Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/zohebabai/deep-learning-projects
Best Deep Learning Projects for Advanced Learners
https://github.com/zohebabai/deep-learning-projects
cnn computer-vision deep-learning gans jax keras machine-learning neural-network nlp pytorch tensorflow transfer-learning transformers tutorial vae
Last synced: 25 days ago
JSON representation
Best Deep Learning Projects for Advanced Learners
- Host: GitHub
- URL: https://github.com/zohebabai/deep-learning-projects
- Owner: ZohebAbai
- License: apache-2.0
- Created: 2018-10-03T08:05:51.000Z (over 6 years ago)
- Default Branch: master
- Last Pushed: 2022-11-03T13:42:45.000Z (about 2 years ago)
- Last Synced: 2024-12-03T14:24:50.203Z (about 1 month ago)
- Topics: cnn, computer-vision, deep-learning, gans, jax, keras, machine-learning, neural-network, nlp, pytorch, tensorflow, transfer-learning, transformers, tutorial, vae
- Language: Jupyter Notebook
- Homepage:
- Size: 246 MB
- Stars: 23
- Watchers: 2
- Forks: 10
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Best Deep Learning Projects for Advanced Learners [2022 Updated]
[](https://mybinder.org/v2/gh/ZohebAbai/Deep-Learning-Projects/master)
#### Using both Tensorflow and PyTorch Libraries
**Get a glimpse of how similar/different these libraries are:**
[Pytorch vs Tensorflow on MNIST dataset](https://nbviewer.org/github/ZohebAbai/Deep-Learning-Projects/blob/master/Pytorch_vs_Tensorflow.ipynb)
**In each notebook, we shall train using free Google Colab resources and eventually deploy them as gradio/streamlit app (depending on projects).**
## Notebooks:
### Fundamentals
* **Tensorflow Fundamentals** [TF Tensors Basics](https://nbviewer.org/github/ZohebAbai/Deep-Learning-Projects/blob/master/00_Tensorflow_Fundamentals.ipynb)
- Constants and Variables
- Compatibility with Numpy
- Random Generators
- Basic Operations
* **Pytorch Fundamentals** [PT Tensors Basics](https://nbviewer.org/github/ZohebAbai/Deep-Learning-Projects/blob/master/00_Pytorch_Fundamentals.ipynb)
- Tensor Basic
- Interoperability with Numpy
- Basic Operations
- Regression Model Training with Custom Data on GPU
### Structured Data
* **Regression** - [Custom TF Model on Medical Insurance Dataset](https://nbviewer.org/github/ZohebAbai/Deep-Learning-Projects/blob/master/01_TF_Regression.ipynb)
- Minimal EDA
- k-Fold Cross Validation
- L1 Regularizers
- Gradio App
### Computer Vision
* **Image Classification** - [Custom TF Model on Cifar10 Dataset](https://nbviewer.org/github/ZohebAbai/Deep-Learning-Projects/blob/master/02_TF_Image_Classification.ipynb)
- Image Augmentation
- LR Finder
- One-Cycle LR Scheduler
- GradCAM visualisation
- Gradio App
* **Multi-Label Image Classification** - [TF Transfer Learning on Custom Dataset](https://nbviewer.org/github/ZohebAbai/Deep-Learning-Projects/blob/master/03_TF_Multilabel_Image_Classification.ipynb)
- Custom Dataset
- TF Record with Image Augmentation
- Custom Loss Function
- Transfer Learning
- Performance Profiling
- Gradio App
* **Image Generation** - [TF VAE Image Generation on Celeb Faces](https://nbviewer.org/github/ZohebAbai/Deep-Learning-Projects/blob/master/04_TF_Image_Generation.ipynb)
- Custom Architecture using Probabilistic Layers
- Reduce LR on Plateau Scheduler
- New Generated Faces
- Reconstructing Faces
- Feature Manipulation
- Face Morphing
- Visualize clusters on UMAP-reduced 1D latent vector
* **Metric Learning** - [TF Similarity Models on Dog-Cat Breed Dataset](https://nbviewer.org/github/ZohebAbai/Deep-Learning-Projects/blob/master/05_TF_Metric_Learning.ipynb)
- Tensorflow Similarity
- Transfer Learning with an embedding layer and Multisimilarity loss
- ANN Search: Indexing, Calibration, Querying
- Precision-Recall Curve
- UMAP-reduced clustering with interactive visualization
* **Image Translation** - [TF Pix2Pix on Edges-to-Handbags Dataset](https://nbviewer.org/github/ZohebAbai/Deep-Learning-Projects/blob/master/08_TF_Pix2Pix_on_Edges2Handbags.ipynb)
- Understanding Pix2Pix Architecture
- Training it from scratch with additional loss fucntion
- Focal Frequency Loss
- Using Tensorboard during model training
- Image Generation
* **Image Segmentation** - [HF SegFormer on Road-Sidewalk Dataset](https://nbviewer.org/github/ZohebAbai/Deep-Learning-Projects/blob/master/09_HF_Image_Segmentation_using_Transformers.ipynb)
- Understanding Semantic Segmentation using Transformers
- Fine-Tuning it using Huggingface Modules
- Mean IOU metric
- [Publishing as HF Model](https://huggingface.co/zoheb/mit-b5-finetuned-sidewalk-semantic)
- [Live Inference Model](https://huggingface.co/spaces/zoheb/segformer_demo)
* **Object Detection** - [PT YOLOS on Matterport Balloons Dataset](https://nbviewer.org/github/ZohebAbai/Deep-Learning-Projects/blob/master/10_PT_Object_Detection_using_Transformers.ipynb)
- Understanding Object Detection using Transformers
- Fine-Tuning YOLOS using Pytorch Lightning
- Detecting object on a video
- Viewing Attention Layers
- [Publishing as HF Model](https://huggingface.co/zoheb/yolos-small-balloon)
- [Live Inference Model](https://huggingface.co/spaces/zoheb/yolos_demo)
### Natural Language Processing
* **Pre-Neural NLP** - [Heuristics-based & Statistical Methods in NLP](https://nbviewer.org/github/ZohebAbai/Deep-Learning-Projects/blob/master/00_Pre_Neural_NLP.ipynb)
- Basics of Sentiment Analysis
- Valence Aware Dictionary and Sentiment Reasoner (VADER)
- Support Vector Machines (SVM)
- Grid Search for Hyperparameters
- ROC Curve
* **Understanding Vanilla Transformers** - [Vanilla Transformers](https://nbviewer.org/github/ZohebAbai/Deep-Learning-Projects/blob/master/06_Understanding_Vanilla_Transformers.ipynb)
- Understanding Seq2Seq Models
- Understanding Attention Mechanism
- Understanding Transformer Architecture
* **Vanilla Transformer Comment to Code** - [PT Train Vanilla Transformer (Sequence to Sequence)](https://nbviewer.org/github/ZohebAbai/Deep-Learning-Projects/blob/master/07_Vanilla_Transformer_Comment_to_Code.ipynb)
- Dataset Augmentation
- Custom Tokenizer
- Build Complete Transformer Architecture
- Custom Loss
- Display Attention
- Gradio App
### Joint CV & NLP
* **Stable Diffusion** - [HF Stable Diffusion Text to Image](https://nbviewer.org/github/ZohebAbai/Deep-Learning-Projects/blob/master/11_HF_Stable_Diffusion_Text_to_Image.ipynb)
- Understanding Diffusion Models (Stable diffusion in particular)
- Exploring Diffusers Library
- Writing an inference pipeline
- Understanding the complete generative process during inference
### Experimental (Excellent ML Applications of few yet not stable libraries)
* **JAX Basics** - [JAX Basics](https://nbviewer.org/github/ZohebAbai/Deep-Learning-Projects/blob/master/JAX_Basics.ipynb)
- Why JAX?
- How randomness is handled
- Speed Comparison
- Asynchronous Dispatch
- JIT Compilation
- Auto-differentiation with grad
- Auto-vectorization with Vmap
- SPMD Programming with Pmap on TPU
- Device Memory Profiler
* **PySyft - Secure and Privacy AI**
- [Data Owner](https://nbviewer.org/github/ZohebAbai/Deep-Learning-Projects/blob/master/Data_Owner.ipynb)
- [Data Scientist](https://nbviewer.org/github/ZohebAbai/Deep-Learning-Projects/blob/master/Data_Scientist.ipynb)
- Differential Privacy
- Remote Data Science
- Covid-19 trends prediction
* **TenSeal - Homomorphic Encryption on Tensors**
- [Homomorphic Encryption Basic and Encrypted Inference](https://nbviewer.org/github/ZohebAbai/Deep-Learning-Projects/blob/master/HE_Basics_n_Inference.ipynb)
- [Homomorphic Encryption NN Training](https://nbviewer.org/github/ZohebAbai/Deep-Learning-Projects/blob/master/HE_Training.ipynb)
- Tenseal Context
- Basic Mathematical Operations on Encrypted Tensors
- Encrypted Evaluation on Encrypted Test Data
- Training Encrypted NN on Encrypted Data