Data Science | Machine Learning with Python for Researchers
31.7K subscribers
1.79K photos
102 videos
22 files
2.07K 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
🧩 Building LEGO for 3D Reconstruction on Mobile Devices

A novel data capturing and 3D annotation pipeline in MobileBrick without relying on expensive 3D scanners.

πŸ–₯ Github: https://github.com/ActiveVisionLab/MobileBrick

⏩ Paper: https://arxiv.org/abs/2303.01932

⭐️ Dataset: https://www.robots.ox.ac.uk/~victor/data/MobileBrick/MobileBrick_Mar23.zip

πŸ’¨ Project: https://code.active.vision/MobileBrick/

https://t.iss.one/DataScienceT
❀5πŸ‘2
Ultra fast ControlNet with 🧨 Diffusers

ControlNet provides a minimal interface allowing users to customize the generation process up to a great extent.

πŸ€— Hugging face blog: https://huggingface.co/blog/controlnet

πŸ–₯ Colab: https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/controlnet.ipynb

πŸ–₯ Github: https://github.com/lllyasviel/ControlNet

⏩ Paprer: https://arxiv.org/abs/2302.05543

https://t.iss.one/DataScienceT
❀‍πŸ”₯6❀1
⭐️ SplineCam: Exact Visualization and Characterization of Deep Network Geometry and Decision Boundaries, CVPR 2023

Exact method for computing partitions of a Deep Neural Network

πŸ–₯ Github: https://github.com/AhmedImtiazPrio/SplineCAM

πŸ–₯ Colab: https://bit.ly/splinecam-demo

⏩ Paper: https://arxiv.org/pdf/2302.12828.pdf

⭐️ Project: https://imtiazhumayun.github.io/splinecam

https://t.iss.one/DataScienceT
❀‍πŸ”₯6
Preference Transformer: Modeling Human Preferences using Transformers for RL (ICLR 2023)

πŸ–₯ Github: https://github.com/csmile-1006/preferencetransformer

⏩ Paper: https://arxiv.org/abs/2303.00957v1

https://t.iss.one/DataScienceT
❀‍πŸ”₯4❀2πŸ‘1
Handwritten Digit Recognition with LeNet5 Model in PyTorch

by Adrian Tam on March 8, 2023 in Deep Learning with PyTorch

πŸ”—: https://machinelearningmastery.com/handwritten-digit-recognition-with-lenet5-model-in-pytorch

https://t.iss.one/DataScienceT
❀‍πŸ”₯5❀1
πŸ’¬ GLIGEN: Open-Set Grounded Text-to-Image Generation

GLIGEN’s zero-shot performance on COCO and LVIS outperforms that of existing supervised layout-to-image baselines by a large margin. Code comming soon.

⭐️ Project: https://gligen.github.io/

⭐️ Demo: https://aka.ms/gligen

βœ…οΈ Paper: https://arxiv.org/abs/2301.07093

πŸ–₯ Github: https://github.com/gligen/GLIGEN

https://t.iss.one/DataScienceT
❀‍πŸ”₯4