Hacker News Reader

rozgoon Real time image animation in opencv using first order model

Oh, I'm interested. Thanks for letting me know. Would love to contribute.

rozgoon Real time image animation in opencv using first order model

This model is trained with short clips of human speech. There is enough statistical information to "guess" how to fill the gap created by opened lips. I'm still amazed how it conserves temporal coherence (what it looks like from frame to frame).

rozgoon Real time image animation in opencv using first order model

It's incredibly satisfying to reproduce these papers. I now make Rust versions of the most interesting projects. And try to make low-latency inference pipelines for those that show potential for real-time use. Some are sketched out here: https://github.com/Simbotic/SimboticTorch

The bulk of the work to get real-time working is to move more of pipeline to GPU. Mostly things handled by numpy and some image/video transformations.

rozgoon Real time image animation in opencv using first order model

I'm working with same model, but in a real-time pipeline developed with GStreamer, Rust and PyTorch:

https://twitter.com/rozgo/status/1255961525187235842

Live motion transfer test with crappy webcam:

https://youtu.be/QVRpstP5Qws

rozgoon John Carmack is reading and contributing to OpenBSD source code

The road to AGI is paved with yak shavings.

rozgoon Ask HN: What's your quarantine side project?

https://youtu.be/QVRpstP5Qws

Using my own face live through webcam.

rozgoon Ask HN: What's your quarantine side project?

https://twitter.com/rozgo/status/1255961525187235842

Real-time avatars with our deep computer vision pipeline; developed with GStreamer, Rust and LibTorch. This CV pipeline is usually used for training robots inside simulations and generating synthetic datasets. But given the circumstances, thought it would be fun to explore other use cases.

rozgoon Ask HN: What is your ML stack like?

I'm building these labs/teams in Latin America, with a few remote people from around the world. Ping me at: alex.rozgo @ vertexstudio.co

rozgoon Ask HN: What is your ML stack like?

Quadcopters, railway vehicles and perching devices.

rozgoon Ask HN: What is your ML stack like?

Traditional simulations don’t translate well. Usually one has to choose a fidelity level; controls, navigation, exploration, mission, etc… We are having more success with models that can tolerate variable dynamics. Simulations don't need to be realistic, only consistent. We then reinforce models with an infinite number of simulation universes and rules, such that reality is just another sample. We don’t have the resources for end-to-end training, and our initial tests did not yield good results. But chaining smaller specific-purpose networks within traditional control and planning systems is looking really good.

rozgoon Ask HN: What is your ML stack like?

Out of Central America. https://vertexstudio.co/

rozgoon Ask HN: What is your ML stack like?

Custom Unreal Engine simulator, simulating agents with NVidia Physx and publishing sensors through GStreamer. GStreamer has sinks and sources for ROS, and tensorflow elements for inferencing. We package this all into NVidia Docker for scalable simulations. Setup is similar for training and inference. The core framework is a streaming engine with stream combinators that enable reasoning about spatio-temporal data streams. Where each datum is related to a point in space and time. The goal is for tensors to be the streaming primitives, but the pipeline is still fragile, it’s a challenge to keep all this working with so many core technologies changing constantly (UE4 + Physx + Cuda + CuDNN + Tensorflow + …). We train robots in simulation.

Most of our tools are built in Rust. Several of those are for creating(cleaning) data streams out of datasets. They are converted into tensors or ROS messages.

rozgoon Building a Kickass Portfolio

Dynamical systems engineer for games and simulations. Portfolio out of necessity, because I've never been good at explaining with words what I do.

https://rozgo.github.io/

rozgoon Building a Kickass Portfolio

https://rozgo.github.io/

I try. Dynamical systems engineer is difficult to describe with text.