Skip to content

Latest commit

 

History

39 Commits

Folders and files

NameName
Last commit message
Last commit date
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Deep Learning Models in Python

A comprehensive Deep Learning repository built with Python, TensorFlow, Keras, and PyTorch, covering the complete deep learning workflow from Neural Network Fundamentals to Modern State-of-the-Art Architectures. This repository contains well-structured Jupyter notebooks implementing popular Artificial Neural Networks (ANNs), Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), Transformers, Generative Models, Graph Neural Networks (GNNs), Computer Vision, Model Optimization, and many other advanced architectures, making it an excellent resource for learning, interview preparation, research, and portfolio projects.


Features

  • Comprehensive collection of Deep Learning algorithms and architectures
  • Beginner-friendly to advanced learning path
  • Well-organized folder structure
  • Clean, well-documented Jupyter notebooks
  • Step-by-step implementations
  • Real-world datasets and practical examples
  • TensorFlow, Keras, and PyTorch implementations
  • Computer Vision, NLP, and Reinforcement Learning models
  • Modern State-of-the-Art (SOTA) architectures
  • Ready-to-run examples using Tensorflow and Pytorch

Repository Structure

Deep-Learning-Models-Python
│
├── 01. Artificial Neural Networks (ANN)
├── 02. Convolutional Neural Networks (CNN)
├── 03. Recurrent Neural Networks (RNN)
├── 04. Attention Mechanisms
├── 05. Transformers
├── 06. Vision Transformers (ViT)
├── 07. Transfer Learning
├── 08. Object Detection
├── 09. Image Segmentation
├── 10. Autoencoders
├── 11. Generative Adversarial Networks (GAN)
├── 12. Diffusion Models
├── 13. Graph Neural Networks (GNN)
├── 14. Capsule Networks
├── 15. Siamese Networks
├── 16. Self-Organizing Maps (SOM)
├── 17. Restricted Boltzmann Machines (RBM)
└── 18. Model Optimization

Algorithms & Models Included

Artificial Neural Networks (ANN)

  • Perceptron
  • Feedforward Neural Networks (FNN)
  • Artificial Neural Networks (ANN)
  • Binary Classification
  • Multi-Class Classification
  • Activation Functions
  • Loss Functions
  • Backpropagation

Convolutional Neural Networks (CNN)

  • Convolution Operation
  • Pooling Layers
  • LeNet
  • AlexNet
  • VGGNet
  • GoogLeNet (Inception)
  • ResNet
  • DenseNet
  • Xception
  • MobileNet
  • EfficientNet
  • Image Classification

Recurrent Neural Networks (RNN)

  • Vanilla RNN
  • Long Short-Term Memory (LSTM)
  • Gated Recurrent Unit (GRU)
  • Bidirectional RNN
  • Encoder-Decoder Architecture
  • Sequence-to-Sequence (Seq2Seq)
  • Time Series Forecasting
  • Text Classification
  • Sequence Prediction

Attention Mechanisms

  • Bahdanau Attention
  • Luong Attention (General)
  • Luong Attention (Dot Product)
  • Self-Attention
  • Single-Head Attention
  • Multi-Head Attention

Transformers

  • Self-Attention
  • Multi-Head Attention
  • Positional Encoding
  • Transformer Architecture
  • Encoder - Decoder
  • BERT, GPT, T5

Vision Transformers (ViT)

  • Vision Transformer (ViT)
  • DeiT
  • Swin Transformer
  • Image Classification with ViT
  • Fine-Tuning Vision Transformers

Transfer Learning

  • Feature Extraction
  • Fine-Tuning
  • Transfer Learning using TensorFlow
  • Transfer Learning using PyTorch
  • VGG19
  • ResNet
  • InceptionV3
  • EfficientNet
  • MobileNet

Object Detection

  • YOLOv8
  • SSD (Single Shot Detector)
  • Faster R-CNN
  • RetinaNet
  • Object Localization
  • Bounding Box Prediction

Image Segmentation

  • U-Net
  • U-Net++
  • Mask R-CNN
  • DeepLabV3+
  • Semantic Segmentation
  • Instance Segmentation

Autoencoders

  • Vanilla Autoencoder
  • Sparse Autoencoder
  • Denoising Autoencoder
  • Convolutional Autoencoder
  • Variational Autoencoder (VAE)
  • Dimensionality Reduction
  • Anomaly Detection

Generative Adversarial Networks (GAN)

  • Vanilla GAN
  • Deep Convolutional GAN (DCGAN)
  • Conditional GAN (CGAN)
  • Pix2Pix
  • CycleGAN
  • StyleGAN
  • Image Generation
  • Image-to-Image Translation

Diffusion Models

  • Diffusion Model Fundamentals
  • Denoising Diffusion Probabilistic Models (DDPM)
  • Stable Diffusion Concepts
  • Latent Diffusion Models
  • Diffusion Transformer
  • Image Generation

Graph Neural Networks (GNN)

  • Graph Convolutional Networks (GCN)
  • Graph Attention Networks (GAT)
  • GraphSAGE
  • Node Classification
  • Link Prediction
  • Graph Embedding
  • Zachary's Karate Club Network
  • Geometric Neural Networks.ipynb

Capsule Networks

  • Capsule Layers
  • Dynamic Routing
  • Image Classification
  • Pose-aware Feature Learning

Siamese Networks

  • Similarity Learning
  • Contrastive Loss
  • Triplet Loss
  • Face Verification
  • Face Recognition
  • Signature Verification
  • One-Shot Learning

Self-Organizing Maps (SOM)

  • Kohonen Self-Organizing Maps
  • Unsupervised Learning
  • Clustering
  • Data Visualization

Restricted Boltzmann Machines (RBM)

  • Energy-Based Models
  • Contrastive Divergence
  • Feature Learning
  • Collaborative Filtering

Model Optimization

  • Weight Initialization
  • Batch Normalization
  • Dropout
  • Early Stopping
  • Learning Rate Scheduling
  • Gradient Descent, Stochastic Gradient Descent (SGD)
  • Momentum
  • RMSProp
  • Adam, AdamW
  • Adagrad
  • Learning Rate Decay
  • L1 & L2 Regularization
  • Hyperparameter Tuning

Technologies Used

  • Python
  • NumPy
  • Pandas
  • Matplotlib
  • TensorFlow
  • Keras
  • PyTorch
  • OpenCV
  • scikit-learn
  • Hugging Face Transformers
  • torchvision
  • Jupyter Notebook

Installation

Clone the repository:

git clone https://github.com/shaahmir/Deep-Learning-Python.git

Install the required dependencies:

pip install numpy pandas matplotlib scikit-learn tensorflow keras torch torchvision opencv-python transformers jupyter

Launch Jupyter Notebook:

jupyter notebook

Open any notebook and run the cells to explore the models.


Repository Goals

This repository is designed for:

  • Students learning Deep Learning
  • Beginners exploring Artificial Intelligence
  • Computer Vision enthusiasts
  • Interview preparation
  • Academic coursework
  • Research projects
  • Portfolio showcasing

Learning Outcomes

By exploring this repository, you will learn:

  • Fundamentals of Deep Learning
  • Neural Network design and implementation
  • Computer Vision using CNNs and Vision Transformers
  • Natural Language Processing using RNNs and Transformers
  • Movie Recommendation system using Autoencoders
  • Image generation using GANs and Diffusion Models
  • Graph learning using Graph Neural Networks
  • Model optimization techniques
  • Transfer Learning using pretrained models
  • Building production-ready Deep Learning models using TensorFlow and PyTorch

License

This project is licensed under the MIT License.


⭐ If you find this repository useful, consider giving it a Star to support the project.

About

A comprehensive collection of Deep Learning models implemented in Python using TensorFlow and PyTorch. This repository covers Artificial Neural Networks (ANNs), Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), LSTMs, GRUs, Autoencoders, Transformers, Transfer Learning, and model evaluation with clean, well-documented code

Topics

Resources

Stars

1 star

Watchers

0 watching

Forks

Contributors

Languages