Robert John securetorobert

## split_boston_data.py
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(predictors, target, test_size=0.3, random_state=40)

## extract_columns_from_boston.py
predictors = train_df[['rm']]
target = train_df['medv']

## read_boston_from_gdrive.py
import pandas as pd
train_df = pd.read_csv('/content/gdrive/My Drive/boston/train.csv', index_col='ID')

## access_google_drive.py
from google.colab import drive
drive.mount('/content/gdrive')

## nginx-deployment.yaml
apiVersion: apps/v1
kind: Deployment
metadata:
  name: nginx-deployment
  labels:
    app: nginx
spec:
  replicas: 3
  selector:
    matchLabels:

## cloud_translation.js
// Imports the Google Cloud client library
const {Translate} = require('@google-cloud/translate').v2;

// Creates a client
const translate = new Translate();

/**
 * TODO(developer): Uncomment the following lines before running the sample.
 */
// const text = 'The text to translate, e.g. Hello, world!';

## train_model_transfer_learning.py
model.compile(optimizer='adam', loss='sparse_categorical_crossentropy', metrics=['accuracy'])
model.fit(ds, epochs=3, steps_per_epoch=10)

## image_input_pipeline.py
def preprocess_image(image):
  image = tf.image.decode_jpeg(image, channels=NUM_CHANNELS)
  image = tf.image.resize(image, [HEIGHT, WIDTH])
  image /= 255.0  # normalize to [0,1] range

  return image

def load_and_preprocess_image(path):
  image = tf.io.read_file(path)
  return preprocess_image(image)

## extend_base_model.py
x = base_model.output
x = layers.GlobalAveragePooling2D()(x)
x = layers.Dense(4096, activation='relu')(x)
x = layers.Dense(1, activation='sigmoid')(x)

model_3 = models.Model(inputs=base_model.input, outputs=x)
print(model_3.summary())

## base_model.py
base_model = tf.keras.applications.vgg19.VGG19(input_shape=(HEIGHT, WIDTH, NUM_CHANNELS), include_top=False, weights='imagenet')
base_model.trainable = False

print(base_model.summary())
	from sklearn.model_selection import train_test_split
	X_train, X_test, y_train, y_test = train_test_split(predictors, target, test_size=0.3, random_state=40)
	import pandas as pd
	train_df = pd.read_csv('/content/gdrive/My Drive/boston/train.csv', index_col='ID')
	from google.colab import drive
	drive.mount('/content/gdrive')
	apiVersion: apps/v1
	kind: Deployment
	metadata:
	name: nginx-deployment
	labels:
	app: nginx
	spec:
	replicas: 3
	selector:
	matchLabels:
	// Imports the Google Cloud client library
	const {Translate} = require('@google-cloud/translate').v2;

	// Creates a client
	const translate = new Translate();

	/**
	* TODO(developer): Uncomment the following lines before running the sample.
	*/
	// const text = 'The text to translate, e.g. Hello, world!';
	model.compile(optimizer='adam', loss='sparse_categorical_crossentropy', metrics=['accuracy'])
	model.fit(ds, epochs=3, steps_per_epoch=10)
	def preprocess_image(image):
	image = tf.image.decode_jpeg(image, channels=NUM_CHANNELS)
	image = tf.image.resize(image, [HEIGHT, WIDTH])
	image /= 255.0 # normalize to [0,1] range

	return image

	def load_and_preprocess_image(path):
	image = tf.io.read_file(path)
	return preprocess_image(image)
	x = base_model.output
	x = layers.GlobalAveragePooling2D()(x)
	x = layers.Dense(4096, activation='relu')(x)
	x = layers.Dense(1, activation='sigmoid')(x)

	model_3 = models.Model(inputs=base_model.input, outputs=x)
	print(model_3.summary())
	base_model = tf.keras.applications.vgg19.VGG19(input_shape=(HEIGHT, WIDTH, NUM_CHANNELS), include_top=False, weights='imagenet')
	base_model.trainable = False

	print(base_model.summary())