISIBLE_DEVICES"] = '1'
config = tf.compat.v1.ConfigProto()
config.gpu_options.allow_growth = True
sess = tf.compat.v1.Session(config=config)

# 导入数据集 fashion_mnist
fashion_mnist = keras.datasets.fashion_mnist
(x_train_all,y_train_all),(x_test_all,y_test_all) = 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:]
x_test , y_test = x_test_all,y_test_all

print(x_train.shape,y_train.shape)
print(x_valid.shape,y_valid.shape)
print(x_test.shape,y_test.shape)

# 数据归一化
from sklearn.preprocessing import StandardScaler
scaler = StandardScaler()
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)


# 模型建立
model = tf.keras.Sequential([
    keras.layers.Flatten(input_shape=[28,28]),
    keras.layers.Dense(300,activation='relu'),
    keras.layers.Dense(100,activation='relu'),
    keras.layers.Dense(10, activation='softmax')
])

# 模型编译
model.compile(loss='sparse_categorical_crossentropy',
               optimizer='sgd',
               metrics=['accuracy'])

# 模型训练 history.history是一个重要的参数
# callbacks : Tensorborad,earlystopping,ModelCheckpoint
logdir = './callbacks'
if not os.path.exists(logdir):
    os.makedirs(logdir)
output_model_file = os.path.join(logdir,'fashion_minst_models.h5')
callbacks = [
    keras.callbacks.TensorBoard(logdir),
    keras.callbacks.ModelCheckpoint(output_model_file,
                                    save_best_only = True),# 只保存最好的模型
    keras.callbacks.EarlyStopping(patience=5,min_delta=1e-3)
]

history = model.fit(x_train_scaled,y_train,
                    epochs=10,
                    validation_data=(x_valid_scaled,y_valid),
                    callbacks = callbacks)

# 绘制history图像
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)

# 测试集上进行测试
model.evaluate(x_test_scaled,y_test)

代码运行后，会生成一个callbacks的文件夹：

然后，在cmd等命令行中输入

tensorboard --logdir=D:[你自己的具体的目录下]/callbacks

或者是先使用cd切换到具体的目录下，再使用上面的命令

然后再浏览器中打开 http://localhost:6006
即可以看到如下图所示的内容：