ocinpp

import requests
import json

# define API urls
route_url = "https://rt.data.gov.hk/v1.1/transport/citybus-nwfb/route/{company_code}"
route_stop_url = "https://rt.data.gov.hk/v1.1/transport/citybus-nwfb/route-stop/{company_code}/{route}/{direction}"
stop_url = "https://rt.data.gov.hk/v1.1/transport/citybus-nwfb/stop/{stop}"

# request header
headers = {

ocinpp

module.exports = {
  getContentUrl: (id) => `http://www.abc.com/${id}.html`,
  getFileName: (id) => `content${id}.jpg`
}

/*
Usage
const conf = require('./export-string-literals');
conf.getContentUrl('123'); => http://www.abc.com/123.html
conf.getFileName('456'); => content456.jpg

ocinpp

def extract_InceptionV3(tensor):
	from keras.applications.inception_v3 import InceptionV3, preprocess_input
	return InceptionV3(weights='imagenet', include_top=False).predict(preprocess_input(tensor))

def InceptionV3_predict_breed(img_path):
    # extract bottleneck features
    bottleneck_feature = extract_InceptionV3(path_to_tensor(img_path))
    # obtain predicted vector
    predicted_vector = InceptionV3_model.predict(bottleneck_feature)
    # return dog breed that is predicted by the model

ocinpp

InceptionV3_model.load_weights('saved_models/weights.best.InceptionV3.hdf5')

# get index of predicted dog breed for each image in test set
InceptionV3_predictions = [np.argmax(InceptionV3_model.predict(np.expand_dims(feature, axis=0))) for feature in test_InceptionV3]

# report test accuracy
test_accuracy = 100*np.sum(np.array(InceptionV3_predictions)==np.argmax(test_targets, axis=1))/len(InceptionV3_predictions)
print('Test accuracy: %.4f%%' % test_accuracy)

ocinpp

InceptionV3_model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])

checkpointer = ModelCheckpoint(filepath='saved_models/weights.best.InceptionV3.hdf5', 
                               verbose=1, save_best_only=True)

InceptionV3_model.fit(train_InceptionV3, train_targets, 
                      validation_data=(valid_InceptionV3, valid_targets), 
                      epochs=20, batch_size=20, callbacks=[checkpointer], verbose=1)

ocinpp

InceptionV3_model = Sequential()
InceptionV3_model.add(GlobalAveragePooling2D(input_shape=train_InceptionV3.shape[1:]))
InceptionV3_model.add(Dense(133, activation='softmax'))

InceptionV3_model.summary()

ocinpp

bottleneck_features = np.load('bottleneck_features/DogInceptionV3Data.npz')
train_InceptionV3 = bottleneck_features['train']
valid_InceptionV3 = bottleneck_features['valid']
test_InceptionV3 = bottleneck_features['test']

ocinpp

model.load_weights('saved_models/weights.best.from_scratch.hdf5')

# get index of predicted dog breed for each image in test set
dog_breed_predictions = [np.argmax(model.predict(np.expand_dims(tensor, axis=0))) for tensor in test_tensors]

# report test accuracy
test_accuracy = 100*np.sum(np.array(dog_breed_predictions)==np.argmax(test_targets, axis=1))/len(dog_breed_predictions)
print('Test accuracy: %.4f%%' % test_accuracy)

ocinpp

from keras.callbacks import ModelCheckpoint  

model.compile(optimizer='rmsprop', loss='categorical_crossentropy', metrics=['accuracy'])

### specify the number of epochs that you would like to use to train the model.
epochs = 5

checkpointer = ModelCheckpoint(filepath='saved_models/weights.best.from_scratch.hdf5', 
                               verbose=1, save_best_only=True)

ocinpp

from keras.layers import Conv2D, MaxPooling2D, GlobalAveragePooling2D
from keras.layers import Dropout, Flatten, Dense
from keras.models import Sequential

model = Sequential()

### TODO: Define your architecture.
# image is 224×224x3 pixels
model.add(Conv2D(filters=16, kernel_size=(2,2), activation='relu', input_shape=(224,224,3)))
model.add(MaxPooling2D(pool_size=(2, 2), strides=None, padding='same', data_format=None))