前言

这几天caffe2发布了,支持移动端,我理解是类似单片机的物联网吧应该不是手机之类的,试想iphone7跑CNN,画面太美~
作为一个刚入坑的,甚至还没入坑的人,咱们还是老实研究下tensorflow吧,虽然它没有caffe好上手。tensorflow的特点我就不介绍了:
tensorflow(tf)运算流程:
tensorflow的运行流程主要有2步,分别是构造模型和训练。
在构造模型阶段,我们需要构建一个图(Graph)来描述我们的模型,tensoflow的强大之处也在这了,支持tensorboard:

就类似这样的图,有点像流程图,这里还推荐一个google的tensoflow游乐场,很有意思。
然后到了训练阶段,在构造模型阶段是不进行计算的,只有在tensoflow.Session.run()时会开始计算。
文本分类
先给出代码,然后我们在一一做解释
# -*- coding: utf-8 -*-
import pandas as pd
import numpy as np
import tensorflow as tf
from collections import Counter
from sklearn.datasets import fetch_20newsgroups
def get_word_2_index(vocab):
word2index = {}
for i,word in enumerate(vocab):
word2index[word] = i
return word2index
def get_batch(df,i,batch_size):
batches = []
results = []
texts = df.data[i*batch_size : i*batch_size+batch_size]
categories = df.target[i*batch_size : i*batch_size+batch_size]
for text in texts:
layer = np.zeros(total_words,dtype=float)
for word in text.split(' '):
layer[word2index[word.lower()]] += 1
batches.append(layer)
for category in categories:
y = np.zeros((3),dtype=float)
if category == 0:
y[0] = 1.
elif category == 1:
y[1] = 1.
else:
y[2] = 1.
results.append(y)
return np.array(batches),np.array(results)
def multilayer_perceptron(input_tensor, weights, biases):
#hidden层RELU函数激励
layer_1_multiplication = tf.matmul(input_tensor, weights['h2'])
layer_1_addition = tf.add(layer_1_multiplication, biases['b1'])
layer_1 = tf.nn.relu(layer_1_addition)
layer_2_multiplication = tf.matmul(layer_1, weights['h3'])
layer_2_addition = tf.add(layer_2_multiplication, biases['b2'])
layer_2 = tf.nn.relu(layer_2_addition)
# Output layer
out_layer_multiplication = tf.matmul(layer_2, weights['out'])
out_layer_addition = out_layer_multiplication + biases['out']
return out_layer_addition
#main
#从sklearn.datas获取数据
cate = ["comp.graphics","sci.space","rec.sport.baseball"]
newsgroups_train = fetch_20newsgroups(subset='train', categories=cate)
newsgroups_test = fetch_20newsgroups(subset='test', categories=cate)
# 计算训练和测试数据总数
vocab = Counter()
for text in newsgroups_train.data:
for word in text.split(' '):
vocab[word.lower()]+=1
for text in newsgroups_test.data:
for word in text.split(' '):
vocab[word.lower()]+=1
total_words = len(vocab)
word2index = get_word_2_index(vocab)
n_hidden_1 = 100 # 一层hidden层神经元个数
n_hidden_2 = 100 # 二层hidden层神经元个数
n_input = total_words
n_classes = 3 # graphics, sci.space and baseball 3层输出层即将文本分为三类
#占位
input_tensor = tf.placeholder(tf.float32,[None, n_input],name="input")
output_tensor = tf.placeholder(tf.float32,[None, n_classes],name="output")
#正态分布存储权值和偏差值
weights = {
'h2': tf.Variable(tf.random_normal([n_input, n_hidden_1])),
'h3': tf.Variable(tf.random_normal([n_hidden_1, n_hidden_2])),
'out': tf.Variable(tf.random_normal([n_hidden_2, n_classes]))
}
biases = {
'b1': tf.Variable(tf.random_normal([n_hidden_1])),
'b2': tf.Variable(tf.random_normal([n_hidden_2])),
'out': tf.Variable(tf.random_normal([n_classes]))
}
#初始化
prediction = multilayer_perceptron(input_tensor, weights, biases)
# 定义 loss and optimizer 采用softmax函数
# reduce_mean计算平均误差
loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=prediction, labels=output_tensor))
optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(loss)
#初始化所有变量
init = tf.global_variables_initializer()
#部署 graph
with tf.Session() as sess:
sess.run(init)
training_epochs = 100
display_step = 5
batch_size = 1000
# Training
for epoch in range(training_epochs):
avg_cost = 0.
total_batch = int(len(newsgroups_train.data) / batch_size)
for i in range(total_batch):
batch_x,batch_y = get_batch(newsgroups_train,i,batch_size)
c,_ = sess.run([loss,optimizer], feed_dict={input_tensor: batch_x,output_tensor:batch_y})
# 计算平均损失
avg_cost += c / total_batch
# 每5次epoch展示一次loss
if epoch % display_step == 0:
print("Epoch:", '%d' % (epoch+1), "loss=", "{:.6f}".format(avg_cost))
print("Finished!")
# Test model
correct_prediction = tf.equal(tf.argmax(prediction, 1), tf.argmax(output_tensor, 1))
# 计算准确率
accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))
total_test_data = len(newsgroups_test.target)
batch_x_test,batch_y_test = get_batch(newsgroups_test,0,total_test_data)
print("Accuracy:", accuracy.eval({input_tensor: batch_x_test, output_tensor: batch_y_test}))另外有需要云服务器可以了解下创新互联scvps.cn,海内外云服务器15元起步,三天无理由+7*72小时售后在线,公司持有idc许可证,提供“云服务器、裸金属服务器、高防服务器、香港服务器、美国服务器、虚拟主机、免备案服务器”等云主机租用服务以及企业上云的综合解决方案,具有“安全稳定、简单易用、服务可用性高、性价比高”等特点与优势,专为企业上云打造定制,能够满足用户丰富、多元化的应用场景需求。