In [6]:
import os, shutil
original_dataset_dir = 'E:\\Datasets\\Kaggle\\dog_cat\\train'
base_dir = 'E:\\Datasets\\Kaggle\\dog_cat\\base'
os.mkdir(base_dir)
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)
train_cats_dir = os.path.join(train_dir, 'cats')
os.mkdir(train_cats_dir)
train_dogs_dir = os.path.join(train_dir, 'dogs')
os.mkdir(train_dogs_dir)
validation_cats_dir = os.path.join(validation_dir, 'cats')
os.mkdir(validation_cats_dir)
validation_dogs_dir = os.path.join(validation_dir, 'dogs')
os.mkdir(validation_dogs_dir)
test_cats_dir = os.path.join(test_dir, 'cats')
os.mkdir(test_cats_dir)
test_dogs_dir = os.path.join(test_dir, 'dogs')
os.mkdir(test_dogs_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)
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)
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)
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)
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)
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)
In [7]:
from keras import layers
from keras import models
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'))
In [8]:
model.summary()
In [9]:
from keras import optimizers
model.compile(loss='binary_crossentropy', optimizer=optimizers.RMSprop(lr=1e-4),
metrics=['acc'])
In [11]:
from keras.preprocessing.image import ImageDataGenerator
train_datagen = ImageDataGenerator(rescale=1./255)
valid_datagen = ImageDataGenerator(rescale=1./255)
train_generator = train_datagen.flow_from_directory(
train_dir,
target_size=(150, 150),
batch_size=20,
class_mode='binary'
)
validation_generator = valid_datagen.flow_from_directory(
validation_dir,
target_size=(150, 150),
batch_size=20,
class_mode='binary'
)
In [13]:
for data_batch, labels_batch in train_generator:
print("data_batch shape", data_batch.shape)
print("labels_batch shape", labels_batch.shape)
break
In [15]:
history = model.fit_generator(
train_generator,
steps_per_epoch=100,
epochs=30,
validation_data=validation_generator,
validation_steps=50
)
model.save(os.path.join(base_dir, 'cats_dogs_small_1.h5'))
In [18]:
import matplotlib.pyplot as plt
acc = history.history['acc']
val_acc = history.history['val_acc']
loss = history.history['loss']
val_loss = history.history['val_loss']
epochs = range(1, len(acc) + 1)
plt.plot(epochs, acc, 'bo', label='Train 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='Train loss')
plt.plot(epochs, val_loss, 'b', label='Validation loss')
plt.title("Training and validation loss")
plt.legend()
plt.show()
In [19]:
# 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'
)
In [22]:
from keras.preprocessing import image
fnames = [os.path.join(train_cats_dir, fname) for fname in os.listdir(train_cats_dir)]
img_path = fnames[3]
img = image.load_img(img_path, target_size=(150, 150))
x = image.img_to_array(img)
x = x.reshape((1, ) + x.shape)
i = 0
for batch in datagen.flow(x, batch_size=1):
plt.figure(i)
plt.imshow(image.array_to_img(batch[0]))
i += 1
if i % 4 == 0:
break
plt.show()
In [27]:
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'])
In [24]:
from keras.preprocessing.image import ImageDataGenerator
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,
fill_mode='nearest')
valid_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,
fill_mode='nearest')
train_generator = train_datagen.flow_from_directory(
train_dir,
target_size=(150, 150),
batch_size=20,
class_mode='binary'
)
validation_generator = valid_datagen.flow_from_directory(
validation_dir,
target_size=(150, 150),
batch_size=20,
class_mode='binary'
)
In [28]:
history = model.fit_generator(
train_generator,
steps_per_epoch=100,
epochs=100,
validation_data=validation_generator,
validation_steps=50
)
model.save(os.path.join(base_dir, 'cats_dogs_small_2.h5'))
In [26]:
import matplotlib.pyplot as plt
acc = history.history['acc']
val_acc = history.history['val_acc']
loss = history.history['loss']
val_loss = history.history['val_loss']
epochs = range(1, len(acc) + 1)
plt.plot(epochs, acc, 'bo', label='Train 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='Train loss')
plt.plot(epochs, val_loss, 'b', label='Validation loss')
plt.title("Training and validation loss")
plt.legend()
plt.show()
In [ ]: