# 存储数据集的目录
base_dir = 'E:/python learn/dog_and_cat/data/'
 
# 训练、验证数据集的目录
train_dir = os.path.join(base_dir, 'train')
validation_dir = os.path.join(base_dir, 'validation')
test_dir = os.path.join(base_dir, 'test')
 
# 猫训练图片所在目录
train_cats_dir = os.path.join(train_dir, 'cats')
 
# 狗训练图片所在目录
train_dogs_dir = os.path.join(train_dir, 'dogs')
 
# 猫验证图片所在目录
validation_cats_dir = os.path.join(validation_dir, 'cats')
 
# 狗验证数据集所在目录
validation_dogs_dir = os.path.join(validation_dir, 'dogs')
 
print('total training cat images:', len(os.listdir(train_cats_dir))) 
print('total training dog images:', len(os.listdir(train_dogs_dir))) 
print('total validation cat images:', len(os.listdir(validation_cats_dir))) 
print('total validation dog images:', len(os.listdir(validation_dogs_dir)))

# 搭建模型
model = Sequential()
model.add(Conv2D(32, (3, 3), activation='relu',
         input_shape=(150, 150, 3)))
model.add(MaxPooling2D((2, 2)))
model.add(Conv2D(64, (3, 3), activation='relu'))
model.add(MaxPooling2D((2, 2)))
model.add(Conv2D(128, (3, 3), activation='relu'))
model.add(MaxPooling2D((2, 2)))
model.add(Conv2D(128, (3, 3), activation='relu'))
model.add(MaxPooling2D((2, 2)))
model.add(Flatten())
model.add(Dense(512, activation='relu'))
model.add(Dense(1, activation='sigmoid'))
 
print(model.summary())
 
model.compile(loss='binary_crossentropy',
       optimizer=RMSprop(lr=1e-4),
       metrics=['acc'])

train_datagen = ImageDataGenerator(rescale=1./255)
test_datagen = ImageDataGenerator(rescale=1./255)
 
train_generator = train_datagen.flow_from_directory(
  train_dir, # target directory
  target_size=(150, 150), # resize图片
  batch_size=20,
  class_mode='binary'
)
 
validation_generator = test_datagen.flow_from_directory(
  validation_dir,
  target_size=(150, 150),
  batch_size=20,
  class_mode='binary'
)
 
for data_batch, labels_batch in train_generator:
  print('data batch shape:', data_batch.shape)
  print('labels batch shape:', labels_batch.shape)
  break
 
hist = model.fit_generator(
  train_generator,
  steps_per_epoch=100,
  epochs=10,
  validation_data=validation_generator,
  validation_steps=50
)
 
model.save('cats_and_dogs_small_1.h5')

acc = hist.history['acc']
val_acc = hist.history['val_acc']
loss = hist.history['loss']
val_loss = hist.history['val_loss']
 
epochs = range(len(acc))
 
plt.plot(epochs, acc, 'bo', label='Training acc')
plt.plot(epochs, val_acc, 'b', label='Validation acc')
plt.title('Training and validation accuracy')
 
plt.legend()
plt.figure()
 
plt.figure()
plt.plot(epochs, loss, 'bo', label='Training loss')
plt.plot(epochs, val_loss, 'b', label='Validation loss')
plt.legend()
plt.show()

imagename = 'E:/python learn/dog_and_cat/data/validation/dogs/dog.2026.jpg'
test_image = image.load_img(imagename, target_size = (150, 150))
test_image = image.img_to_array(test_image)
test_image = np.expand_dims(test_image, axis=0)
result = model.predict(test_image)
 
if result[0][0] == 1:
  prediction ='dog'
else:
  prediction ='cat'
  
print(prediction)

import os
import numpy as np
import tensorflow as tf
import random
import seaborn as sns
import matplotlib.pyplot as plt
import keras
from keras.models import Sequential, Model
from keras.layers import Dense, Dropout, Activation, Flatten, Input,BatchNormalization
from keras.layers.convolutional import Conv2D, MaxPooling2D
from keras.optimizers import RMSprop, Adam, SGD
from keras.preprocessing import image
from keras.preprocessing.image import ImageDataGenerator
from keras.applications.vgg16 import VGG16, preprocess_input
 
from sklearn.model_selection import train_test_split

def read_and_process_image(data_dir,width=64, height=64, channels=3, preprocess=False):
  train_images= [data_dir + i for i in os.listdir(data_dir)]
  
  random.shuffle(train_images)
  
  def read_image(file_path, preprocess):
    img = image.load_img(file_path, target_size=(height, width))
    x = image.img_to_array(img)
    x = np.expand_dims(x, axis=0)
    # if preprocess:
      # x = preprocess_input(x)
    return x
  
  def prep_data(images, proprocess):
    count = len(images)
    data = np.ndarray((count, height, width, channels), dtype = np.float32)
    
    for i, image_file in enumerate(images):
      image = read_image(image_file, preprocess)
      data[i] = image
    
    return data
  
  def read_labels(file_path):
    labels = []
    for i in file_path:
      label = 1 if 'dog' in i else 0
      labels.append(label)
    
    return labels
  
  X = prep_data(train_images, preprocess)
  labels = read_labels(train_images)
  
  assert X.shape[0] == len(labels)
  print("Train shape: {}".format(X.shape))
  return X, labels

# 读取图片
WIDTH = 150
HEIGHT = 150
CHANNELS = 3
X, y = read_and_process_image('D:\\Python_Project\\train\\',width=WIDTH, height=HEIGHT, channels=CHANNELS)

# 统计y
sns.countplot(y)
 
# 显示图片
def show_cats_and_dogs(X, idx):
  plt.figure(figsize=(10,5), frameon=True)
  img = X[idx,:,:,::-1]
  img = img/255
  plt.imshow(img)
  plt.show()
 
 
for idx in range(0,3):
  show_cats_and_dogs(X, idx)
 
train_X = X[0:17500,:,:,:]
train_y = y[0:17500]
test_X = X[17500:25000,:,:,:]
test_y = y[17500:25000]
train_X.shape
test_X.shape

input_layer = Input((WIDTH, HEIGHT, CHANNELS))
# 第一层
z = input_layer
z = Conv2D(64, (3,3))(z)
z = BatchNormalization()(z)
z = Activation('relu')(z)
z = MaxPooling2D(pool_size = (2,2))(z)
 
z = Conv2D(64, (3,3))(z)
z = BatchNormalization()(z)
z = Activation('relu')(z)
z = MaxPooling2D(pool_size = (2,2))(z)
 
z = Conv2D(128, (3,3))(z)
z = BatchNormalization()(z)
z = Activation('relu')(z)
z = MaxPooling2D(pool_size = (2,2))(z)
 
z = Conv2D(128, (3,3))(z)
z = BatchNormalization()(z)
z = Activation('relu')(z)
z = MaxPooling2D(pool_size = (2,2))(z)
 
z = Flatten()(z)
z = Dense(64)(z)
z = BatchNormalization()(z)
z = Activation('relu')(z)
z = Dropout(0.5)(z)
z = Dense(1)(z)
z = Activation('sigmoid')(z)
 
model = Model(input_layer, z)
 
model.compile(
  optimizer = keras.optimizers.RMSprop(),
  loss = keras.losses.binary_crossentropy,
  metrics = [keras.metrics.binary_accuracy]
)
 
model.summary()

history = model.fit(train_X,train_y, validation_data=(test_X, test_y),epochs=10,batch_size=128,verbose=True)
score = model.evaluate(test_X, test_y, verbose=0)
print("Large CNN Error: %.2f%%" %(100-score[1]*100))

def vgg16_model(input_shape= (HEIGHT,WIDTH,CHANNELS)):
  vgg16 = VGG16(include_top=False, weights='imagenet',input_shape=input_shape)
  
  for layer in vgg16.layers:
    layer.trainable = False
  last = vgg16.output
  # 后面加入自己的模型
  x = Flatten()(last)
  x = Dense(256, activation='relu')(x)
  x = Dropout(0.5)(x)
  x = Dense(256, activation='relu')(x)
  x = Dropout(0.5)(x)
  x = Dense(1, activation='sigmoid')(x)
  
  model = Model(inputs=vgg16.input, outputs=x)
  
  return model

model_vgg16 = vgg16_model()
model_vgg16.summary()
model_vgg16.compile(loss='binary_crossentropy',optimizer = Adam(0.0001), metrics = ['accuracy'])

# 训练模型
history = model_vgg16.fit(train_X,train_y, validation_data=(test_X, test_y),epochs=5,batch_size=128,verbose=True)
score = model_vgg16.evaluate(test_X, test_y, verbose=0)
print("Large CNN Error: %.2f%%" %(100-score[1]*100))