框架tensorflow3

tensorflow3

tensorflow 可视化好帮手；

tf.train.SummaryWriter报错，改为tf.summary.FileWriter

软件包安装yum install sqlite-devel

[root@shenzhen tensorflow]# python3 tensor6.py
2018-08-24 21:14:52.513641: I tensorflow/core/platform/cpu_feature_guard.cc:140] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA
[root@shenzhen tensorflow]# ls
events.out.tfevents.1535116493.shenzhen.com  tensor2.py  tensor4.py  tensor6.py
tensor1.py                                   tensor3.py  tensor5.py
[root@shenzhen tensorflow]# cat tensor6.py
#!/usr/local/bin/python3
#coding:utf-8

import tensorflow as tf

def add_layer(inputs,in_size, out_size, activation_function=None):
    #add one more layer and return the output of this layer
    with tf.name_scope('layer'):
        with tf.name_scope('weights'):
            Weights = tf.Variable(tf.random_normal([in_size, out_size]),\
                    name='W')
        with tf.name_scope('biases'):
            biases = tf.Variable(tf.zeros([1,out_size]) + 0.1,name='b')
        with tf.name_scope('Wx_plus_b'):
            Wx_plus_b = tf.add(tf.matmul(inputs, Weights),biases)
        if activation_function is None:
            outputs = Wx_plus_b
        else:
            outputs = activation_function(Wx_plus_b,)
        return outputs

#define placeholder for inputs to network
with tf.name_scope('inputs'):
    xs = tf.placeholder(tf.float32,[None,1],name='x_input')
    ys = tf.placeholder(tf.float32,[None,1],name='y_input')

#add hidden layer
l1 = add_layer(xs,1,10,activation_function=tf.nn.relu)
#add output layer
prediction = add_layer(l1,10,1,activation_function=None)

#the error between prediction and real data
with tf.name_scope('loss'):
    loss = tf.reduce_mean(tf.reduce_sum(tf.square(ys - prediction),\
                       reduction_indices=[1]))
with tf.name_scope('train'):
    train_step = tf.train.GradientDescentOptimizer(0.1).minimize(loss)

init = tf.global_variables_initializer()
sess = tf.Session()
writer = tf.summary.FileWriter('.',sess.graph)
#important step
sess.run(init)

#tensorboard    --logdir='/logs/'

访问浏览器：、、、、

1报错位置：.tf.scalar_summary('batch_loss', loss)AttributeError: 'module' object has no attribute 'scalar_summary'修改为：tf.summary.scalar('batch_loss', loss)原因：新版本做了调整

2.AttributeError: 'module' object has no attribute 'histogram_summary'修改为：tf.summary.histogram

3.tf.merge_all_summaries()改为：summary_op = tf.summaries.merge_all()

4.AttributeError: 'module' object has no attribute 'SummaryWriter':tf.train.SummaryWriter改为tf.summary.FileWriter

报错：

tf.scalar_summary(l.op.name + ' (raw)', l)

AttributeError: 'module' object has no attribute 'scalar_summary'

解决：

tf.scalar_summary('images', images)改为：tf.summary.scalar('images', images)

tf.image_summary('images', images)改为：tf.summary.image('images', images)

还有：

tf.train.SummaryWriter改为：tf.summary.FileWriter

tf.merge_all_summaries()改为：summary_op = tf.summary.merge_all

tf.histogram_summary(var.op.name, var)改为：  tf.summary.histogram

concated = tf.concat(1, [indices, sparse_labels])改为：concated = tf.concat([indices, sparse_labels], 1)