Sushrut Ashtikar novasush

😉

Happy and Focussed

Senior Technical Consultant

novasush / push.js

Created June 17, 2019 06:07 — forked from davideast/push.js

Send push notifications with node-apn and Firebase

	var apn = require("apn");
	var Firebase = require("firebase");

	var service = new apn.connection({ production: false }); // true for production pipeline

	// Create a reference to the push notification queue
	var pushRef = new Firebase("<your-firebase>.firebaseio.com/notificationQueue");
	// listen for items added to the queue
	pushRef.on("child_added", function(snapshot) {

novasush / TensorflowFromBrowser.html

Created December 31, 2019 12:34

Training and predicting an equation in chrome browser asynchronously using tensorflow.js

	<!DOCTYPE html>
	<html>
	<head>
	<title>Training a model on browser</title>
	<script src="https://cdn.jsdelivr.net/npm/@tensorflow/tfjs@latest"></script>

	<script lang="js">
	async function doTraining(model){
	const history =
	await model.fit(xs, ys,

novasush / Rock_Paper_Scissor.ipynb

Last active March 6, 2020 15:42

A simple python based rock paper scissor game

Sorry, something went wrong. Reload?

Sorry, we cannot display this file.

Sorry, this file is invalid so it cannot be displayed.

novasush / setup.py

Last active March 7, 2020 17:43

Setup

	import multiprocessing

	import tensorflow as tf
	import tensorflow_datasets as tfds

	from os import getcwd

novasush / create_model.py

Created March 7, 2020 17:47

	def create_model():
	input_layer = tf.keras.layers.Input(shape=(224, 224, 3))
	base_model = tf.keras.applications.MobileNetV2(input_tensor=input_layer,
	weights='imagenet',
	include_top=False)
	base_model.trainable = False
	x = tf.keras.layers.GlobalAveragePooling2D()(base_model.output)
	x = tf.keras.layers.Dense(2, activation='softmax')(x)

	model = tf.keras.models.Model(inputs=input_layer, outputs=x)

novasush / naive_approach.py

Created March 7, 2020 17:52

	dataset_name = 'cats_vs_dogs'
	filePath = f"{getcwd()}/../tmp2"
	dataset, info = tfds.load(name=dataset_name, split=tfds.Split.TRAIN, with_info=True, data_dir=filePath)

	print(info.version)

	def preprocess(features):
	image = features['image']
	image = tf.image.resize(image, (224, 224))
	image = image / 255.0

novasush / creating_dataset.py

Last active March 7, 2020 18:03



	file_pattern = f'{getcwd()}/../tmp2/{dataset_name}/{info.version}/{dataset_name}-train.tfrecord*'
	files = tf.data.Dataset.list_files(file_pattern)

novasush / parallelize_extraction.py

Created March 7, 2020 18:06

	# Parallelize the extraction of the stored TFRecords of
	# the cats_vs_dogs dataset by using the interleave operation with
	# cycle_length = 4 and the number of parallel calls set to tf.data.experimental.AUTOTUNE.
	train_dataset = files.interleave(tf.data.TFRecordDataset,
	cycle_length=4,
	num_parallel_calls=tf.data.experimental.AUTOTUNE)

novasush / read_tfrecord.py

Created March 7, 2020 18:09

	def read_tfrecord(serialized_example):

	# Create the feature description dictionary
	feature_description = {
	'image': tf.io.FixedLenFeature((), tf.string, ""),
	'label': tf.io.FixedLenFeature((), tf.int64, -1),
	}
	# Parse the serialized_example and decode the image
	example = tf.io.parse_single_example(serialized_example, feature_description)
	image = tf.io.decode_jpeg(example['image'], channels=3)

novasush / parallelize_transformation.py

Created March 7, 2020 18:12

	# Get the number of CPU cores.
	cores = multiprocessing.cpu_count()

	print(cores)

	# Parallelize the transformation of the train_dataset by using
	# the map operation with the number of parallel calls set to
	# the number of CPU cores.
	train_dataset = train_dataset.map(read_tfrecord,num_parallel_calls=cores)