News for hackers. Stuff that matters.

eagledotRL

Re:Show HN: Computer Vision Models for Developers on Saturday June 11, 2022 @12:02AM (#31701808)
Hi,

Almost All models are based on the Darknet[0] configurations which would come under this License[1]. We further trained/finetuned those architectures on additional datasets collected by us.

Whole framework actual used for final products is completely written in Nim.

[0] https://github.com/AlexeyAB/darknet [1] https://github.com/AlexeyAB/darknet/blob/master/LICENSE

Re:Show HN: Computer Vision Models for Developers on Friday June 10, 2022 @02:31PM (#31697747)
Hi HN, I am Anubhav from RamanLabs. We have been developing end to end Computer-vision modules to make it easy for developers, hobbyists to integrate such functionality into their applications with minimal amount of code.

All modules are developed to run real-time on consumer-grade CPUs[0]. For now we are releasing only Python-language SDK. Demos are provided to allow users to test performance on desired data-distribution.

Framework powering these modules in completely written in Nim language, which under the hood wraps some Operation's implementation provided by libraries like OpenBLAS/CuBlas.

We also maintain a blog[1] where we hope to share more underlying technical details.

[0] Quad-core CPU with AVX2 instructions.

[1] https://ramanlabs.in/static/blog

[2] https://ramanlabs.in/static/tutorial

Re: on Wednesday June 08, 2022 @03:23AM (#31664341)
Hi HN, I am Anubhav from RamanLabs. We have been developing end to end Computer-vision modules to make it easy for developers, hobbyists to integrate such functionality into their applications with minimal amount of code.

All modules are developed to run real-time on consumer-grade CPUs[0]. For now we are releasing only Python-language SDK. Demos are provided to allow users to test performance on desired data-distribution.

Framework powering these modules in completely written in Nim language, which under the hood wraps some Operation's implementation provided by libraries like OpenBLAS/CuBlas.

We also maintain a blog[1] where we hope to share more underlying technical details. Any feedback is welcome!

[0] Quad-core CPU with AVX2 instructions.

[1] https://ramanlabs.in/static/blog

[2] https://ramanlabs.in/static/tutorial

Hi,

Since i found it here on HN, it has been my goto language for all serious projects. Only respect and praise for Nim community ,I started by asking dumb questions on Nim channel, but someone was always there to help. Later I started using Nim for wrapping existing C libraries which allowed me to read codebases, i otherwise would not have read. Being able to write high level code and access memory directly where-ever necessary, hit a sweet spot for me. I recently started porting Code to use ARC, which has been really cool to play with and also provides out of the box automatic memory management for existing C code. Having a single codebase for cross-platform development has been a great help. Personally would like to use Metaprogramming, macros features for some complex cases , still learning about them.

I think i know you from Nim discord channel, I mainly spent time in Science channel. Thanks for your contributions and checking out the website!

Show HN: Integrate Computer-vision in your app with just 2 lines of code

https://ramanlabs.in

Hi HN, I am Anubhav from RamanLabs. We have been developing end to end Computer-vision modules to make it easy for developers, hobbyists to integrate such functionality into their applications with minimal amount of code.All modules are developed to run real-time on consumer-grade CPUs[0]. For now we are releasing only Python-language SDK. Demos are provided to allow users to test performance...

( Read More... | 2 comments | 5 points | on HN )
Re:Generate Python extensions using Nim language on Friday April 15, 2022 @11:22AM (#31041221)
Yes. community has been an outstanding factor in my whole journey of Nim so far.It becomes so easy to try out new features with such active feedback.

Show HN: Fast,Compiled deep-learning based modules for inferencing on CPUs

https://ramanlabs.in/static/products.html

Hi HN,I am Anubhav from RamanLabs.We have been developing dedicated modules based on deep-learning for purposes like face-detection,object-detection,pose-estimation etc.We hope to make it easy for developers,hobbyists to integrate such functionalities into their existing app/pipeline at the cost of a few milliseconds.All our modules run end to end in super-realtime even on consumer-grade...

( Read More... | no comments | 6 points | on HN )