%load_ext watermark
%watermark -a "Romell D.Z." -u -d -p numpy,pandas,matplotlib,keras

%matplotlib inline
%config InlineBackend.figure_format = 'retina'
import matplotlib.pyplot as plt
plt.rcParams['figure.figsize'] = (18,6)

import os
import glob
import zipfile
import functools

# Upload the API token.
def get_kaggle_credentials():
    token_dir = os.path.join(os.path.expanduser("~"),".kaggle")
    token_file = os.path.join(token_dir, "kaggle.json")
    if not os.path.isdir(token_dir):
        os.mkdir(token_dir)
    try:
        with open(token_file,'r') as f:
            pass
    except IOError as no_file:
        try:
            from google.colab import files
        except ImportError:
            raise no_file
        uploaded = files.upload()

        if "kaggle.json" not in uploaded:
            raise ValueError("You need an API key! see: "
                           "https://github.com/Kaggle/kaggle-api#api-credentials")
        with open(token_file, "wb") as f:
            f.write(uploaded["kaggle.json"])
        os.chmod(token_file, 600)

get_kaggle_credentials()

import kaggle

# Download data from Kaggle and unzip the files of interest. 
def load_data_from_zip(competition, file):
    with zipfile.ZipFile(os.path.join(competition, file), "r") as zip_ref:
        unzipped_file = zip_ref.namelist()[0]
        zip_ref.extractall(competition)

def load_data_from_7z(competition, file):
    os.system( '7z x %s ' % os.path.join(competition, file) )

def get_data(competition):
    kaggle.api.competition_download_files(competition, competition)
    load_data_from_zip(competition, 'train.zip')
    load_data_from_zip(competition, 'train.zip')

competition = 'dogs-vs-cats'
get_data(competition)

import glob
import numpy as np
import os
import shutil
np.random.seed(42)

files = glob.glob('%s/train/*'%competition)

cat_files = [fn for fn in files if 'cat' in fn]
dog_files = [fn for fn in files if 'dog' in fn]
len(cat_files), len(dog_files)

cat_train = np.random.choice(cat_files, size=1500, replace=False)
dog_train = np.random.choice(dog_files, size=1500, replace=False)
cat_files = list(set(cat_files) - set(cat_train))
dog_files = list(set(dog_files) - set(dog_train))

cat_val = np.random.choice(cat_files, size=500, replace=False)
dog_val = np.random.choice(dog_files, size=500, replace=False)
cat_files = list(set(cat_files) - set(cat_val))
dog_files = list(set(dog_files) - set(dog_val))

cat_test = np.random.choice(cat_files, size=500, replace=False)
dog_test = np.random.choice(dog_files, size=500, replace=False)

print('Cat datasets:', cat_train.shape, cat_val.shape, cat_test.shape)
print('Dog datasets:', dog_train.shape, dog_val.shape, dog_test.shape)

train_dir = 'training_data'
val_dir = 'validation_data'
test_dir = 'test_data'

train_files = np.concatenate([cat_train, dog_train])
validate_files = np.concatenate([cat_val, dog_val])
test_files = np.concatenate([cat_test, dog_test])

os.mkdir(train_dir) if not os.path.isdir(train_dir) else None
os.mkdir(val_dir) if not os.path.isdir(val_dir) else None
os.mkdir(test_dir) if not os.path.isdir(test_dir) else None

for fn in train_files:
    shutil.copy(fn, train_dir)

for fn in validate_files:
    shutil.copy(fn, val_dir)
    
for fn in test_files:
    shutil.copy(fn, test_dir)

import glob
import numpy as np
import matplotlib.pyplot as plt
from keras.preprocessing.image import ImageDataGenerator, load_img, img_to_array, array_to_img
%matplotlib inline

import os
os.sep

IMG_DIM = (150, 150)

train_files = glob.glob('training_data/*')
train_imgs = [img_to_array(load_img(img, target_size=IMG_DIM)) for img in train_files]
train_imgs = np.array(train_imgs)
train_labels = [fn.split(os.sep)[1].split('.')[0].strip() for fn in train_files]

validation_files = glob.glob('validation_data/*')
validation_imgs = [img_to_array(load_img(img, target_size=IMG_DIM)) for img in validation_files]
validation_imgs = np.array(validation_imgs)
validation_labels = [fn.split(os.sep)[1].split('.')[0].strip() for fn in validation_files]

print('Train dataset shape:', train_imgs.shape, 
      '\tValidation dataset shape:', validation_imgs.shape)

train_imgs_scaled = train_imgs.astype('float32')
validation_imgs_scaled  = validation_imgs.astype('float32')
train_imgs_scaled /= 255
validation_imgs_scaled /= 255

print(train_imgs[0].shape)
array_to_img(train_imgs[0])

batch_size = 30
num_classes = 2
epochs = 30
input_shape = (150, 150, 3)

# encode text category labels
from sklearn.preprocessing import LabelEncoder

le = LabelEncoder()
le.fit(train_labels)
train_labels_enc = le.transform(train_labels)
validation_labels_enc = le.transform(validation_labels)

print(train_labels[1495:1505], train_labels_enc[1495:1505])

from keras.layers import Conv2D, MaxPooling2D, Flatten, Dense, Dropout
from keras.models import Sequential
from keras import optimizers

model = Sequential()

model.add(Conv2D(16, kernel_size=(3, 3), activation='relu', 
                 input_shape=input_shape))
model.add(MaxPooling2D(pool_size=(2, 2)))

model.add(Conv2D(64, kernel_size=(3, 3), activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))

model.add(Conv2D(128, kernel_size=(3, 3), activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))

model.add(Flatten())
model.add(Dense(512, activation='relu'))
model.add(Dense(1, activation='sigmoid'))


model.compile(loss='binary_crossentropy',
              optimizer=optimizers.RMSprop(),
              metrics=['accuracy'])

model.summary()

history = model.fit(x=train_imgs_scaled, y=train_labels_enc,
                    validation_data=(validation_imgs_scaled, validation_labels_enc),
                    batch_size=batch_size,
                    epochs=epochs,
                    verbose=1)

f, (ax1, ax2) = plt.subplots(1, 2, figsize=(12, 4))
t = f.suptitle('Basic CNN Performance', fontsize=12)
f.subplots_adjust(top=0.85, wspace=0.3)

epoch_list = list(range(1,31))
ax1.plot(epoch_list, history.history['acc'], label='Train Accuracy')
ax1.plot(epoch_list, history.history['val_acc'], label='Validation Accuracy')
ax1.set_xticks(np.arange(0, 31, 5))
ax1.set_ylabel('Accuracy Value')
ax1.set_xlabel('Epoch')
ax1.set_title('Accuracy')
l1 = ax1.legend(loc="best")

ax2.plot(epoch_list, history.history['loss'], label='Train Loss')
ax2.plot(epoch_list, history.history['val_loss'], label='Validation Loss')
ax2.set_xticks(np.arange(0, 31, 5))
ax2.set_ylabel('Loss Value')
ax2.set_xlabel('Epoch')
ax2.set_title('Loss')
l2 = ax2.legend(loc="best")

model.save('cats_dogs_basic_without_dropout.h5')

model = Sequential()

model.add(Conv2D(16, kernel_size=(3, 3), activation='relu', 
                 input_shape=input_shape))
model.add(MaxPooling2D(pool_size=(2, 2)))

model.add(Conv2D(64, kernel_size=(3, 3), activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))

model.add(Conv2D(128, kernel_size=(3, 3), activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))

model.add(Conv2D(128, kernel_size=(3, 3), activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))

model.add(Flatten())
model.add(Dense(512, activation='relu'))
model.add(Dropout(0.3))
model.add(Dense(512, activation='relu'))
model.add(Dropout(0.3))
model.add(Dense(1, activation='sigmoid'))


model.compile(loss='binary_crossentropy',
              optimizer=optimizers.RMSprop(),
              metrics=['accuracy'])
              
              
history = model.fit(x=train_imgs_scaled, y=train_labels_enc,
                    validation_data=(validation_imgs_scaled, validation_labels_enc),
                    batch_size=batch_size,
                    epochs=epochs,
                    verbose=1) 

model.save('cats_dogs_basic_cnn.h5')

train_datagen = ImageDataGenerator(rescale=1./255, zoom_range=0.3, rotation_range=50,
                                   width_shift_range=0.2, height_shift_range=0.2, shear_range=0.2, 
                                   horizontal_flip=True, fill_mode='nearest')

val_datagen = ImageDataGenerator(rescale=1./255)

img_id = 1991
dog_generator = train_datagen.flow(train_imgs[img_id:img_id+1], train_labels[img_id:img_id+1],
                                   batch_size=1)
dog = [next(dog_generator) for i in range(0,5)]
fig, ax = plt.subplots(1,5, figsize=(15, 6))
print('Labels:', [item[1][0] for item in dog])
l = [ax[i].imshow(dog[i][0][0]) for i in range(0,5)]

img_id = 2595
cat_generator = train_datagen.flow(train_imgs[img_id:img_id+1], train_labels[img_id:img_id+1],
                                   batch_size=1)
cat = [next(cat_generator) for i in range(0,5)]
fig, ax = plt.subplots(1,5, figsize=(16, 6))
print('Labels:', [item[1][0] for item in cat])
l = [ax[i].imshow(cat[i][0][0]) for i in range(0,5)]

train_generator = train_datagen.flow(train_imgs, train_labels_enc, batch_size=30)
val_generator = val_datagen.flow(validation_imgs, validation_labels_enc, batch_size=20)
input_shape = (150, 150, 3)

from keras.layers import Conv2D, MaxPooling2D, Flatten, Dense, Dropout
from keras.models import Sequential
from keras import optimizers

model = Sequential()

model.add(Conv2D(16, kernel_size=(3, 3), activation='relu', 
                 input_shape=input_shape))
model.add(MaxPooling2D(pool_size=(2, 2)))

model.add(Conv2D(64, kernel_size=(3, 3), activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))

model.add(Conv2D(128, kernel_size=(3, 3), activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))

model.add(Conv2D(128, kernel_size=(3, 3), activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))

model.add(Flatten())
model.add(Dense(512, activation='relu'))
model.add(Dropout(0.3))
model.add(Dense(512, activation='relu'))
model.add(Dropout(0.3))
model.add(Dense(1, activation='sigmoid'))

model.compile(loss='binary_crossentropy',
              optimizer=optimizers.RMSprop(lr=1e-4),
              metrics=['accuracy'])
              
history = model.fit_generator(train_generator, steps_per_epoch=100, epochs=100,
                              validation_data=val_generator, validation_steps=50, 
                              verbose=1) 

model.save('cats_dogs_cnn_img_aug.h5')

from keras.applications import vgg16
from keras.models import Model
import keras

vgg = vgg16.VGG16(include_top=False, weights='imagenet', 
                                     input_shape=input_shape)

output = vgg.layers[-1].output
output = keras.layers.Flatten()(output)
vgg_model = Model(vgg.input, output)

vgg_model.trainable = False
for layer in vgg_model.layers:
    layer.trainable = False
    
import pandas as pd
pd.set_option('max_colwidth', -1)
layers = [(layer, layer.name, layer.trainable) for layer in vgg_model.layers]
pd.DataFrame(layers, columns=['Layer Type', 'Layer Name', 'Layer Trainable']) 

bottleneck_feature_example = vgg.predict(train_imgs_scaled[0:1])
print(bottleneck_feature_example.shape)
plt.imshow(bottleneck_feature_example[0][:,:,0])