Data Science | Machine Learning with Python for Researchers
31.8K subscribers
2.08K photos
102 videos
22 files
2.36K 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
PIA: Your Personalized Image Animator via Plug-and-Play Modules in Text-to-Image Models ๐ŸŽ„ ๐ŸŽ ๐ŸŽ… Colab ๐Ÿฅณ

๐ŸŽ“ page: https://pi-animator.github.io

๐Ÿ“š paper: https://arxiv.org/abs/2312.13964

๐Ÿ–ฅ code: https://github.com/open-mmlab/PIA
๐Ÿฅฉ OpenXLab: https://openxlab.org.cn/apps/detail/zhangyiming/PiaPia

๐Ÿฅฉ colab: https://github.com/camenduru/PIA-colab

https://t.iss.one/DataScienceT
๐Ÿ‘5
Repaint123: Fast and High-quality One Image to 3D Generation with Progressive Controllable 2D Repainting

๐Ÿ–ฅ Github: https://github.com/junwuzhang19/repaint123

๐Ÿ“• Paper: https://arxiv.org/pdf/2312.13271v1.pdf

๐Ÿ”ฅ Dataset: https://paperswithcode.com/dataset/nerf

https://t.iss.one/DataScienceT
๐Ÿ‘7
This media is not supported in your browser
VIEW IN TELEGRAM
๐ŸŒ AnyDoor: Zero-shot Object-level Image Customization

pip install git+https://github.com/cocodataset/panopticapi.git

pip install pycocotools -i https://pypi.douban.com/simple

pip install lvis


๐Ÿ–ฅ Code: https://github.com/damo-vilab/AnyDoor

๐ŸŽ“ HF: https://huggingface.co/spaces/xichenhku/AnyDoor-online

๐Ÿ”ฎ Project Page: https://damo-vilab.github.io/AnyDoor-Page/

๐Ÿ“š ArXiv: https://arxiv.org/abs/2307.09481

https://t.iss.one/DataScienceT
๐Ÿ‘4๐Ÿ‘Ž1
๐ŸFerret: Refer and Ground Anything Anywhere at Any Granularity

๐Ÿ–ฅ Code: github.com/apple/ml-ferret

๐ŸŽ“ Paper: https://arxiv.org/abs/2310.07704

https://t.iss.one/DataScienceT
LaneSegNet: Map Learning with Lane Segment Perception for Autonomous Driving

๐Ÿ–ฅ Github: https://github.com/OpenDriveLab/LaneSegNet

๐Ÿ“• Paper: https://arxiv.org/abs/2312.16108v1

๐Ÿ”ฅDatasets: https://paperswithcode.com/dataset/openlane-v2

https://t.iss.one/DataScienceT
๐Ÿ‘3
This media is not supported in your browser
VIEW IN TELEGRAM
๐ŸŒน4DGen: Grounded 4D Content Generation with Spatial-temporal Consistency

๐Ÿ–ฅ Code: https://github.com/VITA-Group/4DGen

๐Ÿ”ฎ Project: https://vita-group.github.io/4DGen/

๐Ÿ“š ArXiv: https://arxiv.org/abs/2305.06456
โค2๐Ÿ‘2
โœ”๏ธ AIJack: Security and Privacy Risk Simulator for Machine Learning

Security and Privacy Risk Simulator for Machine Learning.

pip install git+https://github.com/Koukyosyumei/AIJack

๐Ÿ–ฅ Code: https://github.com/microsoft/promptbench

๐ŸŒŸ Docs: https://promptbench.readthedocs.io/en/latest/

๐Ÿ“š Paper: https://arxiv.org/abs/2312.07910v1

โšก๏ธ Dataset: https://paperswithcode.com/dataset/mmlu

https://t.iss.one/DataScienceT
๐Ÿ‘5โค1