07usingConvnetsWithSmallDatasets.py

import keras
from keras import optimizers
from keras import layers
from keras import models
from keras.preprocessing.image import ImageDataGenerator
import matplotlib.pyplot as plt
import os, shutil
# This is module with image preprocessing utilities
from keras.preprocessing import image

# The path to the directory where the original
# dataset was uncompressed
original_dataset_dir = 'D:/Data/cats_and_dogs/original'

# The directory where we will
# store our smaller dataset
base_dir = 'D:/Data/cats_and_dogs/cats_and_dogs_small'
os.mkdir(base_dir)

# Directories for our training,
# validation and test splits
train_dir = os.path.join(base_dir, 'train')
os.mkdir(train_dir)
validation_dir = os.path.join(base_dir, 'validation')
os.mkdir(validation_dir)
test_dir = os.path.join(base_dir, 'test')
os.mkdir(test_dir)

# Directory with our training cat pictures
train_cats_dir = os.path.join(train_dir, 'cats')
os.mkdir(train_cats_dir)

# Directory with our training dog pictures
train_dogs_dir = os.path.join(train_dir, 'dogs')
os.mkdir(train_dogs_dir)

# Directory with our validation cat pictures
validation_cats_dir = os.path.join(validation_dir, 'cats')
os.mkdir(validation_cats_dir)

# Directory with our validation dog pictures
validation_dogs_dir = os.path.join(validation_dir, 'dogs')
os.mkdir(validation_dogs_dir)

# Directory with our validation cat pictures
test_cats_dir = os.path.join(test_dir, 'cats')
os.mkdir(test_cats_dir)

# Directory with our validation dog pictures
test_dogs_dir = os.path.join(test_dir, 'dogs')
os.mkdir(test_dogs_dir)

# Copy first 1000 cat images to train_cats_dir
fnames = ['cat.{}.jpg'.format(i) for i in range(1000)]
for fname in fnames:
    src = os.path.join(original_dataset_dir, fname)
    dst = os.path.join(train_cats_dir, fname)
    shutil.copyfile(src, dst)

# Copy next 500 cat images to validation_cats_dir
fnames = ['cat.{}.jpg'.format(i) for i in range(1000, 1500)]
for fname in fnames:
    src = os.path.join(original_dataset_dir, fname)
    dst = os.path.join(validation_cats_dir, fname)
    shutil.copyfile(src, dst)
    
# Copy next 500 cat images to test_cats_dir
fnames = ['cat.{}.jpg'.format(i) for i in range(1500, 2000)]
for fname in fnames:
    src = os.path.join(original_dataset_dir, fname)
    dst = os.path.join(test_cats_dir, fname)
    shutil.copyfile(src, dst)
    
# Copy first 1000 dog images to train_dogs_dir
fnames = ['dog.{}.jpg'.format(i) for i in range(1000)]
for fname in fnames:
    src = os.path.join(original_dataset_dir, fname)
    dst = os.path.join(train_dogs_dir, fname)
    shutil.copyfile(src, dst)
    
# Copy next 500 dog images to validation_dogs_dir
fnames = ['dog.{}.jpg'.format(i) for i in range(1000, 1500)]
for fname in fnames:
    src = os.path.join(original_dataset_dir, fname)
    dst = os.path.join(validation_dogs_dir, fname)
    shutil.copyfile(src, dst)
    
# Copy next 500 dog images to test_dogs_dir
fnames = ['dog.{}.jpg'.format(i) for i in range(1500, 2000)]
for fname in fnames:
    src = os.path.join(original_dataset_dir, fname)
    dst = os.path.join(test_dogs_dir, fname)
    shutil.copyfile(src, dst)

# print('total training cat images:', len(os.listdir(train_cats_dir)))          1000
# print('total training dog images:', len(os.listdir(train_dogs_dir)))          1000
# print('total validation cat images:', len(os.listdir(validation_cats_dir)))   500
# print('total validation dog images:', len(os.listdir(validation_dogs_dir)))   500
# print('total test cat images:', len(os.listdir(test_cats_dir)))               500
# print('total test dog images:', len(os.listdir(test_dogs_dir)))               500

# Building network
model = models.Sequential()
model.add(layers.Conv2D(32, (3, 3), activation='relu',
                        input_shape=(150, 150, 3)))
model.add(layers.MaxPooling2D((2, 2)))
model.add(layers.Conv2D(64, (3, 3), activation='relu'))
model.add(layers.MaxPooling2D((2, 2)))
model.add(layers.Conv2D(128, (3, 3), activation='relu'))
model.add(layers.MaxPooling2D((2, 2)))
model.add(layers.Conv2D(128, (3, 3), activation='relu'))
model.add(layers.MaxPooling2D((2, 2)))
model.add(layers.Flatten())
model.add(layers.Dense(512, activation='relu'))
model.add(layers.Dense(1, activation='sigmoid'))

# model.summary()

# Layer (type)                 Output Shape              Param #   
# ================================================================= 卷积个数 * （卷积宽 * 卷积高）* 生成的通道数（即featuremap个数） + 偏置个数
# conv2d_1 (Conv2D)            (None, 148, 148, 32)      896         32 * (3*3) * 3 + 32
# _________________________________________________________________
# max_pooling2d_1 (MaxPooling2 (None, 74, 74, 32)        0         
# _________________________________________________________________
# conv2d_2 (Conv2D)            (None, 72, 72, 64)        18496       64 * (3*3) * 32 + 64
# _________________________________________________________________
# max_pooling2d_2 (MaxPooling2 (None, 36, 36, 64)        0         
# _________________________________________________________________
# conv2d_3 (Conv2D)            (None, 34, 34, 128)       73856       128 * (3*3) * 64 + 128
# _________________________________________________________________
# max_pooling2d_3 (MaxPooling2 (None, 17, 17, 128)       0         
# _________________________________________________________________
# conv2d_4 (Conv2D)            (None, 15, 15, 128)       147584    
# _________________________________________________________________
# max_pooling2d_4 (MaxPooling2 (None, 7, 7, 128)         0         
# _________________________________________________________________
# flatten_1 (Flatten)          (None, 6272)              0         
# _________________________________________________________________
# dense_1 (Dense)              (None, 512)               3211776   
# _________________________________________________________________
# dense_2 (Dense)              (None, 1)                 513    
# Total params: 3,453,121
# Trainable params: 3,453,121
# Non-trainable params: 0
# _________________________________________________________________


model.compile(loss='binary_crossentropy',
              optimizer=optimizers.RMSprop(lr=1e-4),
              metrics=['acc'])

# Data preprocessing
# All images will be rescaled by 1./255
train_datagen = ImageDataGenerator(rescale=1./255)
test_datagen = ImageDataGenerator(rescale=1./255)

train_generator = train_datagen.flow_from_directory(
        # This is the target directory
        train_dir,
        # All images will be resized to 150x150
        target_size=(150, 150),
        batch_size=20,
        # Since we use binary_crossentropy loss, we need binary labels
        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:    # 生成器
#     print('data batch shape:', data_batch.shape)
#     print('labels batch shape:', labels_batch.shape)
#     break

history = model.fit_generator(
      train_generator,
      steps_per_epoch=100,   # 每批20个样本, 总共100个批次（即100次梯度下降），总共2000个训练样本
      epochs=30,      # 迭代次数
      validation_data=validation_generator,
      validation_steps=50)

model.save('cats_and_dogs_small_1.h5')


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

plt.show()

# Using data augmentation
# datagen = ImageDataGenerator(
#       rotation_range=40,
#       width_shift_range=0.2,
#       height_shift_range=0.2,
#       shear_range=0.2,
#       zoom_range=0.2,
#       horizontal_flip=True,
#       fill_mode='nearest')

# fnames = [os.path.join(train_cats_dir, fname) for fname in os.listdir(train_cats_dir)]

# # We pick one image to "augment"
# img_path = fnames[3]

# # Read the image and resize it
# img = image.load_img(img_path, target_size=(150, 150))

# # Convert it to a Numpy array with shape (150, 150, 3)
# x = image.img_to_array(img)

# # Reshape it to (1, 150, 150, 3)
# x = x.reshape((1,) + x.shape)

# # The .flow() command below generates batches of randomly transformed images.
# # It will loop indefinitely, so we need to `break` the loop at some point!
# i = 0
# for batch in datagen.flow(x, batch_size=1):
#     plt.figure(i)
#     imgplot = plt.imshow(image.array_to_img(batch[0]))
#     i += 1
#     if i % 4 == 0:
#         break

# plt.show()

# data augmentation and dropout
model = models.Sequential()
model.add(layers.Conv2D(32, (3, 3), activation='relu',
                        input_shape=(150, 150, 3)))
model.add(layers.MaxPooling2D((2, 2)))
model.add(layers.Conv2D(64, (3, 3), activation='relu'))
model.add(layers.MaxPooling2D((2, 2)))
model.add(layers.Conv2D(128, (3, 3), activation='relu'))
model.add(layers.MaxPooling2D((2, 2)))
model.add(layers.Conv2D(128, (3, 3), activation='relu'))
model.add(layers.MaxPooling2D((2, 2)))
model.add(layers.Flatten())
model.add(layers.Dropout(0.5))
model.add(layers.Dense(512, activation='relu'))
model.add(layers.Dense(1, activation='sigmoid'))

model.compile(loss='binary_crossentropy',
              optimizer=optimizers.RMSprop(lr=1e-4),
              metrics=['acc'])

train_datagen = ImageDataGenerator(
    rescale=1./255,
    rotation_range=40,
    width_shift_range=0.2,
    height_shift_range=0.2,
    shear_range=0.2,
    zoom_range=0.2,
    horizontal_flip=True,)

# Note that the validation data should not be augmented!
test_datagen = ImageDataGenerator(rescale=1./255)

train_generator = train_datagen.flow_from_directory(
        # This is the target directory
        train_dir,
        # All images will be resized to 150x150
        target_size=(150, 150),
        batch_size=32,
        # Since we use binary_crossentropy loss, we need binary labels
        class_mode='binary')

validation_generator = test_datagen.flow_from_directory(
        validation_dir,
        target_size=(150, 150),
        batch_size=32,
        class_mode='binary')

history = model.fit_generator(
      train_generator,
      steps_per_epoch=100,
      epochs=100,
      validation_data=validation_generator,
      validation_steps=50)

model.save('cats_and_dogs_small_2.h5')

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

plt.show()