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

Hi Anubhav, are all modules built by your team? Since if it were based on already available models/repos, then I can't find licenses/attr for the same.

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