Revised and expanded
Topic | Note | Video | Code |
---|---|---|---|
Overview | - | - | |
Supervised Learning | - | - | |
Multilayer Perceptron (MLP) | - | Notebook | |
Convolutional Neural Network (CNN) | - | Notebook | |
Recurrent Neural Network (RNN) | - | Notebook | |
Transformer | - | Notebook | |
Mamba | - | SimpleMamba Mamba2 |
|
Optimization | - | - | |
Regularization | - | - | |
Detection | - | - | |
Segmentation | - | SAM2 | |
Autoencoder (AE) | - | AE & Denoising AE Colorization AE |
|
Variational Autoencoder (VAE) | - | VAE and CVAE | |
Generative Adversarial Network (GAN) | - | DCGAN and CGAN | |
Intro to Large Language Models (LLMs) | - | - | |
LLM Data and Model | - | - |
Topic | Note | Video | Code |
---|---|---|---|
Development Environment | - | - | |
Python | - | - | |
Numpy | - | - | |
Einsum | - | Notebook | |
Einops | - | Notebook | |
PyTorch | - | - | |
Gradio | - | Notebook Llama Chat |
|
Efficiency | - | Code | |
PyTorch Lightning | - | Notebook | |
Model Packaging & Serving | - | ONNX Export ONNX Runtime TorchScript & TensorRT PyTriton Yolo Client PyTriton Yolo Server |
|
Docker | = | - | |
HuggingFcae | - | - |
AI, ML and Deep Learning | Note | Video | Code |
---|---|---|---|
LLM | |||
LangChain | - | Jupyter | |
LLM Fine Tuning & Document Query | - | Jupyter | |
Document Query using Chroma | - | - | Jupyter |
Dolly (Free LLM) | - | - | Jupyter |
LVM | |||
Segment Anything Model (SAM) | - | Prompts & All Masks |
|
Open CLIP & CoCa | - | - | Jupyter |
Agents | |||
HuggingGPT | - | Agents | |
Large MultiModal Models (L3M) | |||
ImageBind | - | ImageBind | |
Stable Diffusion | |||
Diffusion | - | - | Diffusers |
ControlNet | - | - | ControlNet |
Assuming you already have anaconda
or venv
, install the required python packages to run the experiments in this version.
pip install -r requirements.txt --upgrade
AI, ML and Deep Learning | Note | Video | Code |
---|---|---|---|
Overview | YouTube | - | |
Toolkit | |||
Development Environment and Code Editor |
YouTube | - | |
Python | YouTube | - | |
Numpy | YouTube | Jupyter | |
Einsum | YouTube | Jupyter | |
Einops | YouTube | Jupyter & Jupyter (Audio) |
|
PyTorch & Timm | YouTube | PyTorch/Timm & Input Jupyter |
|
Gradio & Hugging Face | YouTube | Jupyter | |
Weights and Biases | YouTube | Jupyter | |
Hugging Face Accelerator | Same as W&B | Same as W&B | Jupyter & Python |
Datasets & Dataloaders | YouTube | Jupyter | |
Supervised Learning | YouTube | ||
PyTorch Lightning | YouTube | MNIST & KWS | |
Keyword Spotting App | cd versions/2022/supervised/python && python3 kws-infer.py --gui |
||
Building blocks: MLPs, CNNs, RNNs, Transformers |
|||
MLP | YouTube | MLP on CIFAR10 | |
CNN | YouTube | CNN on CIFAR10 | |
Transformer | YouTube | Transformer on CIFAR10 | |
Backpropagation | |||
Optimization | |||
Regularization | |||
Unsupervised Learning | Soon | ||
AutoEncoders | YouTube | AE MNIST Colorization CIFAR10 |
|
Variational AutoEncoders | Soon | ||
Practical Applications: Vision, Speech, NLP |
Soon |
If you find this work useful, please give it a star, fork, or cite:
@misc{atienza2020dl,
title={Deep Learning Lecture Notes},
author={Atienza, Rowel},
year={2020},
publisher = {GitHub},
journal = {GitHub repository},
howpublished = {\url{https://github.com/roatienza/Deep-Learning-Experiments}},
}