apple/corenet Alternatives

When you need TensorFlow's production deployment ecosystem rather than CoreNet's PyTorch research stack.

An Open Source Machine Learning Framework for Everyone

When you need a pure Rust deep-learning framework with portable backends and no Python runtime.

Burn is a next generation tensor library and Deep Learning Framework that doesn't compromise on flexibility, efficiency and portability.

When you want a lightweight C++ ML library for embedded or low-overhead training/inference.

A C++ standalone library for machine learning

When you develop in Java/Kotlin and need a JVM training/inference framework.

An Engine-Agnostic Deep Learning Framework in Java

When you prefer Julia's numerical ecosystem and want differentiable programming in Julia.

Relax! Flux is the ML library that doesn't make you tensor

When you're already on JAX and only need lightweight NN module primitives.

JAX-based neural network library

When you need a Nim tensor/deep-learning library for a Nim codebase.

A fast, ergonomic and portable tensor library in Nim with a deep learning focus for CPU, GPU and embedded devices via OpenMP, Cuda and OpenCL backends

When you want a backend-agnostic high-level NN API instead of CoreNet's task-specific model zoo.

Deep Learning for humans

When you need to train/deploy models in JavaScript or browser environments.

A WebGL accelerated JavaScript library for training and deploying ML models.

When you need large-scale distributed training with automatic parallelism and a PyTorch-compatible API.

OneFlow is a deep learning framework designed to be user-friendly, scalable and efficient.

When you need a framework optimized for heterogeneous hardware and easy model deployment.

MegEngine 是一个快速、可拓展、易于使用且支持自动求导的深度学习框架

When you need a JAX-based vision research library with model configs and training pipelines.

Scenic: A Jax Library for Computer Vision Research and Beyond

When you are tied to an existing dfdx-based Rust project and accept its unmaintained state.

Deep learning in Rust, with shape checked tensors and neural networks

When you maintain a legacy Theano/Lasagne codebase; otherwise superseded.

Lightweight library to build and train neural networks in Theano

When you need a turnkey high-level CV API for common tasks and can accept its narrower scope.

A python library built to empower developers to build applications and systems with self-contained Computer Vision capabilities

When you need the official Swin-Transformer implementation for that specific architecture.

This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows".