Data Science by ODS.ai 🦜

2021-09-10 20:51:26 ​​iRobot with poop detection

iRobot (company building cleaning house robots) had a problem with robots regarding pet poops. So they built a special model along with physical models of poop to test the product.

iRobot official YouTube:


TechCrunch: https://techcrunch.com/2021/09/09/actuator-4/

#aiproduct #marketinggurus Open / Comment

2021-09-08 22:01:41 New German V4 Model and English V5 Models

New and improved models in Silero-models! Community edition versions available here: https://github.com/snakers4/silero-models

Huge performance improvements for two new models:

- English V5 (quality)
- German V3 (quality)

The models currently are available in the following flavors:

- English V5 jit (small), onnx (small), jit_q (small, quantized), jit_xlarge, onnx_xlarge
- German V3 jit_large, onnx_large

The xsmall model family for English in on the way.

The quality growth visualization: Open / Comment

2021-08-26 13:16:58 ​​ Breeaking news!

Big project, first public release! From the creator of FastAPI and Typer: SQLModel.

SQLModel is a library for interacting with SQL databases from Python code, with Python objects. It is designed to be intuitive, easy to use, highly compatible, and robust.

SQLModel is based on Python type annotations, and powered by Pydantic and SQLAlchemy.
SQLModel is, in fact, a thin layer on top of Pydantic and SQLAlchemy, carefully designed to be compatible with both.

The key features are:
- Intuitive to write: Great editor support. Completion everywhere. Less time debugging. Designed to be easy to use and learn. Less time reading docs.
- Easy to use: It has sensible defaults and does a lot of work underneath to simplify the code you write.
- Compatible: It is designed to be compatible with FastAPI, Pydantic, and SQLAlchemy.
- Extensible: You have all the power of SQLAlchemy and Pydantic underneath.
- Short: Minimize code duplication. A single type annotation does a lot of work. No need to duplicate models in SQLAlchemy and Pydantic.

https://github.com/tiangolo/sqlmodel Open / Comment

2021-08-24 13:20:48 Structure-aware Interactive Graph Neural Networks for the Prediction of Protein-Ligand Binding Affinityv

#Baidu research proposed a structure-aware interactive graph neural network ( #SIGN ) to better learn representations of protein-ligand complexes, since drug discovery relies on the successful prediction of protein-ligand binding affinity.

Link: https://dl.acm.org/doi/10.1145/3447548.3467311

#biolearning #deeplearning Open / Comment

2021-08-18 11:56:38 ​​Program Synthesis with Large Language Models

Paper compares models used for program synthesis in general purpose programming languages against two new benchmarks, MBPP (The Mostly Basic Programming Problems) and MathQA-Python, in both the few-shot and fine-tuning regimes.

MBPP contains 974 programming tasks, designed to be solvable by entry-level programmers. MathQA benchmark, contains 23914 problems that evaluate the ability of the models to synthesize code from more complex text.

Largest fine-tuned model achieves 83.8 percent accuracy on the latter benchmark.

Why this is interesting: better models for code / problem understanding means improved search for the coding tasks and the improvement of the coding-assistant projects like #TabNine or #Copilot

ArXiV: https://arxiv.org/abs/2108.07732

#DL #NLU #codewritingcode #benchmark Open / Comment

2021-08-17 01:02:06 14 seconds of April #Nvidia 's CEO speech was generated in silico

Why this important: demand for usage of 3080 and newer GPU models might also get pumped by CGI artists and researchers working in VR / AR tech.

And this raises the bar for #speechsinthesis / #speechgeneration and definately for the rendering of photorealistic picture.

YouTube making of video:


Vice article on the subject: https://www.vice.com/en/article/88nbpa/nvidia-reveals-its-ceo-was-computer-generated-in-keynote-speech Open / Comment

2021-08-15 14:58:49 ​​Domain-Aware Universal Style Transfer

Style transfer aims to reproduce content images with the styles from reference images. Modern style transfer methods can successfully apply arbitrary styles to images in either an artistic or a photo-realistic way. However, due to their structural limitations, they can do it only within a specific domain: the degrees of content preservation and stylization depends on a predefined target domain. As a result, both photo-realistic and artistic models have difficulty in performing the desired style transfer for the other domain.

The authors propose Domain-aware Style Transfer Networks (DSTN) that transfer not only the style but also the property of domain (i.e., domainness) from a given reference image. Furthermore, they design a novel domainess indicator (based on the texture and structural features) and introduce a unified framework with domain-aware skip connection to adaptively transfer the stroke and palette to the input contents guided by the domainness indicator.

Extensive experiments validate that their model produces better qualitative results and outperforms previous methods in terms of proxy metrics on both artistic and photo-realistic stylizations.

Paper: https://arxiv.org/abs/2108.04441

Code: https://github.com/Kibeom-Hong/Domain-Aware-Style-Transfer

A detailed unofficial overview of the paper: https://andlukyane.com/blog/paper-review-dstn

#deeplearning #cv #styletransfer Open / Comment

2021-08-12 11:14:20 ​​Virtual fitting room launched by our friends

#in3D launched a 3D virtual fitting room with Replicant Fashion house. 30+ designers, 60+ looks.

Great example of the AI-driven product!

Desktop: https://www.replicant.fashion/digitaltwin
iPhone: https://apps.apple.com/us/app/in3d-3d-body-scanning/id1467153183

#aiproduct #fitting #metaverse Open / Comment

2021-08-09 09:52:00 Tokyo Olympics Alternative medals table

Article on how teams performed with the respect to behavior expected by regression model.

Link: https://ig.ft.com/tokyo-olympics-alternative-medal-table/ Open / Comment

2021-08-03 09:52:00 Online Berkeley Deep Learning Lectures 2021

University of Berkeley released its fresh course lectures online for everyone to watch. Welcome Berkeley CS182/282 Deep Learnings - 2021!

YouTube: https://www.youtube.com/playlist?list=PLuv1FSpHurUevSXe_k0S7Onh6ruL-_NNh

#MOOC #wheretostart #Berkeley #dl Open / Comment