Awesome Ai For Science
Section: Machine Learning · High-performance ML research
FreshScore 86
Entry
JAX
Appears in 8 awesome lists
High-performance numerical computing with composable transformations (JIT, vmap, grad). Rising favorite for research and scientific ML.
Open github.comjax-ml/jax
Found in these lists
Awesome Data Analysis
Section: Tools · Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more.
FreshScore 80
Awesome Generative AI Data Scientist
Section: Pretraining · Google’s library for high-performance computing and automatic differentiation.
SlowScore 52
Awesome Open Source AI
Section: 1. Core Frameworks & Libraries · High-performance numerical computing with composable transformations (JIT, vmap, grad). Rising favorite for research and scientific ML.
FreshScore 89
Awesome Production Machine Learning
Section: Computation and Communication Optimisation · Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more.
FreshScore 92
Awesome Python
Section: Deep Learning · A library for high-performance numerical computing with automatic differentiation and JIT compilation.
FreshScore 94
Libraries and packages
Section: Data Science · Composable transformations of Python+NumPy programs: automatic differentiation, vectorization and JIT compilation to GPU/TPU
FreshScore 86
awesome-python
Section: Machine Learning Frameworks · Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more
FreshScore 81
Often listed next to it
TensorFlow
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.
In 23 listsDetails
PyTorch
(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.
In 16 listsDetails
transformers
(formerly known as pytorch-transformers and pytorch-pretrained-bert) provides state-of-the-art general-purpose architectures (BERT, GPT-2, RoBERTa, XLM, DistilBert, XLNet, CTRL...) for Natural Language Understanding (NLU) and Natural Language Generation (NLG) with over 32+ pretrained models in…
In 14 listsDetails
XGBoost
Scalable, Portable and Distributed Gradient Boosting (GBDT, GBRT or GBM) Library, for Python, R, Java, Scala, C++ and more. Runs on single machine, Hadoop, Spark, Flink and DataFlow. [Apache2]
In 11 listsDetails
TensorFlow-Slim
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.
In 12 listsDetails
scikit-learn
Scikit-learn is a powerful machine learning library that provides a wide variety of modules for data access, data preparation and statistical model building.
In 10 listsDetails