keras tensorboard的使用, 设置GPU使用的内存

keras2.0版本已经添加了一些贡献者的新建议，用keras调用tensorboard对训练过程进行跟踪观察非常方便了。

直接上例子：

# coding: utf-8
import numpy as np
from keras.datasets import mnist
from keras.models import Sequential
from keras.layers.core import Dense, Dropout, Activation
from keras.optimizers import SGD
from keras.utils import np_utils
import keras.callbacks

import os
import tensorflow as tf
import keras.backend.tensorflow_backend as KTF


######################################
# TODO: set the gpu memory using fraction #
#####################################
def get_session(gpu_fraction=0.3):
    """
    This function is to allocate GPU memory a specific fraction
    Assume that you have 6GB of GPU memory and want to allocate ~2GB
    """

    num_threads = os.environ.get('OMP_NUM_THREADS')
    gpu_options = tf.GPUOptions(per_process_gpu_memory_fraction=gpu_fraction)

    if num_threads:
        return tf.Session(config=tf.ConfigProto(
            gpu_options=gpu_options, intra_op_parallelism_threads=num_threads))
    else:
        return tf.Session(config=tf.ConfigProto(gpu_options=gpu_options))
KTF.set_session(get_session(0.6))  # using 60% of total GPU Memory
os.system("nvidia-smi")  # Execute the command (a string) in a subshell
raw_input("Press Enter to continue...")
######################


batch_size = 128
nb_classes = 10
nb_epoch = 10
nb_data = 28 * 28
log_filepath = '/tmp/keras_log'

# load data

(X_train, y_train), (X_test, y_test) = mnist.load_data()

# reshape
print X_train.shape
X_train = X_train.reshape(X_train.shape[0], X_train.shape[1] * X_train.shape[2])
X_test = X_test.reshape(X_test.shape[0], X_test.shape[1] * X_test.shape[2])
# rescale

X_train = X_train.astype(np.float32)
X_train /= 255

X_test = X_test.astype(np.float32)
X_test /= 255
# convert class vectors to binary class matrices (one hot vectors)

Y_train = np_utils.to_categorical(y_train, nb_classes)
Y_test = np_utils.to_categorical(y_test, nb_classes)

model = Sequential()
model.add(Dense(512, input_shape=(nb_data,), init='normal', name='dense1')) 
 # a sample is a row 28*28
model.add(Activation('relu', name='relu1'))
model.add(Dropout(0.2, name='dropout1'))
model.add(Dense(512, init='normal', name='dense2'))
model.add(Activation('relu', name='relu2'))
model.add(Dropout(0.2, name='dropout2'))
model.add(Dense(10, init='normal', name='dense3'))
model.add(Activation('softmax', name='softmax1'))
model.summary()

model.compile(loss='categorical_crossentropy', optimizer=SGD(lr=0.001), metrics=['accuracy'])

tb_cb = keras.callbacks.TensorBoard(log_dir=log_filepath, write_images=1, histogram_freq=1)
# 设置log的存储位置，将网络权值以图片格式保持在tensorboard中显示，设置每一个周期计算一次网络的
#权值，每层输出值的分布直方图
cbks = [tb_cb]
history = model.fit(X_train, Y_train, batch_size=batch_size, nb_epoch=nb_epoch, 
verbose=1, callbacks=cbks, validation_data=(X_test, Y_test))

score = model.evaluate(X_test, Y_test, verbose=0)
print('Test score:', score[0])
print('Test accuracy;', score[1])

其实可以自己给每一层layer命名一个name, 也可以由keras根据自己的命名规则自动取名，自动命名的规则在Layer类中，代码如下：

name = kwargs.get('name')
if not name:
    prefix = self.__class__.__name__
    name = _to_snake_case(prefix) + '_' + str(K.get_uid(prefix))
self.name = name

而在keras的call back模块中,tensorborad class实现源码可以看出，keras默认将模型的所有层的所有weights, bias以及每一层输出的distribution, histogram等传送到tensorborad，方便在浏览器中观察网络的运行情况。实现源码如下：

def set_model(self, model):
    self.model = model
    self.sess = K.get_session()
    if self.histogram_freq and self.merged is None:
        for layer in self.model.layers:

            for weight in layer.weights:
                tf.summary.histogram(weight.name, weight)
                if self.write_images:
                    w_img = tf.squeeze(weight)
                    shape = w_img.get_shape()
                    if len(shape) > 1 and shape[0] > shape[1]:
                        w_img = tf.transpose(w_img)
                    if len(shape) == 1:
                        w_img = tf.expand_dims(w_img, 0)
                    w_img = tf.expand_dims(tf.expand_dims(w_img, 0), -1)
                    tf.summary.image(weight.name, w_img)

            if hasattr(layer, 'output'):
                tf.summary.histogram('{}_out'.format(layer.name),
                                     layer.output)
    self.merged = tf.summary.merge_all()

现在运行最开始的例子，在terminal运行

tensorboard --logdir=/tmp/keras_log

在terminal打开浏览器地址，进入tensorboard可以随意浏览graph, distribution, histogram， 以及sclar列表中的loss, acc等等了