TensorFlow框架下cnn卷积神经网络识别花卉
识别过程
1、第一步在网络上搜索与CNN卷积神经网络识别花卉的相关信息，这里你必定能找到相关的花卉数据集数据集，网上下的花卉数据集大概有3670张图片，分为菊花，郁金香，玫瑰，蒲公英，和向日葵
2、大致过程都一样，跟网上各位大牛的差不多（本人一名大二学生，刚接触不久，但也还算了解吧），导入数据，就是你下的哪些数据集
3、设置相关参数，n_epoch，banch_size什么的。训练模型后保存模型，然后拉出来训练了。
本文仅供参考，网上太多这个了，但是他们的测试结果我觉得并不真实，我自己亲身做过，参考过几篇不错的博主文章，文章后供给大家，以供参考。
**以下这段属于训练并保存模型的代码** import os os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2' 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= 'G:/人工智能/第二次花卉识别/花卉数据集/' #模型保存地址 model_path='G:/人工智能/第二次花卉识别/保存模型' #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') #可以避免生成大量常量来提供输入数据，提高了计算图的利用率（占位符的好处） 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=10 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()
123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181**调用训练好的模型** import os os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2' from skimage import io,transform import tensorflow as tf import numpy as np path1 = "G:/人工智能/第二次花卉识别/测试样本1/daisy/2617111535_54c2ac8462.jpg" path2 = "G:/人工智能/第二次花卉识别/测试样本1/dandelion/479495978_ee22cf05be.jpg" path3 = "G:/人工智能/第二次花卉识别/测试样本1/roses/2065522422_cfdd80044a_n.jpg" path4 = "G:/人工智能/第二次花卉识别/测试样本1/sunflowers/1379256773_bb2eb0d95b_n.jpg" path5 = "G:/人工智能/第二次花卉识别/测试样本1/tulips/444963906_e41492b692.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('G:/人工智能/第二次花卉识别/保存模型.meta') saver.restore(sess,tf.train.latest_checkpoint('G:/人工智能/第二次花卉识别/')) 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训练模型的测试结果如下
开始训练时的截图
测试结果图
网上大多的结果感觉都很勉强，实际测试的结果太让我失望了，但看了其他的博客，都很不真实，毕竟训练的花卉图片只有3000多张（3670张），根本不够，如果你会用Python爬虫的话，可以自己去网上爬取更多的花卉图片，感觉测试用的图片都是在网上爬取，我对爬虫不是很擅长，这里就不给各位介绍了。
训练后保存的模型
##https://blog.csdn.net/qq_41789503/article/details/88960305 详解文件存放路径————（花卉数据集就在这上边，下载之后就是下边这个样子了）
https://blog.csdn.net/mao_hui_fei/article/details/84801620 代码所在网址
最后注明一下，这篇文章大部分都是借鉴CSDN博客上的大牛的，如有侵权请及时指出，谢谢
过程都是经过我自己亲自实践过的，代码自己也该多参数，但结果是真的不准确，人工智障的那种，改过几次了，都还是不行，自己个人觉得主要与样本数量太少有关，毕竟手写数字识别的数据库（minist）都有6万张，这个样本数确实太少了。
还有什么要补充的呢？让我想想，你们自己做的时候别把那个文件路径搞错吧，我自己就搞错了，哈哈哈。
运行的环境的：
GPU处理器
Python 3.5
安装的是TensorFlow1.12.0
相关知识
TensorFlow框架下cnn卷积神经网络识别花卉
深度学习之基于Tensorflow卷积神经网络花卉识别系统
几个卷积神经网络（CNN）可视化的网站
满满干货！一文快速实现CNN(卷积神经网络)识别花朵
基于TensorFlow实现的CNN神经网络 花卉识别系统Demo
花卉识别(tensorflow)
基于深度卷积神经网络的移动端花卉识别系统
基于卷积神经网络的花卉图像分类研究（32页）
基于卷积神经网络的花卉识别技术 Flower Recognition Based on Convolutional Neural Networks
CNN卷积神经网络：花卉分类
网址: TensorFlow框架下cnn卷积神经网络识别花卉 https://m.huajiangbk.com/newsview375778.html
| 上一篇: sklearn |
下一篇: 这8种“入侵植物”，在国外泛滥成 |
