Keras使用

2018-05-14  本文已影响0人  咫尺是梦

参考:
Keras学习率调整
深度学习框架Keras使用心得

一、如何调整学习率

Keras提供两种学习率适应方法,可通过回调函数实现。

LearningRateScheduler

1.  keras.callbacks.LearningRateScheduler(schedule)  

该回调函数是学习率调度器

参数

ReduceLROnPlateau

1.  keras.callbacks.ReduceLROnPlateau(monitor='val_loss', factor=0.1,
patience=10, verbose=0, mode='auto', epsilon=0.0001, cooldown=0, min_lr=0)  

当评价指标不在提升时,减少学习率

当学习停滞时,减少2倍或10倍的学习率常常能获得较好的效果。该回调函数检测指标的情况,如果在patience个epoch中看不到模型性能提升,则减少学习率

参数


二、如何在使用train_on_batch时候调用tensorboard

Tensorboard On Train_on_batch

运行下列代码

import numpy as np
import tensorflow as tf
from keras.callbacks import TensorBoard
from keras.layers import Input, Dense
from keras.models import Model


def write_log(callback, names, logs, batch_no):
    for name, value in zip(names, logs):
        summary = tf.Summary()
        summary_value = summary.value.add()
        summary_value.simple_value = value
        summary_value.tag = name
        callback.writer.add_summary(summary, batch_no)
        callback.writer.flush()
    
net_in = Input(shape=(3,))
net_out = Dense(1)(net_in)
model = Model(net_in, net_out)
model.compile(loss='mse', optimizer='sgd', metrics=['mae'])

log_path = './graph'
callback = TensorBoard(log_path)
callback.set_model(model)
train_names = ['train_loss', 'train_mae']
val_names = ['val_loss', 'val_mae']
for batch_no in range(100):
    X_train, Y_train = np.random.rand(32, 3), np.random.rand(32, 1)
    logs = model.train_on_batch(X_train, Y_train)
    write_log(callback, train_names, logs, batch_no)
    
    if batch_no % 10 == 0:
        X_val, Y_val = np.random.rand(32, 3), np.random.rand(32, 1)
        logs = model.train_on_batch(X_val, Y_val)
        write_log(callback, val_names, logs, batch_no//10)
Using TensorFlow backend.
上一篇 下一篇

猜你喜欢

热点阅读