Data Science | Machine Learning with Python for Researchers
31.7K subscribers
1.97K photos
102 videos
22 files
2.25K links
Admin: @HusseinSheikho

The Data Science and Python channel is for researchers and advanced programmers

Buy ads: https://telega.io/c/dataScienceT
Download Telegram
This media is not supported in your browser
VIEW IN TELEGRAM
NVIDIA just made Pandas 150x faster with zero code changes.

All you have to do is:
%load_ext cudf.pandas
import pandas as pd


Their RAPIDS library will automatically know if you're running on GPU or CPU and speed up your processing.

You can try it in this colab notebook

GitHub repo: https://github.com/rapidsai/cudf

https://t.iss.one/DataScienceT
πŸ‘7❀2
πŸͺž Mirror: A Universal Framework for Various Information Extraction Tasks

πŸ–₯ Github: https://github.com/Spico197/Mirror

πŸ“• Paper: https://arxiv.org/abs/2311.05419v1

🌐 Dataset: https://paperswithcode.com/dataset/glue

https://t.iss.one/DataScienceT
πŸ‘6❀2
⚑️ LCM-LoRA: A Universal Stable-Diffusion Acceleration Module

Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference.

pip install diffusers transformers accelerate gradio==3.48.0

πŸ–₯ Github: https://github.com/luosiallen/latent-consistency-model

πŸ“• Paper: https://arxiv.org/abs/2311.05556v1

🌐 Project: https://latent-consistency-models.github.io

πŸ€— Demo: https://huggingface.co/spaces/SimianLuo/Latent_Consistency_Model

https://t.iss.one/DataScienceT
πŸ‘3
Do you enjoy reading this channel?

Perhaps you have thought about placing ads on it?

To do this, follow three simple steps:

1) Sign up: https://telega.io/c/dataScienceT
2) Top up the balance in a convenient way
3) Create an advertising post

If the topic of your post fits our channel, we will publish it with pleasure.
πŸ‘4
πŸ”Š Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models

Π‘hat & pretrained large audio language model proposed by Alibaba Cloud.

🐱 Github: https://github.com/qwenlm/qwen-audio

πŸš€ Demo: https://qwen-audio.github.io/Qwen-Audio/

πŸ“• Paper: https://arxiv.org/abs/2311.07919v1

⏩ Dataset: https://paperswithcode.com/dataset/vocalsound

https://t.iss.one/DataScienceT
πŸ‘3
🌴Data Science A-Zβ„’: Hands-On Exercises & ChatGPT Bonus [2023]🌴

Learn
Data Science step by step through real Analytics examples. Data Mining, Modeling, Tableau Visualization and more!

Price :- 120$ - 20$

Price: 20$

Contact @hussein_sheikho
πŸ‘2
Inherently Interpretable Time Series Classification via Multiple Instance Learning (MILLET)

πŸ–₯ Github: https://github.com/jaearly/miltimeseriesclassification

πŸ“• Paper: https://arxiv.org/pdf/2311.10049v1.pdf

✨ Tasks: https://paperswithcode.com/task/decision-making

https://t.iss.one/DataScienceT
πŸ‘4
βž• SA-Med2D-20M Dataset: Segment Anything in 2D Medical Imaging with 20 Million masks

πŸ–₯ Github: https://github.com/OpenGVLab/SAM-Med2D

πŸ–₯ Colab: https://colab.research.google.com/github/OpenGVLab/SAM-Med2D/blob/main/predictor_example.ipynb

πŸ“• Paper: https://arxiv.org/abs/2311.11969v1

⭐️ Dataset: https://arxiv.org/abs/2311.11969
πŸ‘7❀2
This media is not supported in your browser
VIEW IN TELEGRAM
πŸ”₯ flowty-realtime-lcm-canvas

A realtime sketch to image demo using LCM and the gradio library.

Source: https://github.com/flowtyone/flowty-realtime-lcm-canvas

πŸ‘Œ https://t.iss.one/CodeProgrammer

More Likes, Share, Subscribe πŸ˜‰β€οΈ
πŸ‘1
πŸ—£ HierSpeech++: Bridging the Gap between Semantic and Acoustic Representation by Hierarchical Variational Inference for Zero-shot Speech Synthesis

πŸ–₯ Code: https://github.com/sh-lee-prml/hierspeechpp

🦾 Checkpoint: https://drive.google.com/drive/folders/1-L_90BlCkbPyKWWHTUjt5Fsu3kz0du0w?usp=sharing

⚑️ Demo: https://sh-lee-prml.github.io/HierSpeechpp-demo/

πŸ“š Paper: https://arxiv.org/abs/2311.12454v1

πŸ”— Dataset: https://paperswithcode.com/dataset/libri-light

https://t.iss.one/DataScienceT
ChessVision - A dataset for logically coherent multi-label classification.

πŸ–₯ Github: https://github.com/espressovi/chessvisionchallenge

πŸ“• Paper: https://arxiv.org/pdf/2311.12610v1.pdf

✨ Tasks: https://paperswithcode.com/task/classification-1

https://t.iss.one/DataScienceT
πŸ‘1
πŸ”₯ Diffusion360: Seamless 360 Degree Panoramic Image Generation based on Diffusion Models.

πŸ–₯ Code: https://github.com/archerfmy/sd-t2i-360panoimage

πŸ“š Paper: https://arxiv.org/abs/2311.13141v1

πŸ”— Dataset: https://paperswithcode.com/dataset/sun360

https://t.iss.one/DataScienceT
πŸ‘3