<?xml version="1.0" encoding="UTF-8"?><rss xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:atom="http://www.w3.org/2005/Atom" version="2.0" xmlns:cc="http://cyber.law.harvard.edu/rss/creativeCommonsRssModule.html">
    <channel>
        <title><![CDATA[Stories by Lokesh Soni on Medium]]></title>
        <description><![CDATA[Stories by Lokesh Soni on Medium]]></description>
        <link>https://medium.com/@lokeshsonii?source=rss-d7fd36562d14------2</link>
        <image>
            <url>https://cdn-images-1.medium.com/fit/c/150/150/1*Isda-4oIjdIa-r4fIVhpNQ.jpeg</url>
            <title>Stories by Lokesh Soni on Medium</title>
            <link>https://medium.com/@lokeshsonii?source=rss-d7fd36562d14------2</link>
        </image>
        <generator>Medium</generator>
        <lastBuildDate>Fri, 20 Nov 2026 00:17:16 GMT</lastBuildDate>
        <atom:link href="https://medium.com/@lokeshsonii/feed" rel="self" type="application/rss+xml"/>
        <webMaster><![CDATA[yourfriends@medium.com]]></webMaster>
        <atom:link href="http://medium.superfeedr.com/" rel="hub"/>
        <item>
            <title><![CDATA[Computer Vision for Everyone]]></title>
            <link>https://medium.com/@lokeshsonii/computer-vision-for-everyone-9f1f05219bea?source=rss-d7fd36562d14------2</link>
            <guid isPermaLink="false">https://medium.com/p/9f1f05219bea</guid>
            <category><![CDATA[deep-learning]]></category>
            <category><![CDATA[machine-learning]]></category>
            <category><![CDATA[computer-vision]]></category>
            <category><![CDATA[google-cloud-platform]]></category>
            <dc:creator><![CDATA[Lokesh Soni]]></dc:creator>
            <pubDate>Fri, 30 Aug 2019 08:49:56 GMT</pubDate>
            <atom:updated>2019-09-06T20:51:31.027Z</atom:updated>
            <content:encoded><![CDATA[<p>Hello, I’m Lokesh Soni and this is my first post off the many upcoming posts on How-Tos, Hacks, Comparisons and Best Practices. I’m a Computer Vision Engineer by profession and problem-solver by heart. I was talking to a friend lately who’s an awesome developer and wanted to learn Machine Learning as its one of the coolest thing happening around. After a lot of discussions on where to start, I gave him a piece of advice on integrating ML in his projects without knowing ML. Yes, that’s what I’m going to focus in this post. This was supposed to be ML for everyone but since I’ll be taking an example of Image Classification, hence the title.</p><p>Here are some of the ways using which you can use ML coming from different backgrounds of Software Development Track.</p><p><strong>Google Cloud Vision API</strong></p><p>Vision API (along with other ML APIs) by Google Cloud offers powerful ML models through REST and RPC APIs. It can do a lot of tasks like classify your images into millions of predefined categories, detect objects and faces, read printed and handwritten text (YES!!), etc. This is for the developers who don’t have any knowledge of ML yet can build powerful apps using it.</p><p>Pro Tip: If you want to classify pizza vs burger or something general, then this is your guy who’ll do the job at a very less cost and no effort!</p><p>You can try out a demo at this link and refer the docs for further integration with your app.</p><p><a href="https://cloud.google.com/vision/#vision-api-demo">Vision AI | Derive Image Insights via ML | Google Cloud</a></p><p>Also, the pricing is pretty reasonable!</p><p><a href="https://cloud.google.com/vision/pricing">Pricing | Cloud Vision API | Google Cloud</a></p><p><strong>AutoML Vision</strong></p><p>Although much of the things can be done by <strong>Vision API, </strong>you might fall into a requirement of differentiating between your dog and your friend’s dog as a use case in your app. Since the Vision API is meant to be more generalized, in specific situations like these it fails to differentiate. In this case, you can train a custom model to do the same without knowing ML!! What??? Train a model without knowing ML? Yes, you heard right! This is another product by Google Cloud offering you to train a custom model which suits your requirements! All you have to do here is grab a bunch of images of different classes you want to classify and boom! You can upload the images using the AutoML Vision Console and just hit the Train button. It trains a custom model trying all possible pre-trained models and gives you a model which you can use through REST and RPC APIs. Additionally, it also provides a model for offline use in Android, iOS and edge devices by automatically converting the model in the required format (tflite) to be used offline for low latency purposes.</p><p>Start here:</p><p><a href="https://cloud.google.com/automl/ui/vision/">Google Developers</a></p><p><strong>TensorFlow and Cloud ML Engine</strong></p><p>You might ask what’s the role of a Computer Vision Engineer when Vision API and AutoML is already there! Ok, so you have a model which is trained on AutoML on the custom classes (your dog and your friend’s) you provided but when you want to cross that extra mile of accuracy, that’s where you have the choice of having your own custom model, typically CNNs in this case. You have control of preprocessing your images, training different models and getting extra accuracy. That’s where you have to learn TensorFlow and become a full-time ML Engineer :). Here you have to manage everything on your own including collecting and formatting data, training and serving at the app (More on that in the upcoming posts!).</p><p>Hope, I managed to save my job at the end of this post and give you a good brief about different ways to integrate ML in your app!</p><figure><a href="https://usejournal.com/?utm_source=medium.com&amp;utm_medium=noteworthy_blog&amp;utm_campaign=tech&amp;utm_content=guest_post_image"><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*PYxBP_WV7LI6zc-zdUkNqQ.png" /></a></figure><p>📝 Read this story later in <a href="https://usejournal.com/?utm_source=medium.com&amp;utm_medium=noteworthy_blog&amp;utm_campaign=tech&amp;utm_content=guest_post_read_later_text">Journal</a>.</p><p>👩‍💻 Wake up every Sunday morning to the week’s most noteworthy stories in Tech waiting in your inbox. <a href="https://usejournal.com/newsletter/noteworthy-in-tech/?utm_source=medium.com&amp;utm_medium=noteworthy_blog&amp;utm_campaign=tech&amp;utm_content=guest_post_text">Read the Noteworthy in Tech newsletter</a>.</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=9f1f05219bea" width="1" height="1" alt="">]]></content:encoded>
        </item>
    </channel>
</rss>