AWESOME DATA SCIENCE
Section: Deep Learning Packages
Entry
Appears in 6 awesome lists
Sonnet is DeepMind's library built on top of TensorFlow for building complex neural networks.
Section: Deep Learning Packages
Section: Frameworks
Section: TensorFlow · TensorFlow-based neural network library.
Section: TensorFlow related · Google Deepmind APIs on top of TensorFlow.
Section: Libraries · Sonnet is DeepMind's library built on top of TensorFlow for building complex neural networks.
Section: 库 · Sonnet is DeepMind's library built on top of TensorFlow for building complex neural networks.
How to use the Hexagon Delegate to speed up model inference on mobile and edge devices. Also see blog post Accelerating TensorFlow Lite on Qualcomm Hexagon DSPs.
(label: good first issue) PyTorch is an open source machine learning library based on the Torch library, used for applications such as computer vision and natural language processing.
Visualizer for deep learning and machine learning models (no Python code, but visualizes models from most Python Deep Learning frameworks).
(from Hpcaitech) - A Unified Deep Learning System for Large-Scale Parallel Training (1D, 2D, 2.5D, 3D and sequence parallelism, and ZeRO protocol).
Official TensorFlow repository of state-of-the-art (SOTA) models and modeling solutions. Contains reference implementations for BERT, ResNet, Transformer, and many more with pre-trained weights and training scripts. Apache 2.0 licensed.
MLOps Tools For Managing & Orchestrating The Machine Learning LifeCycle. Reproducible and scalable machine learning workflows on Kubernetes with experiment tracking, model management, and pipeline orchestration. Apache 2.0 licensed.
Allows the user to manipulate documents based on data to render charts in SVG.
PyTorch's official computer vision library with 50+ pre-trained model architectures including ResNet, EfficientNet, Vision Transformers (ViT), ConvNeXt, and more. The de facto standard model zoo for PyTorch computer vision. BSD-3-Clause licensed.