Tensorflow五种花卉分类

train.py

from skimage import io,transform
import glob
import os
import tensorflow as tf
import numpy as np
import time
import matplotlib.pyplot as plt

#数据集地址
path='D:\date_1\\flowers\\'
#模型保存地址
model_path='D:\model_1\\model.ckpt\\'

#将所有的图片resize成100*100
w=100          #宽
h=100          #高
c=3            #通道数

#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),mode='constant')
            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  训练集（train)优化、验证集（validation）人工处理参数调整  和测试集（test）不经过处理
ratio=0.8
s=np.int(num_example*ratio)
x_train=data[:s]             #训练集%80 验证集20%
y_train=label[:s]
x_val=data[s:]
y_val=label[s:]

#-----------------构建网络----------------------
#占位符
tf.reset_default_graph()
#定义一个容器 存放图像数据
x=tf.placeholder(tf.float32,shape=[None,w,h,c],name='x')   #参数有 数据类型 数据形状 名称  
y_=tf.placeholder(tf.int32,shape=[None,],name='y_')

#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。
#卷积层提取特征 池化层对输入的特征图进行压缩，一方面使特征图变小，简化网络计算复杂度；一方面进行特征压缩，提取主要特征
#全连接层连接所有的特征，将输出值送给分类器（如softmax分类器）
def inference(input_tensor, train, regularizer):  #  张量  训练  正则化
    with tf.variable_scope('layer1-conv1'):
        #卷积核5x5 输入通道3个 输出通道32个
        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')
        #激活relu非线性处理
        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    交叉熵计算损失
n_epoch=5          #训练次数                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        
batch_size=64        #批处理参数  训练集样本总数  
saver=tf.train.Saver()             #定义模型保存器/载入器
sess=tf.Session()  
sess.run(tf.global_variables_initializer())
fig_loss = np.zeros([n_epoch])
fig_acc1 = np.zeros([n_epoch])
fig_acc2= np.zeros([n_epoch])
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))
    fig_loss[epoch] = np.sum(train_loss)/ n_batch
    fig_acc1[epoch] = 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))
    fig_acc2[epoch] = np.sum(val_acc) / n_batch
# 训练loss图
fig, ax1 = plt.subplots()
lns1 = ax1.plot(np.arange(n_epoch), fig_loss, label="Loss")
ax1.set_xlabel('iteration')
ax1.set_ylabel('training loss')

# 训练和验证两种准确率曲线图放在一张图中
fig2, ax2 = plt.subplots()
ax3 = ax2.twinx()#由ax2图生成ax3图
lns2 = ax2.plot(np.arange(n_epoch), fig_acc1, label="Loss")
lns3 = ax3.plot(np.arange(n_epoch), fig_acc2, label="Loss")

ax2.set_xlabel('iteration')
ax2.set_ylabel('training acc')
ax3.set_ylabel('val acc')
   # 合并图例
lns = lns3 + lns2
labels = ["train acc", "val acc"]
plt.legend(lns, labels, loc=7)

plt.show()
saver.save(sess,model_path)    
sess.close()

predict.py

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

path1 = "D:\date_1\\flowers\\tulip\\8838983024_5c1a767878_n.jpg"
path2 = "D:\date_1\\flowers\\sunflower\\4895721242_89014e723c_n.jpg"
path3 = "D:\date_1\\flowers\\rose\\475947979_554062a608_m.jpg"
path4 = "D:\date_1\\flowers\\dandelion\\5749815755_12f9214649_n.jpg"
path5 = "D:\date_1\\flowers\\daisy\\286875003_f7c0e1882d.jpg"
path=[path1,path2,path3,path4,path5]
flower_dict = {0:'dasiy',1:'dandelion',2:'rose',3:'sunflower',4:'tulip'}

w=100
h=100
c=3

def read_one_image(path):
    img = io.imread(path)
    img = transform.resize(img,(w,h),mode='constant')
    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('D:\model_1\\model.ckpt\\.meta')
    saver.restore(sess,tf.train.latest_checkpoint('D:\model_1\\'))

    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]]+"-----"+"原图像路径："+path[i])