Nitin Rai (@imneonizer) header
Nitin Rai (@imneonizer) profile picture

Making things smarter.

Hyderabad, India
Joined December 2014
Photo by Nitin Rai (@imneonizer)Photo by Nitin Rai (@imneonizer)Photo by Nitin Rai (@imneonizer)Photo by Nitin Rai (@imneonizer)Photo by Nitin Rai (@imneonizer)Photo by Nitin Rai (@imneonizer)Photo by Nitin Rai (@imneonizer)Photo by Nitin Rai (@imneonizer)Photo by Nitin Rai (@imneonizer)
How to build deep learning image dataset quickly? Answer: crawl images from yandex reverse image search results, for clean and meaningful images. I wrote my own crawler using selenium Inspired by @PyImageSearch Also i used PIL to verify images dimensions on the go instead.
3
20
144
Introducing: Few Shot Annotations You only draw 1-2 samples, and the tool will recognize it and automatically draw boxes / polygons around similar objects. app.algofly.ai
2
2
3
28
7,694
1/3 "if it works, don't touch it." AI agents changed that for me. They're generating feature updates so quickly that I can't realistically review every line anymore, even if I wanted to.
2
44
3/3 A year ago: Weekdays = coding Weekends = cleanup Today: Weekends = agents coding Weekdays = cleanup Not ideal. More debt. More tradeoffs. But we're shipping faster than ever, and for non-critical systems I think it's worth it.
29
2/3 AlgoFly AI's architecture took me 2 years to build. Most of the time Codex follows it surprisingly well. Sometimes it doesn't. I can usually spot the divergence, but I still want the feature shipped ASAP. That's the tradeoff.
33
Exciting time, so proud to have achieved this much on in house computer vision dataset management platform.
1
1
65
Is it me or is there really like computer vision market is bad right now because I was looking for some new opportunities and I don't find any.
28
🚀 Control your PC remotely with an ESP8266! Built a tiny module that connects to your motherboard + hosts a web app for real-time power control. ✅ On/off over Wi-Fi ✅ Great for servers/media centers 🔗 YT: lnkd.in/g8pnZE_W 💻 Code: lnkd.in/gA2XiGmr
2
63
Replying to @svpino @0xbnomial
Yes, I recommend! Thank you for this original service and for the quality of the question. I miss zero question until it starts! 😅
2
5
23
Nitin Rai retweeted
After talking to many machine learning engineers, only those at the top use this technique to train their models. Distribute training makes a world of difference. And contrary to what you may believe, anyone can start doing this immediately. A quick summary: 1 of 8
14
134
6
761
Finding of the day 🎉 Happy programming
Replying to @IrisClasson
And for anyone that doesn't know it: grep.app is a must have bookmark for anyone coding! Best code search I've ever used
3
Check out this project about controlling #ESP8266 aka #Node #MCU over wifi or cloud using #Micro #Python and #flask youtu.be/JaxmWng-6JI
2
Apollo has an onboard audio & video I/O system, and a base frame that allows it to stand upright, making it easy to work with. Apollo Video >> youtu.be/LLeaVO8_ffE Contact us >> [email protected] #edgecomputing #NLP #IVA #RIVAEmbedded #DeepStream #DevKit @NVIDIAEmbedded
2
3
Syntax highlighting is missing from the website @PyImageSearch It makes reading the code much harder
1
Also, there is no code block or segment so it gets mixed with the website content.
"Introduction to Deep Learning -- 170 Video Lectures from 𝐀daptive Linear Neurons to 𝐙ero-shot Classification with Transformers" Just organized all DL-related videos I recorded in 2021. Hoping it might be useful for one or the other person out there: sebastianraschka.com/blog/20…
43
603
34
2,236
Using PyTorch + NumPy? You're making a mistake. A bug that plagues thousands of open-source ML projects: tanelp.github.io/posts/a-bug…
14
196
34
997
Replying to @svpino
Since I skipped the ones for learning the language, my main reference is Effective Python. It's a great book if you already know Python and want to write better code.
2
9
112