记微软openhack机器学习挑战赛(代码片段)

def normalize(src):
    arr = array(src)
    arr = arr.astype(‘float‘)
    # Do not touch the alpha channel
    for i in range(3):
        minval = arr[...,i].min()
        maxval = arr[...,i].max()
        if minval != maxval:
            arr[...,i] -= minval
            arr[...,i] *= (255.0/(maxval-minval))
    arr = arr.astype(uint8)
    return Image.fromarray(arr,‘RGB‘)

import matplotlib.pyplot as plt
from PIL import ImageColor 
from matplotlib.pyplot import imshow
from PIL import Image
from pylab import *
import copy

plt.figure(figsize=(10,10)) #设置窗口大小

# src = Image.open("100974.jpeg")
src = Image.open("rose.jpg")

src_array = array(src)
plt.subplot(2,2,1), plt.title(‘src‘)
plt.imshow(src), plt.axis(‘off‘)


ar=src_array[:,:,0].flatten()
ag=src_array[:,:,1].flatten()
ab=src_array[:,:,2].flatten()
plt.subplot(2,2,2),  plt.title(‘src hist‘)
plt.axis([0,255,0,0.03])
plt.hist(ar, bins=256, normed=1,facecolor=‘red‘,edgecolor=‘r‘,hold=1) #原始图像直方图
plt.hist(ag, bins=256, normed=1,facecolor=‘g‘,edgecolor=‘g‘,hold=1) #原始图像直方图
plt.hist(ab, bins=256, normed=1,facecolor=‘b‘,edgecolor=‘b‘) #原g始图像直方图


dst = normalize(src)
dst_array = array(dst)

plt.subplot(2,2,3), plt.title(‘dst‘)
plt.imshow(dst), plt.axis(‘off‘)

ar=dst_array[:,:,0].flatten()
ag=dst_array[:,:,1].flatten()
ab=dst_array[:,:,2].flatten()
plt.subplot(2,2,4),  plt.title(‘dst hist‘)
plt.axis([0,255,0,0.03])
plt.hist(ar, bins=256, normed=1,facecolor=‘red‘,edgecolor=‘r‘,hold=1) #原始图像直方图
plt.hist(ag, bins=256, normed=1,facecolor=‘g‘,edgecolor=‘g‘,hold=1) #原始图像直方图
plt.hist(ab, bins=256, normed=1,facecolor=‘b‘,edgecolor=‘b‘) #原g始图像直方图

dir_data ="data/preprocess_images/"

equipments = [‘axes‘, ‘boots‘, ‘carabiners‘, ‘crampons‘, ‘gloves‘, ‘hardshell_jackets‘, ‘harnesses‘, ‘helmets‘,
              ‘insulated_jackets‘, ‘pulleys‘, ‘rope‘, ‘tents‘]
train_data = [] 
y = [] 

import os
from PIL import Image
for equip_name in equipments:
    dir_equip = dir_data + equip_name
    
    for filename in os.listdir(dir_equip):             
        if(filename.find(‘jpeg‘)!=-1):
            name = dir_equip + ‘/‘ + filename
            img = Image.open(name).convert(‘L‘)
            train_data.append(list(img.getdata()))
            y.append(equip_name)

from sklearn import svm
from sklearn.cross_validation import train_test_split  

train_X,test_X, train_y, test_y = train_test_split(train_data, y, test_size = 0.3, random_state = 0)

from sklearn import neighbors 
from sklearn.metrics import precision_recall_fscore_support as score
from sklearn.metrics import precision_score,recall_score

clf_knn = neighbors.KNeighborsClassifier(algorithm=‘kd_tree‘)  
clf_knn.fit(train_X, train_y)
y_pred = clf_knn.predict(test_X)

print(__doc__)

import itertools
import numpy as np
import matplotlib.pyplot as plt

from sklearn import svm, datasets
from sklearn.model_selection import train_test_split
from sklearn.metrics import confusion_matrix

def plot_confusion_matrix(cm, classes,
                          
                          normalize=False,
                          title=‘Confusion matrix‘,
                          cmap=plt.cm.Blues):
    """
    This function prints and plots the confusion matrix.
    Normalization can be applied by setting `normalize=True`.
    """
    if normalize:
        cm = cm.astype(‘float‘) / cm.sum(axis=1)[:, np.newaxis]
        print("Normalized confusion matrix")
    else:
        print(‘Confusion matrix, without normalization‘)

    print(cm)

    plt.imshow(cm, interpolation=‘nearest‘, cmap=cmap)
    plt.title(title)
    plt.colorbar()
    tick_marks = np.arange(len(classes))
    plt.xticks(tick_marks, classes, rotation=45)
    plt.yticks(tick_marks, classes)

    fmt = ‘.2f‘ if normalize else ‘d‘
    thresh = cm.max() / 2.
    for i, j in itertools.product(range(cm.shape[0]), range(cm.shape[1])):
        plt.text(j, i, format(cm[i, j], fmt),
                 horizontalalignment="center",
                 color="white" if cm[i, j] > thresh else "black")

    plt.tight_layout()
    plt.ylabel(‘True label‘)
    plt.xlabel(‘Predicted label‘)

# Compute confusion matrix
# cnf_matrix = confusion_matrix(y_test, y_pred)
np.set_printoptions(precision=2)
confusion_mat = confusion_matrix(test_y, y_pred, labels = equipments)

# Plot non-normalized confusion matrix
plt.figure(figsize=(10,10))
plot_confusion_matrix(confusion_mat, classes=equipments,
                      title=‘Confusion matrix, without normalization‘)

# Plot normalized confusion matrix
plt.figure(figsize=(10,10))

plot_confusion_matrix(confusion_mat, classes=equipments, normalize=True,
                      title=‘Normalized confusion matrix‘)

plt.show()

import matplotlib.pyplot as plt
from PIL import ImageColor 
from matplotlib.pyplot import imshow
from PIL import Image
from pylab import *
dir_data ="data/preprocess_images/"

equipments = [‘axes‘, ‘boots‘, ‘carabiners‘, ‘crampons‘, ‘gloves‘, ‘hardshell_jackets‘, ‘harnesses‘, ‘helmets‘,
              ‘insulated_jackets‘, ‘pulleys‘, ‘rope‘, ‘tents‘]
train_data = [] 
y = [] 

import os
from PIL import Image
i=0
for equip_name in equipments:
    dir_equip = dir_data + equip_name
    for filename in os.listdir(dir_equip):             
        if(filename.find(‘jpeg‘)!=-1):
            name = dir_equip + ‘/‘ + filename
            img = Image.open(name).convert(‘L‘)
            train_data.append(array(img).tolist())
            y.append(i)
    i += 1
train_data = np.asarray(train_data)  

from sklearn import svm
from sklearn.cross_validation import train_test_split  
import numpy as np
import keras
num_classes=12
img_rows=128
img_cols=128
train_X, test_X, train_y, test_y = train_test_split(train_data, y, test_size = 0.3, random_state = 0)

train_X = train_X.reshape(train_X.shape[0], img_rows, img_cols, 1)
test_X = test_X.reshape(test_X.shape[0], img_rows, img_cols, 1)
    
train_X = train_X.astype(‘float32‘)
test_X = test_X.astype(‘float32‘)
train_X /= 255
test_X /= 255
print(‘x_train shape:‘, train_X.shape)
print(train_X.shape[0], ‘train samples‘)
print(test_X.shape[0], ‘test samples‘)

# convert class vectors to binary class matrices
train_y = keras.utils.to_categorical(train_y, num_classes)
test_y = keras.utils.to_categorical(test_y, num_classes)

from keras.layers import Dense, Activation, Convolution2D, MaxPooling2D, Flatten
from keras.models import Sequential
from keras.layers import Convolution2D,MaxPooling2D, Conv2D
import keras

model = Sequential()
model.add(Conv2D(32, kernel_size=(3, 3),
                 activation=‘relu‘,
                 input_shape=(128, 128, 1)))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Conv2D(64, (3, 3), activation=‘relu‘))
model.add(MaxPooling2D(pool_size=(2, 2)))
# model.add(Dropout(0.25))
model.add(Flatten())
model.add(Dense(128, activation=‘relu‘))
# model.add(Dropout(0.5))
model.add(Dense(12, activation=‘softmax‘))

model.compile(loss=keras.losses.categorical_crossentropy,
              optimizer=keras.optimizers.Adadelta(),
              metrics=[‘accuracy‘])

model.fit(train_X, train_y,
          batch_size=128,
          epochs=50,
          verbose=1,
          validation_data=(test_X, test_y))
score = model.evaluate(test_X, test_y, verbose=0)
print(‘Test loss:‘, score[0])
print(‘Test accuracy:‘, score[1])