Machinelearning – Telegram
383K subscribers
4.45K photos
858 videos
17 files
4.89K links
Погружаемся в машинное обучение и Data Science

Показываем как запускать любые LLm на пальцах.

По всем вопросам - @haarrp

@itchannels_telegram -🔥best channels

Реестр РКН: clck.ru/3Fmqri
Download Telegram
💬 A Text Attention Network for Spatial Deformation Robust Scene Text Image Super-resolution

Github: https://github.com/mjq11302010044/tatt

Paper: https://arxiv.org/abs/2203.09388v2

Dataset:
https://deepchecks.com/blog/

@ai_machinelearning_big_data
9👍2🔥1
💭 NeuralSpeech is a research project in focusing on neural network based speech processing

Github: https://github.com/microsoft/NeuralSpeech

Paper: https://arxiv.org/pdf/2109.14420v3.pdf

Speech Research: https://speechresearch.github.io/

Dataset:
https://paperswithcode.com/dataset/aishell-1

@ai_machinelearning_big_data
👍81🔥1
🔎 BigDetection: A Large-scale Benchmark for Improved Object Detector Pre-training

Github: https://github.com/amazon-research/bigdetection

Paper: https://arxiv.org/abs/2203.13249v1

Dataset:
https://paperswithcode.com/dataset/lvis

@ai_machinelearning_big_data
11👍1
SuperGAT

A self-supervised graph attention network (SuperGAT), an improved graph attention model for noisy graph

Code: https://github.com/dongkwan-kim/SuperGAT

Paper: https://arxiv.org/abs/2204.04879v1

Dataset: https://paperswithcode.com/dataset/ogb

@ai_machinelearning_big_data
🔥9👍2
🔥 DALL·E 2

DALL·E 2 is a new AI system that can create realistic images and art from a denoscription in natural language.

Openai: https://openai.com/dall-e-2/

Paper: https://cdn.openai.com/papers/dall-e-2.pdf

Video: https://vimeo.com/692375454

@ai_machinelearning_big_data
🔥45👍3👎1
🔗 Unsupervised Image-to-Image Translation with Generative Prior

A novel framework GP-UNIT, to improve the overall quality and applicability of the translation algorithm

Github: https://github.com/williamyang1991/gp-unit

Paper: https://arxiv.org/abs/2204.03641v1

Datasett: https://paperswithcode.com/dataset/celeba-hq

@ai_machinelearning_big_data
👍10🔥31
✏️ Sat2lod2: A Software For Automated Lod-2 Modeling From Satellite-Derived Orthophoto And Digital Surface Model

The proposed method starts building detection results through a deep learning-based detector and vectorizes individual segments into polygons using a “three-step” polygon extraction method

Github: https://github.com/gdaosu/lod2buildingmodel

Paper: https://arxiv.org/abs/2204.04139v1

Datasett: https://drive.google.com/file/d/1rA7SRPbSYFJwOBc7IfXxBgmUroTOZIOF/view?usp=sharing

Video: https://youtu.be/Nn4OABsEOXk

@ai_machinelearning_big_data
👍72
✏️ Sat2lod2: A Software For Automated Lod-2 Modeling From Satellite-Derived Orthophoto And Digital Surface Model

The proposed method starts building detection results through a deep learning-based detector and vectorizes individual segments into polygons using a “three-step” polygon extraction method

Github: https://github.com/jingkang50/openood

Paper: https://arxiv.org/abs/2204.05306v1

Dataset: https://entuedu-my.sharepoint.com/:f:/g/personal/jingkang001_e_ntu_edu_sg/Eso7IDKUKQ9AoY7hm9IU2gIBMWNnWGCYPwClpH0TASRLmg?e=iEYhXO

More tutorials: https://github.com/Jingkang50/OpenOOD/wiki/Get-Started

@ai_machinelearning_big_data
👍7
👍8