TensorFlow应用:识别花的种类

TensorFlow应用:识别花的种类

这是一篇非常基础的TensorFlow的CNN应用教程,示例代码实现了花的种类识别,你可以在这里看到图像集的训练、模型的保存和调用方法。

笔者在Win10+TensorFlow 1.8.0下运行通过,Win10上部署TF的方法:

首先需要下载好数据集:http://download.tensorflow.org/example_images/flower_photos.tgz

为了能成功一次跑起来请注意数据集保存路径以及文件中需要修改的地方笔者已添加“请自行修改”的字样

数据集的训练training.py,该文件实现了数据训练、模型的保存,哦对了,别忘了在该文件的目录下建个model目录用来存放模型。

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

#数据集地址,请自行修改
path='E:/TensorFlow/dataSets/flower_photos/'
#模型保存地址,请自行修改
model_path='E:/TensorFlow/Projects/TF-CNN/model/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()

预测predict.py,该文件实现了模型的调用及花儿类型预测

from skimage import io,transform
import tensorflow as tf
import numpy as np

#此处为要预测识别的测试图片,可图片搜索下载,请自行修改
path1 = "E:/TensorFlow/dataSets/flower_photos/daisy/5547758_eea9edfd54_n.jpg"
path2 = "E:/TensorFlow/dataSets/flower_photos/dandelion/7355522_b66e5d3078_m.jpg"
path3 = "E:/TensorFlow/dataSets/flower_photos/roses/394990940_7af082cf8d_n.jpg"
path4 = "E:/TensorFlow/dataSets/flower_photos/sunflowers/6953297_8576bf4ea3.jpg"
path5 = "E:/TensorFlow/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)

    #训练好的模型,请自行修改目录
    saver = tf.train.import_meta_graph('E:/TensorFlow/Projects/TF-CNN/model/model.ckpt.meta')
    saver.restore(sess,tf.train.latest_checkpoint('E:/TensorFlow/Projects/TF-CNN/model/'))

    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]])

将以上两个文件保存下来后修改相关路径配置后就可以运行了,先训练

python training.py

训练结果

   train loss: 1330.096962
   train acc: 0.323958
   validation loss: 86.252253
   validation acc: 0.409091
   train loss: 71.787370
   train acc: 0.529514
   validation loss: 78.465698
   validation acc: 0.545455
   train loss: 58.876704
   train acc: 0.628125
   validation loss: 73.999440
   validation acc: 0.549716
   train loss: 51.185135
   train acc: 0.690972
   validation loss: 71.450195
   validation acc: 0.553977
   train loss: 42.075136
   train acc: 0.752083
   validation loss: 73.619540
   validation acc: 0.572443
   train loss: 33.243433
   train acc: 0.812153
   validation loss: 73.291354
   validation acc: 0.583807
   train loss: 23.589171
   train acc: 0.879167
   validation loss: 83.940641
   validation acc: 0.562500
   train loss: 20.822868
   train acc: 0.888889
   validation loss: 82.642556
   validation acc: 0.607955
   train loss: 12.286841
   train acc: 0.941667
   validation loss: 89.398277
   validation acc: 0.596591
   train loss: 7.091239
   train acc: 0.970833
   validation loss: 95.333896
   validation acc: 0.620739

接下来预测

python predict.py

运行结果

[[10.594988    3.5799916  -8.448204   -3.8759303  -6.4648085 ]
 [-0.1714828   5.6841183  -2.7628996  -1.1280164   1.3521246 ]
 [-4.4547043  -4.8152595  11.268807   -4.099991    4.0173736 ]
 [-9.557638   -0.57269955 -5.8606277  12.746286    5.3812127 ]
 [-6.17485    -6.020256    4.201649    1.3861963  10.299406  ]]
[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:tulips

Read Comments

  • AI lover1 year ago1

    为什么我训练出来的loss 和acc都是nan值啊。。。。

    • julian1 year ago0

      你用的CPU还是GPU?

    • Julian1 year ago0

      参考我本地部署的Tf环境:https://towait.com/blog/install-anaconda-and-tensorflow-on-win10/
      我觉得可能跟您的运行环境有差异

Post Comment