Недавно я вдруг поняла, что в телеграме можно делать вот такие гифки из стикеров и фото.

Люди целые мультики с этим инструментом делают в блендере

С удивлением обнаружил, что ещё есть люди, которые не в курсе, и просто хотел напомнить, что в блендере есть crease pencil.

Джама давно его форсил, и сейчас ещё вот этот чувак появился, видео его же.

Вообще, туторов, конечно, полно, и инструмент в концептинге полезный.

Ооочень интересная новинка от Facebook AI research.

Мокап система на основе анализа видео. Можно получить отдельно тело, отдельно руки или тело и руки вместе.

Кто разберётся и потестит, покажите результаты, хочется глянуть.

https://github.com/facebookresearch/frankmocap

GAN sculptures
#gan #machine_learning #3d #generative
https://studioanf.com/ai-sculptures/

enjoying it means you are at right level, anxiety means you are fighting a difficult task. boredom is it's too easy for you and you need to make things difficult for yourself to advance

SimCLR

Abstract
SimCLR is a simple framework for contrastive learning of visual representations. We simplify recently proposed contrastive self-supervised learning algorithms without requiring specialized architectures or a memory bank. In order to understand what enables the contrastive prediction tasks to learn useful representations, we systematically study the major components of our framework.
We show that (1) composition of data augmentations plays a critical role in defining effective predictive tasks, (2) introducing a learnable nonlinear transformation between the representation and the contrastive loss substantially improves the quality of the learned representations, and (3) contrastive learning benefits from larger batch sizes and more training steps compared to supervised learning. By combining these findings, we are able to considerably outperform previous methods for self-supervised and semi-supervised learning on ImageNet. A linear classifier trained on self-supervised representations learned by SimCLR achieves 76.5% top-1 accuracy, which is a 7% relative improvement over previous state-of-the-art, matching the performance of a supervised ResNet-50. When fine-tuned on only 1% of the labels, we achieve 85.8% top-5 accuracy, outperforming AlexNet with 100X fewer labels.

* Available in pytorch-lightning-bolts with a couple of code lines
* Paper
* Colab implementation
* Explanation and implementation details in a series of short videos
#self_supervised

NYC Deep Learning Course: Structured Prediction

Final lecture of the course on deep learning led by Yann LeCun. It covers structured prediction, energy-based factor graphs, and graph transformer networks.

https://poloclub.github.io/ganlab/
Милая интерактивная демка с объяснением ганов на tf.js.

Flame plugin for blender for random face expression and random face generation
#morphable_model