README.md

PyTorch Fundamentals

Learn the fundamentals of deep learning with PyTorch! This beginner friendly learning path will introduce key concepts to building machine learning models in multiple domains include speech, vision, and natural language processing.

• Basic Python knowledge
• Basic knowledge about how to use Jupyter Notebooks
• Basic understanding of machine learning

And if you are interested to know more, please check another repo Implementation for the different ML tasks on Kaggle platform with GPUs.

NOTE: There do have many bugs due to the different version of dependencies, please open new issue to discuss it.

Introduce to PyTorch

No	Title	Open in Sagemaker	Open in Kaggle
1	What are Tensors?
2	Loading and normalizing datasets
3	Building the model layers
4	Automatic differentiation
5	About the optimization loop
6	Load and run model predictions
7	The full model building process

Audio classification with PyTorch

No	Title	Open in SageMaker	Open in Kaggle
1	Understand audio data and concepts
2	Audio transforms and visualizations

Natural language processing with PyTorch

No	Title	Open in SageMaker	Open in Kaggle
1	Representing text as Tensors
2	Represent words with embeddings
3	Capture patterns with RNN
4	Generate text with RNN

Computer vision with PyTorch

No	Title	Open in SageMaker	Open in Kaggle
1	Introduction to CV with PyTorch
2	Training a simple sense neural network
3	Convolutional Neural Networks
4	Multilayer Dense Neural Network
5	Pre-trained models and transfer learning
6	Lightweight Networks and MobileNet

Diffusion

No	Title	Open in SageMaker	Open in Kaggle	Open in Colab
1	Deconstruct the Stable Diffusion pipeline
2	Basic training model
3	Deconstruct the basic pipeline
4	Details for models and schedulers
5	Effective and Efficient diffusion
6	Generting by using float16(sppeding up)
7	Stable Diffusion v1.5 demo
8	Load checkpoints models and schedulers
9	Schedulers Performance
10	Stable diffusion with diffusers

Paper implementation

No	Title	Open in SageMaker	Open in Kaggle	Open in Colab	Paper
1	The annotated diffusion model				1503.03585 1907.05600 2006.11239
2	QLoRA Fine-tuning for Falcon-7B with PEFT

On macOS

All the notebooks are support mps, except if the notebooks import fp16 speeding up:

• The kernel crashed

Contributing

Warm welcome for any contributions, please follow the contributing guidelines.

Acknowledgement

• Huggingface diffusers
• Microsoft learning