Making Machines Learn

Rishit Dagli Rishit-dagli

Making Machines Learn

interested in learning algorithms: machine learning, vision, graphics (simulation)

Rishit-dagli / import_tensorflow2.0.py

Created December 25, 2019 11:00

Import TensorFlow in Colab

	try:
	# %tensorflow_version only exists in Colab.
	%tensorflow_version 2.x
	except Exception:
	pass

	import tensorflow as tf

Rishit-dagli / fashion_mnist import.py

Created December 27, 2019 16:32

	mnist = tf.keras.datasets.fashion_mnist
	(training_images, training_labels), (test_images, test_labels) = mnist.load_data()

Rishit-dagli / Callback_class.py

Last active December 27, 2019 16:58

	class myCallback(tf.keras.callbacks.Callback):
	def on_epoch_end(self, epoch, logs = {}):
	if logs.get('loss') < 0.7:
	print("\n Low loss so cancelling the training")
	self.model.stop_training = True

Rishit-dagli / excercise2_solution.py

Created December 27, 2019 17:16

	def train_mnist():
	# Please write your code only where you are indicated.
	# please do not remove # model fitting inline comments.

	# YOUR CODE SHOULD START HERE
	class myCallback(tf.keras.callbacks.Callback):
	def on_epoch_end(self, epoch, logs={}):
	if(logs.get('acc')>0.99):
	print("/nReached 99% accuracy so cancelling training!")
	self.model.stop_training = True

Rishit-dagli / Excercise 3 Solution.py

Created January 15, 2020 11:58

	def train_mnist_conv():
	# Please write your code only where you are indicated.
	# please do not remove model fitting inline comments.

	# YOUR CODE STARTS HERE
	class myCallback(tf.keras.callbacks.Callback):
	def on_epoch_end(self, epoch, logs={}):
	if(logs.get('acc')>0.998):
	print("/n Reached 99.8% accuracy so cancelling training!")
	self.model.stop_training = True

Rishit-dagli / monster_ex.java

Created January 24, 2020 16:16

	public class Monster{

	private String name;
	private final int MAX_HEALTH = 100;
	private static int curr_health = 100;
	private double dmg_inf;
	private double dmg_taken;

	public String getName() {
	return name;

Rishit-dagli / projector_config_imdb.json

Created March 20, 2020 10:43

TF projector for IMDB dataset

	{
	"embeddings": [
	{
	"tensorName": "My tensor",
	"tensorShape": [
	1000,
	50
	],
	"tensorPath": "https://raw.githubusercontent.com/.../tensors.tsv",
	"metadataPath": "https://raw.githubusercontent.com/.../optional.metadata.tsv"

Rishit-dagli / index.html

Created March 31, 2020 12:38

STarter index.html for TF.js

	<!DOCTYPE html>
	<html>
	<head>
	<title>TensorFlow.js Tutorial</title>

	<!-- Import TensorFlow.js -->
	<script src="https://cdn.jsdelivr.net/npm/@tensorflow/[email protected]/dist/tf.min.js"></script>
	<!-- Import tfjs-vis -->
	<script src="https://cdn.jsdelivr.net/npm/@tensorflow/[email protected]/dist/tfjs-vis.umd.min.js"></script>

Rishit-dagli / script.js

Created March 31, 2020 13:31

Addon script.js for loading data

	/**
	* Get the car data reduced to just the variables we are interested
	* and cleaned of missing data.
	*/
	async function getData() {
	const carsDataReq = await fetch('https://storage.googleapis.com/tfjs-tutorials/carsData.json');
	const carsData = await carsDataReq.json();
	const cleaned = carsData.map(car => ({
	mpg: car.Miles_per_Gallon,
	horsepower: car.Horsepower,

Rishit-dagli / script.js

Created March 31, 2020 13:34

Scatterplot of data

	async function run() {
	// Load and plot the original input data that we are going to train on.
	const data = await getData();
	const values = data.map(d => ({
	x: d.horsepower,
	y: d.mpg,
	}));

	tfvis.render.scatterplot(
	{name: 'Horsepower v MPG'},