用CNN做垃圾分类，最后达到90准确度
CNN实现垃圾分类，包含降维、PCA
- 整体代码
-
- 导入包
- 导入图片
- 用ImageDataGenerator给CNN训练的每次epoch喂固定数量随机转换的图片，提高模型的鲁棒性和泛化能力
-
- 构建模型
- 模型总结
- 训练模型
- Testing PREDICTION
-
- Accuracy Graph
- Improve
-
- 可选改进（不一定有效）
-
- 将图片灰度化
- PCA降维
整体代码
导入包
import numpy as np
import cv2
from keras.callbacks import ModelCheckpoint,EarlyStopping
from keras.layers import Conv2D, Flatten, MaxPooling2D,Dense,Dropout,SpatialDropout2D
from keras.models import Sequential
from keras.preprocessing.image import ImageDataGenerator, img_to_array, load_img, array_to_img
import random,os,glob
import matplotlib.pyplot as plt
导入图片
dir_path = './Garbage classification/Garbage classification'
img_list = glob.glob(os.path.join(dir_path, '*/*.jpg'))
len(img_list)
用ImageDataGenerator给CNN训练的每次epoch喂固定数量随机转换的图片，提高模型的鲁棒性和泛化能力
train=ImageDataGenerator(horizontal_flip=True,
vertical_flip=True,
validation_split=0.1,
rescale=1./255,
shear_range = 0.1,
zoom_range = 0.1,
width_shift_range = 0.1,
height_shift_range = 0.1,)
test=ImageDataGenerator(rescale=1/255,
validation_split=0.1)
train_generator=train.flow_from_directory(dir_path,
target_size=(300,300),
batch_size=32,
class_mode='categorical',
subset='training')
test_generator=test.flow_from_directory(dir_path,
target_size=(300,300),
batch_size=32,
class_mode='categorical',
subset='validation')
labels = (train_generator.class_indices)
print(labels)
for image_batch, label_batch in train_generator:
break
image_batch.shape, label_batch.shape
print (train_generator.class_indices)
Labels = '\n'.join(sorted(train_generator.class_indices.keys()))
with open('labels.txt', 'w') as f:
f.write(Labels)
构建模型
model=Sequential()
#Convolution blocks
model.add(Conv2D(32,(3,3), padding='same',input_shape=(300,300,3),activation='relu'))
model.add(MaxPooling2D(pool_size=2))
#model.add(SpatialDropout2D(0.5)) # No accuracy
model.add(Conv2D(64,(3,3), padding='same',activation='relu'))
model.add(MaxPooling2D(pool_size=2))
#model.add(SpatialDropout2D(0.5))
model.add(Conv2D(32,(3,3), padding='same',activation='relu'))
model.add(MaxPooling2D(pool_size=2))
#Classification layers
model.add(Flatten())
model.add(Dense(64,activation='relu'))
#model.add(SpatialDropout2D(0.5))
model.add(Dropout(0.2))
model.add(Dense(32,activation='relu'))
model.add(Dropout(0.2))
model.add(Dense(6,activation='softmax'))
filepath="trained_model.h5"
checkpoint1 = ModelCheckpoint(filepath, monitor='val_acc', verbose=1, save_best_only=True, mode='max')
callbacks_list = [checkpoint1]
模型总结
model.summary()
训练模型
Compiling Model using categorical cross entropy loss function & Adam Optimizer
model.compile(loss='categorical_crossentropy',
optimizer='adam',
metrics=['acc']) # RMS PROP - No accuracy
#es=EarlyStopping(monitor='val_loss', mode='min', verbose=1, patience=50)
history = model.fit_generator(train_generator,
epochs=100,
steps_per_epoch=2276//32,
validation_data=test_generator,
validation_steps=251//32,
workers = 4,
callbacks=callbacks_list)
#41 epoch - 75% #73- 76.9%
#78 epoch - 80%
Testing PREDICTION
from keras.preprocessing import image
img_path = './Garbage classification/Garbage classification/plastic/plastic75.jpg'
img = image.load_img(img_path, target_size=(300, 300))
img = image.img_to_array(img, dtype=np.uint8)
img=np.array(img)/255.0
plt.title("Loaded Image")
plt.axis('off')
plt.imshow(img.squeeze())
p=model.predict(img[np.newaxis, ...])
#print("Predicted shape",p.shape)
print("Maximum Probability: ",np.max(p[0], axis=-1))
predicted_class = labels[np.argmax(p[0], axis=-1)]
print("Classified:",predicted_class)
classes=[]
prob=[]
print("\n-------------------Individual Probability--------------------------------\n")
for i,j in enumerate (p[0],0):
print(labels[i].upper(),':',round(j*100,2),'%')
classes.append(labels[i])
prob.append(round(j*100,2))
def plot_bar_x():
# this is for plotting purpose
index = np.arange(len(classes))
plt.bar(index, prob)
plt.xlabel('Labels', fontsize=12)
plt.ylabel('Probability', fontsize=12)
plt.xticks(index, classes, fontsize=12, rotation=20)
plt.title('Probability for loaded image')
plt.show()
plot_bar_x()
Accuracy Graph
acc = history.history['acc']
val_acc = history.history['val_acc']
loss = history.history['loss']
val_loss = history.history['val_loss']
# ________________ Graph 1 -------------------------
plt.figure(figsize=(8, 8))
plt.subplot(2, 1, 1)
plt.plot(acc, label='Training Accuracy')
plt.plot(val_acc, label='Validation Accuracy')
plt.legend(loc='lower right')
plt.ylabel('Accuracy')
plt.ylim([min(plt.ylim()),1])
plt.title('Training and Validation Accuracy')
# ________________ Graph 2 -------------------------
plt.subplot(2, 1, 2)
plt.plot(loss, label='Training Loss')
plt.plot(val_loss, label='Validation Loss')
plt.legend(loc='upper right')
plt.ylabel('Cross Entropy')
plt.ylim([0,max(plt.ylim())])
plt.title('Training and Validation Loss')
plt.show()
Improve
改用自适应的Nadam优化器，并加上earlyStopping
model.compile(loss='categorical_crossentropy',
optimizer='Nadam',
metrics=['acc'])
history1 = model.fit(train_generator,
epochs=100,
steps_per_epoch=2276//32,
validation_data=test_generator,
validation_steps=251//32,
workers = 4,
callbacks=callbacks_list)
earlyStopping = EarlyStopping(monitor='acc', patience=20, verbose=1, mode='max')
acc = history1.history['acc']
val_acc = history1.history['val_acc']
loss = history1.history['loss']
val_loss = history1.history['val_loss']
# ________________ Graph 1 -------------------------
plt.figure(figsize=(8, 8))
plt.subplot(2, 1, 1)
plt.plot(acc, label='Training Accuracy')
plt.plot(val_acc, label='Validation Accuracy')
plt.legend(loc='lower right')
plt.ylabel('Accuracy')
plt.ylim([min(plt.ylim()),1])
plt.title('Training and Validation Accuracy')
# ________________ Graph 2 -------------------------
plt.subplot(2, 1, 2)
plt.plot(loss, label='Training Loss')
plt.plot(val_loss, label='Validation Loss')
plt.legend(loc='upper right')
plt.ylabel('Cross Entropy')
plt.ylim([0,max(plt.ylim())])
plt.title('Training and Validation Loss')
plt.show()
可选改进（不一定有效）
将图片灰度化
char_list = os.listdir("./Garbage classification/Garbage classification/")
print(char_list)
x = np.ones((2527,300,300))
y = []
x_index = 0
for index in range(0, len(char_list)):
image_list = os.listdir("./Garbage classification/Garbage classification/" + char_list[index])
print(os.path.join("./Garbage classification/Garbage classification/", char_list[index]))
for image in image_list:
img = io.imread(os.path.join("./Garbage classification/Garbage classification/", char_list[index],image))
reader = skimage.transform.resize(img, (300, 300))
item_gray = color.rgb2gray(reader)
item_gray = feature.canny(item_gray, sigma=3)
item_gray = morphology.dilation(item_gray)
x[x_index] = item_gray
y.append(index)
x_index = x_index + 1
PCA降维
import numpy as np
import os
from PIL import Image, ImageOps
import random
import scipy.io
import imageio
dir_path = os.path.join('E:/MLPRO/Garbage classification/Garbage classification/paper')
def PCA_Jittering(path):
img_list = os.listdir(path)
img_num = len(img_list)
for i in range(img_num):
img_path = os.path.join(path, img_list[i])
img = Image.open(img_path)
img = np.asanyarray(img, dtype = 'float32')
img = img / 255.0
img_size = img.size // 3 #转换为单通道
img1 = img.reshape(img_size, 3)
img1 = np.transpose(img1) #转置
img_cov = np.cov([img1[0], img1[1], img1[2]]) #协方差矩阵
lamda, p = np.linalg.eig(img_cov) #得到上述协方差矩阵的特征向量和特征值
#p是协方差矩阵的特征向量
p = np.transpose(p) #转置回去
#生成高斯随机数********可以修改
alpha1 = random.gauss(0,3)
alpha2 = random.gauss(0,3)
alpha3 = random.gauss(0,3)
#lamda是协方差矩阵的特征值
v = np.transpose((alpha1*lamda[0], alpha2*lamda[1], alpha3*lamda[2])) #转置
#得到主成分
add_num = np.dot(p,v)
#在原图像的基础上加上主成分
img2 = np.array([img[:,:,0]+add_num[0], img[:,:,1]+add_num[1], img[:,:,2]+add_num[2]])
#现在是BGR，要转成RBG再进行保存
img2 = np.swapaxes(img2,0,2)
img2 = np.swapaxes(img2,0,1)
img2 = (img2 * 255).astype(np.uint8)
save_name = 'paper'+str(i)+'.jpg'
save_path = os.path.join('E:/MLPRO/Garbage classification/Garbage classification/new_paper', save_name)
imageio.imsave(save_path,img2)
#plt.imshow(img2)
#plt.show()
PCA_Jittering(dir_path)
model=Sequential()
#Convolution blocks
model.add(Conv2D(32,(3,3), padding='same',input_shape=(300,300,1),activation='relu'))
model.add(MaxPooling2D(pool_size=2))
#model.add(SpatialDropout2D(0.5)) # No accuracy
model.add(Conv2D(64,(3,3), padding='same',activation='relu'))
model.add(MaxPooling2D(pool_size=2))
#model.add(SpatialDropout2D(0.5))
model.add(Conv2D(32,(3,3), padding='same',activation='relu'))
model.add(MaxPooling2D(pool_size=2))
#Classification layers
model.add(Flatten())
model.add(Dense(64,activation='relu'))
#model.add(SpatialDropout2D(0.5))
model.add(Dropout(0.2))
model.add(Dense(32,activation='relu'))
model.add(Dropout(0.2))
model.add(Dense(6,activation='softmax'))
filepath="trained_model.h5"
checkpoint1 = ModelCheckpoint(filepath, monitor='val_acc', verbose=1, save_best_only=True, mode='max')
callbacks_list = [checkpoint1,es]