【发布时间】：2020-01-05 08:19:02
【问题描述】：
我正在构建一个模型来检测太阳能电池板的缺陷。我正在使用 255*255 的图像来训练模型，我想使用混淆矩阵来改进我的模型。
矩阵给了我错误分类的图像，但我需要找出误报和误报图像的确切文件名
我怎样才能实现这个目标？
我在下面提供了我的代码：
import numpy as np
import os
import time
import keras
from keras.applications.resnet50 import preprocess_input
from keras.preprocessing import image
from keras.layers import GlobalAveragePooling2D, Dense, Dropout
#from keras.layers import GlobalAveragePooling2D, Dense, Dropout,Activation,Flatten
#from keras.layers import Input
from keras.models import Model
from keras.utils import np_utils
from sklearn.utils import shuffle
from sklearn.model_selection import train_test_split
from keras.layers import Input
from keras import models
from keras import layers
from keras import optimizers
from keras_applications.resnet import ResNet101
from keras.optimizers import SGD, Adagrad, Adadelta, RMSprop, Adam
from keras.callbacks import LearningRateScheduler
from keras.models import load_model
from keras import regularizers
from keras.preprocessing.image import ImageDataGenerator, array_to_img, img_to_array, load_img
###########################################################################################################################
## Model Initials
IMAGE_SIZE = (255, 255)
BATCH_SIZE = 24
NUM_EPOCHS = 1
WEIGHTS_FINAL = 'defectdetection.hdf5'
MODEL_FINAL = 'defectdetection.h5'
BEST_WEIGHT ='1defectdetection.hdf5'
##############################################################################################
## Loading dataset for the training process
## Define data path
# Loading the training data
img_path = 'C:/Users/TeamSoloMid/SolarCellsImages/dataset/Sample0001.jpg'
img = image.load_img(img_path, target_size=(255, 255))
x = image.img_to_array(img)
print (x.shape)
x = np.expand_dims(x, axis=0)
print (x.shape)
x = preprocess_input(x)
print('Input image shape:', x.shape)
PATH = os.getcwd()
data_path = 'C:/Users/TeamSoloMid/SolarCellsImages'
data_dir_list = os.listdir(data_path)
img_data_list=[]
for dataset in data_dir_list:
img_list=os.listdir(data_path+'/'+ dataset)
print ('Loaded the images of dataset-'+'{}\n'.format(dataset))
for img in img_list:
img_path = data_path + '/'+ dataset + '/'+ img
img = image.load_img(img_path, target_size=(255,255))
x = image.img_to_array(img)
x = np.expand_dims(x, axis=0)
x = preprocess_input(x)
#print('Input image shape:', x.shape)
img_data_list.append(x)
img_data = np.array(img_data_list)
print (img_data.shape)
img_data=np.rollaxis(img_data,1,0)
print (img_data.shape)
img_data=img_data[0]
print (img_data.shape)
#t=time.time()
# Define the number of classes
num_classes = 2
num_of_samples = img_data.shape[0]
labels = np.ones((num_of_samples,),dtype='int64')
labels[0:1603]=0
labels[1604:3225]=1
names = ['Defect', 'Almost']
Y = np_utils.to_categorical(labels, num_classes)
#Shuffle the dataset
x,y = shuffle(img_data,Y, random_state=2)
# Split the dataset
TestPcnt = 0.2
X_train, X_test, y_train, y_test = train_test_split(x, y,
test_size=TestPcnt,
random_state=2)
epoch=NUM_EPOCHS
###############################################################################################
# Fine tune the resnet 101
image_input = Input(shape=(255, 255, 3))
model = ResNet101(include_top=False,
input_tensor=image_input,
weights='imagenet',
backend=keras.backend,
layers=keras.layers,
models=keras.models,
utils=keras.utils)
# Freeze all the layers
for layer in model.layers[:-3]:
layer.trainable = False
#model.summary()
last_layer = model.output
# add a global spatial average pooling layer
x = GlobalAveragePooling2D()(last_layer)
x = Dense(256, activation='relu',name='fc-1')(x)
x = Dropout(0.5)(x)
out = Dense(num_classes, activation='softmax',name='output_layer')(x)
# this is the model we will train
net_model = Model(inputs=model.input, outputs=out)
net_model.summary()
for layer in net_model.layers[:-5]:
layer.trainable = False
net_model.summary()
for layer in net_model.layers:
print(layer, layer.trainable)
#my_opti= optimizers.Adam(lr=0.00002)
#my_opti= optimizers.Adam(lr=0.00001)
################################################################################################
#Define learning Rate
learning_rate = 0.00002
decay_rate = learning_rate / epoch
momentum = 0.9
sgd = SGD(lr=learning_rate, momentum=momentum,
decay=decay_rate,
nesterov=False)
##############################################################################
## we will keep the weights of the epoch that scores highest in terms of accuracy on the test set.
from keras.callbacks import ModelCheckpoint
checkpointer = ModelCheckpoint(filepath=BEST_WEIGHT,
monitor = 'val_acc',
verbose=1,
save_best_only=True,
mode = 'max')
###################################################################
callback_list = [checkpointer]
net_model.compile(loss='categorical_crossentropy',
optimizer=sgd,
metrics=['accuracy'])
t=time.time()
hist = net_model.fit(X_train, y_train, batch_size=BATCH_SIZE,
epochs=NUM_EPOCHS, verbose=1,
callbacks = [checkpointer],
validation_data=(X_test, y_test))
print('Training time: %s' % (time.time()-1))
(loss, accuracy) = net_model.evaluate(X_test, y_test,
batch_size=BATCH_SIZE,
verbose=1)
print("[INFO] loss={:.4f}, accuracy: {:.4f}%".format(loss,accuracy * 100))
############################################################################################
## Saving The weights of the model after training
net_model.save_weights(WEIGHTS_FINAL)
print('1. Weights Saved')
net_model.save_weights(BEST_WEIGHT)
print('2. Best Weights Saved')
##############################################################################
## Saving The Complete model after training
net_model.save(MODEL_FINAL)
print('3. Model Saved')
############################################################################################
import matplotlib.pyplot as plt
# visualizing losses and accuracy
train_loss=hist.history['loss']
val_loss=hist.history['val_loss']
train_acc=hist.history['acc']
val_acc=hist.history['val_acc']
xc=range(NUM_EPOCHS)
plt.figure(1,figsize=(7,5))
plt.plot(xc,train_loss)
plt.plot(xc,val_loss)
plt.xlabel('num of Epochs')
plt.ylabel('loss')
plt.title('train_loss vs val_loss')
plt.grid(True)
plt.legend(['train','val'])
#print plt.style.available # use bmh, classic,ggplot for big pictures
plt.style.use(['classic'])
plt.figure(2,figsize=(7,5))
plt.plot(xc,train_acc)
plt.plot(xc,val_acc)
plt.xlabel('num of Epochs')
plt.ylabel('accuracy')
plt.title('train_acc vs val_acc')
plt.grid(True)
plt.legend(['train','val'],loc=4)
#print plt.style.available # use bmh, classic,ggplot for big pictures
plt.style.use(['classic'])
############################################################################
from sklearn.metrics import confusion_matrix, classification_report
import itertools
from sklearn.utils.multiclass import unique_labels
from sklearn import metrics
import seaborn as sns
import pandas as pd
from sklearn.datasets import load_files
from sklearn.svm import LinearSVC
from sklearn import svm
LABELS= ['Defect', 'Almost']
# Print confusion matrix for training data
y_pred_train = net_model.predict(X_train)
def show_confusion_matrix(validations, predictions):
matrix = metrics.confusion_matrix(validations, predictions)
plt.figure(figsize=(10, 10))
sns.heatmap(matrix,
cmap='coolwarm',
linecolor='white',
linewidths=1,
xticklabels=LABELS,
yticklabels=LABELS,
annot=True,
fmt='d')
plt.title('Confusion Matrix')
plt.ylabel('True Label')
plt.xlabel('Predicted Label')
plt.show()
y_pred_test = net_model.predict(X_test)
# Take the class with the highest probability from the test predictions
max_y_pred_test = np.argmax(y_pred_test, axis=1)
max_y_test = np.argmax(y_test, axis=1)
show_confusion_matrix(max_y_test, max_y_pred_test)
print(classification_report(max_y_test, max_y_pred_test))
【问题讨论】：
标签： python