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*128reshaped = 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_biasesreturn 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()#trainingtrain_loss, train_acc, n_batch = 0, 0, 0for 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 += 1print("   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_batchfig_acc1[epoch] = np.sum(train_acc) / n_batch#validationval_loss, val_acc, n_batch = 0, 0, 0for 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 += 1print("   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 nppath1 = "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=3def 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])

Tensorflow五种花卉分类相关推荐

7 Resnet深度残差网络实现102种花卉分类
Resnet(Deep residual network, ResNet),深度残差神经网络,卷积神经网络历史在具有划时代意义的神经网络.与Alexnet和VGG不同的是,网络结构上就有很大的改变,在 ...
【MYSQL】五种语言分类
文章目录一.DDL(Data Define Language) 数据定义语言二.DML(Data Manipulation Language) 数据操作语言三.DQL(Data Query La ...
CNN卷积神经网络：花卉分类
文章目录简介一.CNN卷积神经网络基础知识二.数据集介绍三.代码实现读取数据数据处理搭建网络训练网络测试网络保存网络结果展示总结简介本篇文章利用pytorch搭建CNN卷积 ...
Keras 和 Tensorflow 框架下五种视频分类
目前视频分类是机器学习模式中独树一帜的挑战.今天我们就要来看看在Keras 和 Tensorflow 框架下的不同的视频行为识别策略,我们将会学着如何使用五深度学习的模式去学习UCF101数据组,具体 ...
基于TensorFlow的CNN卷积网络模型花卉分类（1）
一.项目描述使用TensorFlow进行卷积神经网络实现花卉分类的项目,加载十种花分类,建立模型后进行预测分类图片环境:win10 +TensorFlow gpu 1.12.0+pycharm 训 ...
密码学–数字签名Digital Signature五种分类
密码学–数字签名Digital Signature五种分类基于数字签名用途的分类基于数学难题的分类基于密码体制的分类基于数字签名安全性的分类基于签名用户的个数分类 A. 基于数字签名用途的分 ...
基于TensorFlow的CNN卷积网络模型花卉分类GUI版（2）
一.项目描述 10类花的图片1100张,按{牡丹,月季,百合,菊花,荷花,紫荆花,梅花,-}标注,其中1000张作为训练样本,100张作为测试样本,设计一个CNN卷积神经网络花卉分类器进行花卉的分类, ...
五种便签分类方法,让你的事项清单一目了然
在工作过程中,会需要处理各种工作中的待办事项,当大量的任务事项堆叠在一起时,可能会让你感觉到压力山大,不知该从何处入手才好.其实,现在的应用市场中有一些好用便签工具,可辅助高效整理待办事项任务.这里就 ...
linux下的文件可以分为哪五种类型,LINUX系统文件类型分类
使用LINUX过程中,时常会对文件进行操作.但是linux中文件究竟有哪些分类呢?今天让我们大家来总结一下吧! 概述: linux文件可以分为五种类型,分别为:普通文件.目录.字符设备或块设备.套接口 ...

Tensorflow五种花卉分类

Tensorflow五种花卉分类相关推荐

最新文章

热门文章