github.com
List of awesome compiler projects and papers for tensor computation and deep learning.
Directory
Search results
Published directory entries matching your search.
github.com
A curated list of R packages, frameworks and software, organized into sections such as integrated development environments, data manipulation and machine learning. The repository also links to learning resources including websites, books and MOOCs.
github.com
burn is a next-generation tensor library and deep learning framework developed by tracel-ai. It is designed to prioritize flexibility, efficiency, and portability, with available resources covering use with Rust, its ecosystem, supported backends, and training and inference functionality.
github.com
Caffe is a deep learning framework developed by Berkeley AI Research and community contributors, designed with expression, speed, and modularity in mind. It is released under the BSD 2-Clause license and includes associated reference models.
github.com
Catniff is a small deep learning framework for JavaScript built to be Torch-like and inspired by Tinygrad APIs. It is under development, and its APIs can be unstable and backwards-incompatible. It provides tensors, autograd and optimizers, and is installed through npm.
github.com
A PyTorch based deep learning library for drug pair scoring.
github.com
A fast Clojure Tensor & Deep Learning library.
github.com
DeepDetect is a deep learning runtime, command-line tool and REST server for training and inference. It provides Python wheel variants for CPU and GPU environments and a command-line interface with profiles such as object detection and semantic segmentation. YAML configuration files make runs repeatable. It handles images, text, tabular data, time series, object-detection boxes and segmentation masks through a single API surface.
github.com
DeepSeek-R1 is the first-generation reasoning model family from DeepSeek, including DeepSeek-R1-Zero and DeepSeek-R1. The repository describes training via large-scale reinforcement learning and cold-start data, and open-sources the models plus six distilled dense models based on Llama and Qwen.
github.com
DeepSeek-V3 is a Mixture-of-Experts language model with 671B total parameters and 37B activated per token. It uses Multi-head Latent Attention and DeepSeekMoE architectures, was pre-trained on 14.8 trillion tokens, and then underwent supervised fine-tuning and reinforcement learning. The repository provides the model weights and inference code.
github.com
Deep learning optimization library that makes distributed training easy, efficient, and effective.
github.com
Detecto is a Python package for building computer vision and object detection models with PyTorch. It supports inference on still images and videos, transfer learning on custom datasets, and serialization of models to files, and is distributed under an MIT license.
github.com
Deep learning in Rust, with shape checked tensors and neural networks.
github.com
A deep learning-based translation library between 50 languages, built with transformers.
github.com
Deep learning operations reinvented (for pytorch, tensorflow, jax and others).
github.com
Flare is a Clojure library for building dynamic neural network graphs, described as similar to PyTorch and DynNet. It supports tensor operations, LSTM cells, one-dimensional CNNs and fixed embeddings, and uses Neanderthal as its tensor backend. The project states it is mostly for learning purposes.
github.com
Friendly Federated Learning Framework.
github.com
Library for high performance deep learning inference on NVIDIA GPUs.
github.com
Frog integrates memory-based natural language processing modules developed for Dutch, all based on the Timbl learning software package. Modules originated in the 1990s, and a dependency parser, base phrase chunker and named-entity recognizer were added more recently. It offers a command-line interface that can run as a daemon, plus a C++ library.
github.com
A curated list of generative deep learning tools, works, models, etc. for artistic uses, by @filipecalegario.
github.com
Half Beer is an open-source JavaScript example project that demonstrates a neural network learning to predict whether a beer glass is perceived as half full or half empty based on user decisions. It is built using the synaptic.js neural network library.
github.com
Distributed deep learning training framework for TensorFlow, Keras, PyTorch, and Apache MXNet.
github.com
Keras-contrib is the official extension repository for the Keras deep learning library, with additional layers, activations, loss functions and optimizers not yet in Keras. It is deprecated and archived; the project migrated to TensorFlow Addons. The repository is read-only.
github.com
Koç University Deep Learning Framework.