[TensorFlow深度学习入门]实战六·用CNN做Kaggle比赛手写数字识别准确率99%+

[TensorFlow深度学习入门]实战六·用CNN做Kaggle比赛手写数字识别准确率99%+

参考博客地址
本博客采用Lenet5实现,也包含TensorFlow模型参数保存与加载参考我的博文,实用性比较好。在训练集准确率99.85%,测试训练集准确率99%+。

  • 训练与模型参数保存

train文件

import os
os.environ["KMP_DUPLICATE_LIB_OK"]="TRUE"
import pandas as pd
import tensorflow as tf  
from tensorflow.examples.tutorials.mnist import input_data  
  
mnist = input_data.read_data_sets('./1CNN/mnistcnn/data', one_hot=True)  
  
#sess = tf.InteractiveSession()  
  
#训练数据  
x = tf.placeholder("float", shape=[None, 784],name="x")  
#训练标签数据  
y_ = tf.placeholder("float", shape=[None, 10],name="y_")  
#把x更改为4维张量,第1维代表样本数量,第2维和第3维代表图像长宽, 第4维代表图像通道数, 1表示灰度  
x_image = tf.reshape(x, [-1,28,28,1])  
  
#第一层:卷积层  
conv1_weights = tf.get_variable("conv1_weights", [5, 5, 1, 32], initializer=tf.truncated_normal_initializer(stddev=0.1)) #过滤器大小为5*5, 当前层深度为1, 过滤器的深度为32  
conv1_biases = tf.get_variable("conv1_biases", [32], initializer=tf.constant_initializer(0.0))  
conv1 = tf.nn.conv2d(x_image, conv1_weights, strides=[1, 1, 1, 1], padding='SAME') #移动步长为1, 使用全0填充  
relu1 = tf.nn.relu( tf.nn.bias_add(conv1, conv1_biases) ) #激活函数Relu去线性化  

#第二层:最大池化层  
#池化层过滤器的大小为2*2, 移动步长为2,使用全0填充  
pool1 = tf.nn.max_pool(relu1, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME')  

#第三层:卷积层  
conv2_weights = tf.get_variable("conv2_weights", [5, 5, 32, 64], initializer=tf.truncated_normal_initializer(stddev=0.1)) #过滤器大小为5*5, 当前层深度为32, 过滤器的深度为64  
conv2_biases = tf.get_variable("conv2_biases", [64], initializer=tf.constant_initializer(0.0))  
conv2 = tf.nn.conv2d(pool1, conv2_weights, strides=[1, 1, 1, 1], padding='SAME') #移动步长为1, 使用全0填充  
relu2 = tf.nn.relu( tf.nn.bias_add(conv2, conv2_biases) )  

#第四层:最大池化层  
#池化层过滤器的大小为2*2, 移动步长为2,使用全0填充  
pool2 = tf.nn.max_pool(relu2, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME')  
  
#第五层:全连接层  
fc1_weights = tf.get_variable("fc1_weights", [7 * 7 * 64, 1024], initializer=tf.truncated_normal_initializer(stddev=0.1)) #7*7*64=3136把前一层的输出变成特征向量  
fc1_baises = tf.get_variable("fc1_baises", [1024], initializer=tf.constant_initializer(0.1))  
pool2_vector = tf.reshape(pool2, [-1, 7 * 7 * 64])  
fc1 = tf.nn.relu(tf.matmul(pool2_vector, fc1_weights) + fc1_baises)  
  
#为了减少过拟合,加入Dropout层  
keep_prob = tf.placeholder(tf.float32,name="keep_prob") 
fc1_dropout = tf.nn.dropout(fc1, keep_prob)  

#第六层:全连接层  
fc2_weights = tf.get_variable("fc2_weights", [1024, 10], initializer=tf.truncated_normal_initializer(stddev=0.1)) #神经元节点数1024, 分类节点10  
fc2_biases = tf.get_variable("fc2_biases", [10], initializer=tf.constant_initializer(0.1))  
fc2 = tf.matmul(fc1_dropout, fc2_weights) + fc2_biases  
  
#第七层:输出层  
# softmax  
y_conv = tf.nn.softmax(fc2,name="y_conv")  
y_conv_labels = tf.argmax(y_conv,1,name='y_conv_labels')
#定义交叉熵损失函数  
y_conv = tf.clip_by_value(y_conv,1e-4,1.99)
cross_entropy = tf.reduce_mean(-tf.reduce_sum(y_ * tf.log(y_conv), reduction_indices=[1]))  
  
#选择优化器,并让优化器最小化损失函数/收敛, 反向传播  
train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)  
  
# tf.argmax()返回的是某一维度上其数据最大所在的索引值,在这里即代表预测值和真实值  
# 判断预测值y和真实值y_中最大数的索引是否一致,y的值为1-10概率  
correct_prediction = tf.equal(y_conv_labels, tf.argmax(y_,1))  
  
# 用平均值来统计测试准确率  
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32),name="accuracy")  

def convert2onehot(data):
    # covert data to onehot representation
    return pd.get_dummies(data)

file_path = "./1CNN/mnistcnn/datas/train.csv"
df_data = pd.read_csv(file_path, sep=",", header="infer")
np_data = df_data.values
trainx = np_data[:, 1:]/255
trainy = convert2onehot(np_data[:, 0]).values

with tf.Session() as sess:

    #开始训练  
    srun = sess.run
    srun(tf.global_variables_initializer())
    saver = tf.train.Saver()
    
    for i in range(6001):  
        start_step = i*100 % 42000
        stop_step = start_step+100

        batch_x, batch_y = trainx[start_step:stop_step], trainy[start_step:stop_step]
        srun(train_step,feed_dict={x: batch_x, y_: batch_y, keep_prob: 0.5}) #训练阶段使用50%的Dropout  
        if i%100 == 0:  
            train_accuracy = srun(accuracy,feed_dict={x:batch_x, y_: batch_y, keep_prob: 1.0}) #评估阶段不使用Dropout  
            print("step %d, training accuracy %f" % (i, train_accuracy))  
            saver_path = saver.save(sess, "./1CNN/mnistcnn/ckpt/my_model.ckpt",global_step=i)  # 将模型保存到save/model.ckpt文件

    
    #print("W1:", sess.run(conv1_weights)) # 打印v1、v2的值一会读取之后对比
    #print("W2:", sess.run(conv1_biases))

    print("Model saved in file:", saver_path)
    
    #在测试数据上测试准确率  
    print("test accuracy %g" % srun(accuracy,feed_dict={x: trainx, y_: trainy, keep_prob: 1.0}))  
    print("test accuracy %g" % srun(accuracy,feed_dict={x: mnist.test.images, y_: mnist.test.labels, keep_prob: 1.0}))  

运行结果:

...
step 5800, training accuracy 1.000000
step 5900, training accuracy 0.990000
step 6000, training accuracy 1.000000
Model saved in file: ./1CNN/mnistcnn/ckpt/my_model.ckpt-6000
test accuracy 0.998571
test accuracy 0.9958
  • 模型加载与复用

app文件:

import os
os.environ["KMP_DUPLICATE_LIB_OK"]="TRUE"
import tensorflow as tf
import pandas as pd


file_path = "./1CNN/mnistcnn/datas/test.csv"
df_data = pd.read_csv(file_path, sep=",", header="infer")
np_data = df_data.values
testx = np_data[:, :]/255

file_path1 = "./1CNN/mnistcnn/datas/sample_submission.csv"
df_data1 = pd.read_csv(file_path1, sep=",", header="infer")

print(df_data1.head())
df_data1.drop(labels="Label",axis = 1,inplace=True)
print(df_data1.head())

with tf.Session() as sess:    
    #加载运算图
    saver = tf.train.import_meta_graph('./1CNN/mnistcnn/ckpt/my_model.ckpt-6000.meta')
    #加载参数
    saver.restore(sess,tf.train.latest_checkpoint('./1CNN/mnistcnn/ckpt'))
    graph = tf.get_default_graph()
    #导入输入接口
    x = graph.get_tensor_by_name("x:0")
    #导入输出接口
    y_ = graph.get_tensor_by_name("y_:0")

    keep_prob = graph.get_tensor_by_name("keep_prob:0")
    y_conv_labels = graph.get_tensor_by_name("y_conv_labels:0")

    y_conv_labels_val = sess.run(y_conv_labels,{x:testx[:],keep_prob:1.0})

    #进行预测
    print("y: ",y_conv_labels_val[:10])

    df_data1["Label"] = y_conv_labels_val
    print(df_data1.head())
    df_data1.to_csv(file_path1,columns=["ImageId","Label"],index=False)
    print("Ok")

运行结果:

 ImageId  Label
0        1      0
1        2      0
2        3      0
3        4      0
4        5      0
   ImageId
0        1
1        2
2        3
3        4
4        5

y:  [2 0 9 9 3 7 0 3 0 3]
   ImageId  Label
0        1      2
1        2      0
2        3      9
3        4      9
4        5      3
Ok
  • 结果分析

Kaagle平台结果

Your Best Entry 
You advanced 381 places on the leaderboard!

Your submission scored 0.98928, which is an improvement of your previous score of 0.98142. Great job!

通过这个cnn识别手写数字实战,加深了对于cnn的理解与运用能力。
使用TensorFlow模型参数保存与加载参考我的博文也使得代码应用更加灵活高效,条理也更加清晰了,推荐大家使用。

发布了168 篇原创文章 · 获赞 398 · 访问量 19万+
展开阅读全文

没有更多推荐了,返回首页

©️2019 CSDN 皮肤主题: Age of Ai 设计师: meimeiellie

分享到微信朋友圈

×

扫一扫,手机浏览