本文主要通过CNN进行花卉的分类,训练结束保存模型,最后通过调用模型,输入花卉的图片通过模型来进行类别的预测。
测试平台:win 10+tensorflow 1.2
数据集:http://download.tensorflow.org/example_images/flower_photos.tgz
数据集中总共有五种花,分别放在五个文件夹下。
一、CNN训练模型
模型尺寸分析:卷积层全都采用了补0,所以经过卷积层长和宽不变,只有深度加深。池化层全都没有补0,所以经过池化层长和宽均减小,深度不变。
模型尺寸变化:100×100×3->100×100×32->50×50×32->50×50×64->25×25×64->25×25×128->12×12×128->12×12×128->6×6×128
CNN训练代码如下:
from skimage import io,transform
import glob
import os
import tensorflow as tf
import numpy as np
import time
#数据集地址
path='E:/data/datasets/flower_photos/'
#模型保存地址
model_path='E:/data/model/flower/model.ckpt'
#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_')
def inference(input_tensor, train, regularizer):
with tf.variable_scope('layer1-conv1'):
conv1_weights = tf.get_variable("weight",[5,5,3,32],initializer=tf.truncated_normal_initializer(stddev=0.1))
conv1_biases = tf.get_variable("bias", [32], initializer=tf.constant_initializer(0.0))
conv1 = tf.nn.conv2d(input_tensor, conv1_weights, strides=[1, 1, 1, 1], padding='SAME')
relu1 = tf.nn.relu(tf.nn.bias_add(conv1, conv1_biases))
with tf.name_scope("layer2-pool1"):
pool1 = tf.nn.max_pool(relu1, ksize = [1,2,2,1],strides=[1,2,2,1],padding="VALID")
with tf.variable_scope("layer3-conv2"):
conv2_weights = tf.get_variable("weight",[5,5,32,64],initializer=tf.truncated_normal_initializer(stddev=0.1))
conv2_biases = tf.get_variable("bias", [64], initializer=tf.constant_initializer(0.0))
conv2 = tf.nn.conv2d(pool1, conv2_weights, strides=[1, 1, 1, 1], padding='SAME')
relu2 = tf.nn.relu(tf.nn.bias_add(conv2, conv2_biases))
with tf.name_scope("layer4-pool2"):
pool2 = tf.nn.max_pool(relu2, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='VALID')
with tf.variable_scope("layer5-conv3"):
conv3_weights = tf.get_variable("weight",[3,3,64,128],initializer=tf.truncated_normal_initializer(stddev=0.1))
conv3_biases = tf.get_variable("bias", [128], initializer=tf.constant_initializer(0.0))
conv3 = tf.nn.conv2d(pool2, conv3_weights, strides=[1, 1, 1, 1], padding='SAME')
relu3 = tf.nn.relu(tf.nn.bias_add(conv3, conv3_biases))
with tf.name_scope("layer6-pool3"):
pool3 = tf.nn.max_pool(relu3, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='VALID')
with tf.variable_scope("layer7-conv4"):
conv4_weights = tf.get_variable("weight",[3,3,128,128],initializer=tf.truncated_normal_initializer(stddev=0.1))
conv4_biases = tf.get_variable("bias", [128], initializer=tf.constant_initializer(0.0))
conv4 = tf.nn.conv2d(pool3, conv4_weights, strides=[1, 1, 1, 1], padding='SAME')
relu4 = tf.nn.relu(tf.nn.bias_add(conv4, conv4_biases))
with tf.name_scope("layer8-pool4"):
pool4 = tf.nn.max_pool(relu4, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='VALID')
nodes = 6*6*128
reshaped = tf.reshape(pool4,[-1,nodes])
with tf.variable_scope('layer9-fc1'):
fc1_weights = tf.get_variable("weight", [nodes, 1024],
initializer=tf.truncated_normal_initializer(stddev=0.1))
if regularizer != None: tf.add_to_collection('losses', regularizer(fc1_weights))
fc1_biases = tf.get_variable("bias", [1024], initializer=tf.constant_initializer(0.1))
fc1 = tf.nn.relu(tf.matmul(reshaped, fc1_weights) + fc1_biases)
if train: fc1 = tf.nn.dropout(fc1, 0.5)
with tf.variable_scope('layer10-fc2'):
fc2_weights = tf.get_variable("weight", [1024, 512],
initializer=tf.truncated_normal_initializer(stddev=0.1))
if regularizer != None: tf.add_to_collection('losses', regularizer(fc2_weights))
fc2_biases = tf.get_variable("bias", [512], initializer=tf.constant_initializer(0.1))
fc2 = tf.nn.relu(tf.matmul(fc1, fc2_weights) + fc2_biases)
if train: fc2 = tf.nn.dropout(fc2, 0.5)
with tf.variable_scope('layer11-fc3'):
fc3_weights = tf.get_variable("weight", [512, 5],
initializer=tf.truncated_normal_initializer(stddev=0.1))
if regularizer != None: tf.add_to_collection('losses', regularizer(fc3_weights))
fc3_biases = tf.get_variable("bias", [5], initializer=tf.constant_initializer(0.1))
logit = tf.matmul(fc2, fc3_weights) + fc3_biases
return logit
#---------------------------网络结束---------------------------
regularizer = tf.contrib.layers.l2_regularizer(0.0001)
logits = inference(x,False,regularizer)
#(小处理)将logits乘以1赋值给logits_eval,定义name,方便在后续调用模型时通过tensor名字调用输出tensor
b = tf.constant(value=1,dtype=tf.float32)
logits_eval = tf.multiply(logits,b,name='logits_eval')
loss=tf.nn.sparse_softmax_cross_entropy_with_logits(logits=logits, labels=y_)
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
saver=tf.train.Saver()
sess=tf.Session()
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" % (np.sum(train_loss)/ n_batch))
print(" train acc: %f" % (np.sum(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" % (np.sum(val_loss)/ n_batch))
print(" validation acc: %f" % (np.sum(val_acc)/ n_batch))
saver.save(sess,model_path)
sess.close()123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177
二、调用模型进行预测
调用模型进行花卉的预测,代码如下:
from skimage import io,transform
import tensorflow as tf
import numpy as np
path1 = "E:/data/datasets/flower_photos/daisy/5547758_eea9edfd54_n.jpg"
path2 = "E:/data/datasets/flower_photos/dandelion/7355522_b66e5d3078_m.jpg"
path3 = "E:/data/datasets/flower_photos/roses/394990940_7af082cf8d_n.jpg"
path4 = "E:/data/datasets/flower_photos/sunflowers/6953297_8576bf4ea3.jpg"
path5 = "E:/data/datasets/flower_photos/tulips/10791227_7168491604.jpg"
flower_dict = {0:'dasiy',1:'dandelion',2:'roses',3:'sunflowers',4:'tulips'}
w=100
h=100
c=3
def read_one_image(path):
img = io.imread(path)
img = transform.resize(img,(w,h))
return np.asarray(img)
with tf.Session() as sess:
data = []
data1 = read_one_image(path1)
data2 = read_one_image(path2)
data3 = read_one_image(path3)
data4 = read_one_image(path4)
data5 = read_one_image(path5)
data.append(data1)
data.append(data2)
data.append(data3)
data.append(data4)
data.append(data5)
saver = tf.train.import_meta_graph('E:/data/model/flower/model.ckpt.meta')
saver.restore(sess,tf.train.latest_checkpoint('E:/data/model/flower/'))
graph = tf.get_default_graph()
x = graph.get_tensor_by_name("x:0")
feed_dict = {x:data}
logits = graph.get_tensor_by_name("logits_eval:0")
classification_result = sess.run(logits,feed_dict)
#打印出预测矩阵
print(classification_result)
#打印出预测矩阵每一行最大值的索引
print(tf.argmax(classification_result,1).eval())
#根据索引通过字典对应花的分类
output = []
output = tf.argmax(classification_result,1).eval()
for i in range(len(output)):
print("第",i+1,"朵花预测:"+flower_dict[output[i]])
123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657
运行结果:
[[ 5.76620245 3.18228579 -3.89464641 -2.81310582 1.40294015]
[ -1.01490593 3.55570269 -2.76053429 2.93104005 -3.47138596]
[ -8.05292606 -7.26499033 11.70479774 0.59627819 2.15948296]
[ -5.12940931 2.18423128 -3.33257103 9.0591135 5.03963232]
[ -4.25288343 -0.95963973 -2.33347392 1.54485476 5.76069307]]
[0 1 2 3 4]
第 1 朵花预测:dasiy
第 2 朵花预测:dandelion
第 3 朵花预测:roses
第 4 朵花预测:sunflowers
第 5 朵花预测:tulips1234567891011
预测结果和调用模型代码中的五个路径相比较是完全准确的。
本文的模型对于花卉的分类准确率大概在70%左右,采用迁移学习调用Inception-v3模型对本文中的花卉数据集分类准确率在95%左右。主要的原因在于本文的CNN模型较于简单,而且花卉数据集本身就比mnist手写数字数据集分类难度就要大一点,同样的模型在mnist手写数字的识别上准确率要比花卉数据集准确率高不少。
本文的CNN模型完全可以通过增大模型复杂度或者改参数调试以及对图像进行预处理来提高准确率,但本文只是想记录一下最近的学习,这已经足够了。
参考博客:http://www.cnblogs.com/denny402/p/6931338.html
---------------------
作者:Enchanted_ZhouH
来源:CSDN
原文:https://blog.csdn.net/Enchanted_ZhouH/article/details/74116823
版权声明:本文为博主原创文章,转载请附上博文链接!