Image for post
Image for post
Photo by 𝚂𝚒𝚘𝚛𝚊 𝙿𝚑𝚘𝚝𝚘𝚐𝚛𝚊𝚙𝚑𝚢 on Unsplash

In this article, I will introduce basic knowledge of Tensorflow to the real example of Tensorflow.

I will recommend you to read this article if you haven’t read it.

Above article will help you to learn the basic math operations in Tensorflow. It will be good to have work with session and placeholder.

Let’s move to the

We have 28*28 = 784 pixels of the images. In training.csv we have the correct digit of the number. We will create a model based on the training.csv file and will submit the output of the predicted values on testing.csv file.

# seperating labels and images [X_train = images, Y_train = numbers on respective image]
X_train = train_df.drop(labels = ["label"],axis = 1) # contains values of digits in 255 range
Y_train = train_df['label'] # contains digits
X_train = X_train.values.reshape(-1,28,28,1)/ 255 # reshaping arrays in…

Image for post
Image for post
Photo by Drew Beamer on Unsplash

Well, in this world, everyone has some habits. Good habits/bad habits. Good habits are like stepper that keeps us up every day.

Those who are using smartphones, have the habit to check the phone every 5 minutes. That obviously disturb our mind, At a result, It comes methodology like a lake of focus, less productivity and anxiety. Many people ignore other, short term relationships etc blah blah blah. So how can we challenge improve this and make commit to use cell-phone less? Try yourself, you will be okay for not using phone for three days but then..? …


Image for post
Image for post
Photo by Marco Zoppi on Unsplash

Hello, welcome to this article. In this article, I will discuss NLP API of ML-Kit and common details of cloud and firebase and where to start with ML-Kit.

Introduction

Firebase first initiated in 2011 by two tech-professionals James Tamplin and Andrew Lee. Goal to create firebase is to provide API that synchronizes application data across iOS, Android and web services, the first product of firebase is Firebase Real-time Database. Later on, in 2014, it is acquired by Goolge. As of March 2020, Firebase platform has 19 products, which are used by more than 1.5 millions of apps. ML-Kit is announced in Google IO 2018. The main focus area for this API is to use the Machine learning pre-trained model on cloud and on-device in smaller devices. It also supports custom models. As in the cons part, while using a custom model, application size increase largely. …


Approve your agent in the production without rejection

Image for post
Image for post
Photo by Olav Ahrens Røtne on Unsplash

Hi folks, I’m writing this article to cover various points which needs to be taken care of while submitting your Actions (Action for Google Assistant) for review in order to avoid rejection. So without wasting time lets Start :-)

This is the story when I was developing and publishing ML Wordtoit — Chatbot that helps with vocabularies of Machine learning. I got this email when I first submitted my agent.

Image for post
Image for post

I improved and passed it by the following steps…

#1. Don’t let mic open

If you have chosen Dialogflow as your building action then make sure your using suggestion chips in order to let the user know that mic is still open or action is waiting for your next instruction. In case you do not want any suggestion chips assuming it is the end of conversation do not forget to close the mic by toggling the button on placed at the bottom of response tab. …


Recap: plan — > work — >result => summary

Image for post
Image for post
Photo by Suzanne D. Williams on Unsplash

Around the same days last year, I listened a podcast new year resolutions podcast of super-datascience and made my plan to do it in 2018. I managed almost all significant tasks at the end of the year. Here are some points how I managed to succeed it.

Every morning, on a working day, I made a plan. Task(s) that were not completed, that moved to the weekend. I listed out 5 tasks, but somehow not every task get done. This year I will make it three so that workflow will be constant. …


Image for post
Image for post
Tensorflow step by step (Source)

Machine Learning is making a boom in the tech world, specifically for the developers and for the talented data scientists. We will never learn new things if we don’t start it from the bottom. In this article, we are striking at the root of Tensorflow. After reading this article you will be able to perform some basic mathematical operations in Tensorflow.

Where it starts?

Tensorflow was published in November 2015 by the Google Brain Team and currently Tensorflow 1.5 version is the latest release with Tensorflow lite, announced for mobile and embedded devices.

Tensor is a multidimensional array. Nodes in the graph (aka ops or operations) perform mathematical computations and produce the tensors. …


Image for post
Image for post

Machine learning is trending topic for data-scientist, developers and researchers. Before, going into machine learning, first understand basic concepts about machine learning with it’s most used phrases.

Why we need machine learning?

People watch lots of science fiction movies, Iron-Man, Her, I-Robot etc. All those movies have character of machine that can interact like human. For achieving that part in real life we use a technique name as machine learning. We also succeed in some area, where user speak a command, machine will understand that command and give some output. e.g., …

About

Krunal Kapadiya

Machine Learning Facilitator | Google Certified Android Developer | Engineer @ClarionTechnologies https://krunal3kapadiya.app/

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store