Open-source library with pretrained transformer models and tooling for NLP, vision, audio, and multimodal machine learning tasks.
Useful for practical ML projects involving text classification, chatbots, embeddings, summarization, image-text models, and fine-tuning pretrained models.
Official PyTorch learning portal covering tensors, neural networks, training loops, computer vision, NLP, deployment, and distributed training.
Strong learning resource for students building hands-on deep learning projects in Python using PyTorch.
Official collection of TensorFlow model implementations, research models, pretrained models, and example training pipelines.
Good source of practical project templates for object detection, vision, NLP, recommendation, and production-oriented ML workflows.
Free practical deep learning course focused on building real models quickly, using the fastai and PyTorch ecosystem.
Excellent learning path for project-based ML, especially for students who want to train useful models before diving deeply into theory.
Open-source platform for managing the ML lifecycle, including experiment tracking, model packaging, model registry, and deployment workflows.
Relevant for practical ML teams that need reproducibility, experiment tracking, and project organization beyond just training models.
Curated collection of runnable Keras examples for computer vision, NLP, generative AI, structured data, time series, and reinforcement learning.
Helpful for quickly starting practical ML projects with clean, concise example code and common model patterns.
Long-running public repository of datasets commonly used for machine learning education, benchmarking, and applied data projects.
Useful source of clean, well-known datasets for classification, regression, clustering, and exploratory data analysis projects.
Searchable platform linking machine learning papers to code implementations, datasets, benchmarks, and evaluation tables.
Useful for finding project ideas, reproducible implementations, benchmark datasets, and state-of-the-art methods across ML domains.
A widely used Python machine learning library with classification, regression, clustering, and model selection tools.
Useful foundation for many beginner and intermediate machine learning projects.