tensorflow 1.0 学习：用CNN进行图像分类

Posted 2020-09-21 denny的学习专栏

tensorflow升级到1.0之后，增加了一些高级模块： 如tf.layers, tf.metrics, 和tf.losses，使得代码稍微有些简化。

任务：花卉分类

版本：tensorflow 1.0

数据：http://download.tensorflow.org/example_images/flower_photos.tgz

花总共有五类，分别放在5个文件夹下。

闲话不多说，直接上代码，希望大家能看懂：）

 

# -*- coding: utf-8 -*-

from skimage import io,transform
import glob
import os
import tensorflow as tf
import numpy as np
import time

path=‘e:/flower/‘

#将所有的图片resize成100*100
w=100
h=100
c=3


#读取图片
def read_img(path):
    cate=[path+x for x in os.listdir(path) if os.path.isdir(path+x)]
    imgs=[]
    labels=[]
    for idx,folder in enumerate(cate):
        for im in glob.glob(folder+‘/*.jpg‘):
            print(‘reading the images:%s‘%(im))
            img=io.imread(im)
            img=transform.resize(img,(w,h))
            imgs.append(img)
            labels.append(idx)
    return np.asarray(imgs,np.float32),np.asarray(labels,np.int32)
data,label=read_img(path)


#打乱顺序
num_example=data.shape[0]
arr=np.arange(num_example)
np.random.shuffle(arr)
data=data[arr]
label=label[arr]


#将所有数据分为训练集和验证集
ratio=0.8
s=np.int(num_example*ratio)
x_train=data[:s]
y_train=label[:s]
x_val=data[s:]
y_val=label[s:]

#-----------------构建网络----------------------
#占位符
x=tf.placeholder(tf.float32,shape=[None,w,h,c],name=‘x‘)
y_=tf.placeholder(tf.int32,shape=[None,],name=‘y_‘)

#第一个卷积层（100——>50)
net=tf.layers.conv2d(
      inputs=x,
      filters=32,
      kernel_size=[5, 5],
      padding="same",
      activation=tf.nn.relu)
net=tf.layers.max_pooling2d(inputs=net, pool_size=[2, 2], strides=2)

#第二个卷积层(50->25)
net=tf.layers.conv2d(
      inputs=net,
      filters=64,
      kernel_size=[5, 5],
      padding="same",
      activation=tf.nn.relu)
net=tf.layers.max_pooling2d(inputs=net, pool_size=[2, 2], strides=2)

#第三个卷积层(25->12)
net=tf.layers.conv2d(
      inputs=net,
      filters=128,
      kernel_size=[3, 3],
      padding="same",
      activation=tf.nn.relu)
net=tf.layers.max_pooling2d(inputs=net, pool_size=[2, 2], strides=2)

#第四个卷积层(12->6)
net=tf.layers.conv2d(
      inputs=net,
      filters=128,
      kernel_size=[3, 3],
      padding="same",
      activation=tf.nn.relu)
net=tf.layers.max_pooling2d(inputs=net, pool_size=[2, 2], strides=2)

net = tf.reshape(net, [-1, 6 * 6 * 128])

#全连接层
net = tf.layers.dense(inputs=net, units=1024, activation=tf.nn.relu)
net = tf.layers.dense(inputs=net, units=512, activation=tf.nn.relu)
logits= tf.layers.dense(inputs=net, units=5, activation=None)

#---------------------------网络结束---------------------------

loss=tf.losses.sparse_softmax_cross_entropy(labels=y_,logits=logits)
train_op=tf.train.AdamOptimizer(learning_rate=0.001).minimize(loss)
correct_prediction = tf.equal(tf.cast(tf.argmax(logits,1),tf.int32), y_)    
acc= tf.reduce_mean(tf.cast(correct_prediction, tf.float32))


#定义一个函数，按批次取数据
def minibatches(inputs=None, targets=None, batch_size=None, shuffle=False):
    assert len(inputs) == len(targets)
    if shuffle:
        indices = np.arange(len(inputs))
        np.random.shuffle(indices)
    for start_idx in range(0, len(inputs) - batch_size + 1, batch_size):
        if shuffle:
            excerpt = indices[start_idx:start_idx + batch_size]
        else:
            excerpt = slice(start_idx, start_idx + batch_size)
        yield inputs[excerpt], targets[excerpt]


#训练和测试数据，可将n_epoch设置更大一些

n_epoch=10
batch_size=64
sess=tf.InteractiveSession()  
sess.run(tf.global_variables_initializer())
for epoch in range(n_epoch):
    start_time = time.time()
    
    #training
    train_loss, train_acc, n_batch = 0, 0, 0
    for x_train_a, y_train_a in minibatches(x_train, y_train, batch_size, shuffle=True):
        _,err,ac=sess.run([train_op,loss,acc], feed_dict={x: x_train_a, y_: y_train_a})
        train_loss += err; train_acc += ac; n_batch += 1
    print("   train loss: %f" % (train_loss/ n_batch))
    print("   train acc: %f" % (train_acc/ n_batch))
    
    #validation
    val_loss, val_acc, n_batch = 0, 0, 0
    for x_val_a, y_val_a in minibatches(x_val, y_val, batch_size, shuffle=False):
        err, ac = sess.run([loss,acc], feed_dict={x: x_val_a, y_: y_val_a})
        val_loss += err; val_acc += ac; n_batch += 1
    print("   validation loss: %f" % (val_loss/ n_batch))
    print("   validation acc: %f" % (val_acc/ n_batch))

sess.close()