CNN訓練模型花卉

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：

?
from skimage import io,transform
import glob
import os
import tensorflow as tf
import numpy as np
import 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*100
w=100
h=100
c=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=0.8
s=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=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()

二、調用模型進行預測

調用模型進行花卉的預測，代碼如下：

?
from skimage import io,transform
import tensorflow as tf
import numpy as np
path1 = "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=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('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：

?
[[? 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。