Tensorflow2.0与Tensorflow1.0的理解

Tensorflow1.x与Tensorflow2.x的理解

首先，作者接触过tf1.0和tf2.0，结合说明一下！

Tensorflow0.x.x

这个版本貌似很难install到，笔者安装好几次都是失败，但是不可否认的是现在还有许多github开源的人工智能源码还是使用tf0.x.x版本。这里笔者只能提供一个0.x.x升级到1.x.x代码的脚本(引用小伙伴的博客)。

Tensorflow1.x

Tensorflow1.x最重要的在于Graph的概念，个人认为搭建相对较为麻烦，但是tf1.x也较为灵活。

Tensorflow2.x

Tensorflow2.x兼容keras，非常好用。

考虑CNN模型

tensorflow1.x.x版本如下：

import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
import os
os.environ["CUDA_DEVICE_ORDER"] = "0,1"
 
 
mnist = input_data.read_data_sets("MNIST_data",one_hot=True)
 
def compute_accuracy(v_xs,v_ys):
    global prediction
    y_pre = sess.run(prediction,feed_dict ={xs:v_xs,keep_prob:1})
    correct_predicton = tf.equal(tf.argmax(y_pre,1),tf.argmax(v_ys,1))
    accuracy = tf.reduce_mean(tf.cast(correct_predicton,tf.float32))
    result = sess.run(accuracy,feed_dict = {xs:v_xs,ys:v_ys,keep_prob:1})
    return result
 
def weight_variable(shape):
    initial = tf.truncated_normal(shape=shape,stddev=0.1)
    return tf.Variable(initial)
 
def bias_variable(shape):
    initial = tf.constant(0.1,shape=shape)
    return tf.Variable(initial)
 
def conv2d(x,W):
    #stride [1,x_movement,y_movement,1]
    #Must have strides[0] = strides[3] = 1
    return tf.nn.conv2d(x,W,strides=[1,1,1,1],padding="SAME")
 
def max_pool_2x2(x):
    # stride [1,x_movement,y_movement,1]
    return tf.nn.max_pool(x,ksize=[1,2,2,1],strides=[1,2,2,1],padding="SAME")
 
def add_layer(inputs,in_size,out_size,activation_function=None):
    Weight = tf.Variable(tf.random_normal([in_size,out_size]))
    biases = tf.Variable(tf.zeros([1,out_size])+0.1)
    Wx_plus_b = tf.matmul(inputs,Weight)+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
 
xs = tf.placeholder(tf.float32,[None,784])
ys = tf.placeholder(tf.float32,[None,10])
keep_prob = tf.placeholder(tf.float32)
x_image = tf.reshape(xs,[-1,28,28,1])
 
## conv1 layer ##
W_conv1 = weight_variable([5,5, 1,32]) # patch 5x5, in size 1, out size 32
b_conv1 = bias_variable([32])
h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1) # output size 28x28x32
h_pool1 = max_pool_2x2(h_conv1)                                         # output size 14x14x32
 
## conv2 layer ##
W_conv2 = weight_variable([5,5, 32, 64]) # patch 5x5, in size 32, out size 64
b_conv2 = bias_variable([64])
h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2) # output size 14x14x64
h_pool2 = max_pool_2x2(h_conv2)              # output size 7x7x64
 
 
# #func1 layer
# input = tf.reshape(h_pool2,[-1,7*7*64])
# fc1 = add_layer(input,7*7*64,1024,activation_function=tf.nn.relu)
# fc1_drop = tf.nn.dropout(fc1,keep_prob)
#
# #func2 layer
# fc2 = add_layer(fc1_drop,1024,10,activation_function=tf.nn.softmax)
# prediction = fc2
 
## func1 layer ##
W_fc1 = weight_variable([7*7*64, 1024])
b_fc1 = bias_variable([1024])
# [n_samples, 7, 7, 64] ->> [n_samples, 7*7*64]
h_pool2_flat = tf.reshape(h_pool2, [-1, 7*7*64])
h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1)
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)
 
## func2 layer ##
W_fc2 = weight_variable([1024, 10])
b_fc2 = bias_variable([10])
prediction = tf.nn.softmax(tf.matmul(h_fc1_drop, W_fc2) + b_fc2)
 
#loss
cross_entropy = tf.reduce_mean(-tf.reduce_sum(ys*tf.log(prediction),reduction_indices=[1]))
 
train_step = tf.train.AdamOptimizer(0.0001).minimize(cross_entropy)
 
config = tf.ConfigProto(log_device_placement=True)
config.gpu_options.allow_growth = True
 
sess = tf.Session(config=config)
 
sess.run(tf.initialize_all_variables())
 
for i in range(1000):
    batch_xs,batch_ys = mnist.train.next_batch(100)
    sess.run(train_step,feed_dict={xs:batch_xs,ys:batch_ys,keep_prob:0.5})
    if i%50 ==0:
        print(compute_accuracy(mnist.test.images,mnist.test.labels))

tensorflow2.x.x版本如下：

from tensorflow.keras import Sequential,layers
import tensorflow as tf
network = Sequential([ # 网络容器
    layers.Conv2D(6,kernel_size=3,strides=1), # 第一个卷积层, 6 个3x3 卷积核
    layers.MaxPooling2D(pool_size=2,strides=2), # 高宽各减半的池化层
    layers.ReLU(), # 激活函数
    layers.Conv2D(16,kernel_size=3,strides=1), # 第二个卷积层, 16 个3x3 卷积核
    layers.MaxPooling2D(pool_size=2,strides=2), # 高宽各减半的池化层
    layers.ReLU(), # 激活函数
    layers.Flatten(), # 打平层，方便全连接层处理
    layers.Dense(120, activation='relu'), # 全连接层，120 个节点
    layers.Dense(84, activation='relu'), # 全连接层，84 节点
    layers.Dense(10) # 全连接层，10 个节点
    ])
# build 一次网络模型，给输入X 的形状，其中4 为随意给的batchsz
network.build(input_shape=(4, 28, 28, 1))
# 统计网络信息
network.summary()
# network.fit(x, y) 通过x和y训练模型

总结

两者皆有好坏，tensorflow1.x.x的热度胜于tensorflow2.x.x，这是由于目前tensorflow2.x.x版本的源码不多。

关于作者

如果需要将tensorflow1.x.x不通过脚本的方式转换为tensorflow2.x.x可以联系作者(QQ邮箱：[email protected])