from keras.preprocessing.image import ImageDataGenerator
from keras.models import Sequential
from keras.layers import Flatten, Dense, Conv2D, MaxPooling2D, Convolution2D
from keras.preprocessing import image
import numpy as ny

test_image= image.load_img('test_image.jpg',target_size=(256,256))
test_image= image.img_to_array(test_image)
test_image= ny.expand_dims(test_image,axis=0)

traintest_dir = '/data/traintest/'



train_datagen = ImageDataGenerator(rescale=1./255,zoom_range=0.5,horizontal_flip=True)
test_datagen = ImageDataGenerator(rescale=1./255)

training_set = train_datagen.flow_from_directory(traintest_dir,(256,256),batch_size=64,class_mode='binary')

test_set = test_datagen.flow_from_directory(traintest_dir,(256,256),batch_size=64,class_mode='binary')

model = Sequential()
model.add(Convolution2D(32,3,3,input_shape=(img_width,img_height),activation='relu'))
model.add(MaxPooling2D(pool_size=(2,2)))
model.add(Flatten())
model.add(Dense(output_dim=128,activation='relu'))
model.add(Dense(output_dim=1,activation='sigmoid'))
model.compile(loss='binary_crossentropy',optimizer='adam',metrics=['accuracy'])

model.fit_generator(training_set,steps_per_epoch=12000,epochs=20,validation_data=test_set,validation_steps=12000)

result=model.predict(test_image)
training_set.class_indices
if result[0|0] >= 0.5:
    prediction = 'dog'
else:
    prediction = 'cat'
print(prediction)