一、CNN訓練模型

模型尺寸分析：卷積層全都采用了補0，所以經過卷積層長和寬不變，只有深度加深。池化層全都沒有補0，所以經過池化層長和寬均減小，深度不變。http://download.tensorflow.org/example_images/flower_photos.tgz

模型尺寸變化：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訓練代碼如下：

?

123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174

from skimage import io,transformimport globimport osimport tensorflow as tfimport numpy as npimport time#數據集地址path='E:/data/datasets/flower_photos/'#模型保存地址model_path='E:/data/model/flower/model.ckpt'#將所有的圖片resize成100*100w=100h=100c=3#讀取圖片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)#打亂順序num_example=data.shape[0]arr=np.arange(num_example)np.random.shuffle(arr)data=data[arr]label=label[arr]#將所有數據分為訓練集和驗證集ratio=0.8s=np.int(num_example*ratio)x_train=data[:s]y_train=label[:s]x_val=data[s:]y_val=label[s:]#-----------------構建網絡----------------------#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#---------------------------網絡結束---------------------------regularizer = tf.contrib.layers.l2_regularizer(0.0001)logits = inference(x,False,regularizer)#(小處理)將logits乘以1賦值給logits_eval，定義name，方便在后續調用模型時通過tensor名字調用輸出tensorb = 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))#定義一個函數，按批次取數據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]#訓練和測試數據，可將n_epoch設置更大一些n_epoch=10??????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????batch_size=64saver=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()

二、調用模型進行預測

調用模型進行花卉的預測，代碼如下：

?

12345678910111213141516171819202122232425262728293031323334353637383940414243444546474849505152535455

from skimage import io,transformimport tensorflow as tfimport numpy as nppath1 = "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=100h=100c=3def 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)????#打印出預測矩陣????print(classification_result)????#打印出預測矩陣每一行最大值的索引????print(tf.argmax(classification_result,1).eval())????#根據索引通過字典對應花的分類????output = []????output = tf.argmax(classification_result,1).eval()????for i in range(len(output)):????????print("第",i+1,"朵花預測:"+flower_dict[output[i]])

運行結果：

?

1234567891011

[[? 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 朵花預測:dasiy第 2 朵花預測:dandelion第 3 朵花預測:roses第 4 朵花預測:sunflowers第 5 朵花預測:tulips

預測結果和調用模型代碼中的五個路徑相比較是完全準確的。

本文的模型對于花卉的分類準確率大概在70%左右，采用遷移學習調用Inception-v3模型對本文中的花卉數據集分類準確率在95%左右。主要的原因在于本文的CNN模型較于簡單，而且花卉數據集本身就比mnist手寫數字數據集分類難度就要大一點，同樣的模型在mnist手寫數字的識別上準確率要比花卉數據集準確率高不少。

總結

以上是生活随笔為你收集整理的CNN训练模型 花卉的全部內容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網站內容還不錯，歡迎將生活随笔推薦給好友。