DeepWorks

DeepWorks By Avkash Chauhan (@avkashchauhan)

 DeepWorks

A collection of Deep Learning projects  and resources
Join my @Prodramp YouTube Channel for  all things about Data Science, machine learning and Artificial Intelligence and technology.                 

Among the Upcoming Deep Learning repository on GitHub and YouTube Channel     

@Prodramp YouTube channel - Please visit YouTube channel to watch all the videos specific the GitHub content you find in this GitHub repo

---

Developer Program

• Developer Program

• Data Processing course in Python for budding Python Developers - 4 Parts

• Developing Gradio Based Tabbed UI - 2 Parts

• Creating Python Module, Packaging it as Wheel Package, Delivery and Istallation - 3 Parts

• Rust By ChatGPT

• Statistics of Machine Learning

Deep learning Workshop(s)

• [1] Processing Satellite Imagery to Identify various landmarks (4 Hours in 3 Videos)

• Part 1. Satellite Imagery Data Processing

• Part 2. Appling Deep Learning methods on Satellite Imagery Data

• Part 3. Model Deployment and Various other tasks

LLM and OpenSource Models

• LLM Research and Opensource LLM Models

Exciting NeRF Projects and OpenSource Models

• NeRF Research and Opensource NeRF Models

Generative AI - Art, Content, Media

• Whiteboarding - Understanding ChatGPT

• Whiteboarding - Understanding LLM Tech Stack

• Developing ChatGPT style Enterprise Content Q/A Application

• ChatGPT

• FineTune LLM

• Learning Large Language Models

• Deep Learning Study Plan MindMap

Deep Learning and Artificial Intelligence

• OpenAI Whisper - Audio/Video to Text(Transcribe/Translate)

• Stable Diffusion Video - Multiple Prompts to Video

• Stable Diffusion GUI - Gradio UI for Text-to-Image TensorFlow Models

• Stable Diffusion - Text-to-Image OpenSource AI Model

• Bloom 176B Parameters - Large Language Model

• TorchStudio - Import Dataset, Train and Save Models

• EG3D - Efficient Geometry-aware 3D Generative Adversarial Networks

• Hugging Face - Model Training and Tuning, Inference, all at one place

Deep Learning Content

• JoJoGAN - Face Stylization (3 Videos Series on training, inference, model export and deployment)

• 12 Research Papers to learn Text-2-Image Research

• Diffusion Models - Theory, Implemenations and Models

• All Things VQ-GAN - A 3 part video series

• Text to Image using AI Models Workshop - Step by Step Guide

• Text to Image AI Models - Different methods & different results, same target

• NeRF Scene - Instant-ngp

• LIMoE (Multimodal Mixture of Experts - Google)

• MoE (Mixture of Experts - Google)

• PyTorch Tutorials

• DALL-E Mini

• GraphViz

• Graph Neural Networks

• Topic Modeling

• Convolution Example in Python

• Self-driving Technology

• Number Series and Prediction with ML

• GPT Models (OpenAI and OpenSource)

• No More Blackbox Models: MLI or XAI

• Vision GNN: An Image is Worth Graph of Nodes

• ruDALL-E: Text 2 Image 1.3B parameters open source model

• BCI - Brain Computer Interface

Developer Tools

• Deep Learning Rig - Installation Nvidia drivers, Cuda toolkits for Conda, TensorFlow and PyTorch

• JAX/JAXlib Installation with Cuda/cudNN

• dlib installation with Cuda, cudNN on Ubuntu 22.04 with Conda and Python

• Apple M1 with Metal GPU for Deep Learning

Contact

• If you would like to see here or need some help on similar topics, please feel free  connect me at any below channels.

Prodramp Contact

• YouTube Channel: https://www.youtube.com/channel/UClLqLPWRsta-inJcDrqh6Pg

• Twitter: https://twitter.com/prodramp

Personal Contact

• Avkash Chauhan (@avkashchauhan)

• https://www.linkedin.com/in/avkashchauhan

• https://twitter.com/avkashchauhan

• https://github.com/Avkash

• https://blogs.prodramp.com/

Learning In Progress

• https://github.com/eriklindernoren/ML-From-Scratch

• https://github.com/kwea123/nerf_pl#blender

• https://github.com/bmild/nerf

• https://github.com/musikalkemist/pytorchforaudio

• https://medium.com/@oleguer.canal/the-attention-mechanism-zoo-309c05768ed9

• https://towardsdatascience.com/audio-deep-learning-made-simple-part-1-state-of-the-art-techniques-da1d3dff2504

• https://github.com/RizwanMunawar/yolov7-pose-estimation

• https://github.com/ultralytics/yolov5

• https://www.augmentedstartups.com/yolox-pro-computer-vision-dashboard