DotTorch Layers is a high-performance, modular neural network layers library for .NET 8 and .NET 9. It includes core layers such as Linear, ReLU, Sequential, Dropout, Embedding, Sigmoid, SoftMax, Tanh, LeakyReLU, GELU, ELU, and Flatten. Advanced recurrent layers like RNN, LSTM, and GRU are also implemented, along with powerful Transformer layers. The package features normalization layers: LayerNorm (currently not optimized) and BatchNorm (optimized, with LayerNorm mode support). All layers seamlessly integrate with the DotTorch.Core autograd system, enabling automatic differentiation and backpropagation. Designed for ease of use, extensibility, and efficient execution on CPU and GPU devices. This library supports modern .NET frameworks and follows best practices for maintainability and performance in machine learning model construction.
$ dotnet add package DotTorch.LayersDotTorch.Layers — модульная библиотека нейросетевых слоёв для платформы .NET. Пакет расширяет DotTorch.Core, предоставляя базовые строительные блоки нейронных сетей с полной поддержкой broadcasting и автоматического дифференцирования (autograd).
Linear, ReLU, Sequential, и других.DotTorch.Core: поддержка Tensor, вычислительного графа и autograd.Module с поддержкой вложенных структур и параметров.DotTorch.Layers предназначен для создания нейронных сетей любой сложности на базе функциональности DotTorch.Core.
DotTorch.Layers is a modular neural network layer library for the .NET platform. It extends DotTorch.Core by offering essential building blocks for model construction, with full support for broadcasting and automatic differentiation.
Linear, ReLU, Sequential, and more.DotTorch.Core: tensor operations, computation graph, autograd.Module interface with support for parameter trees and nested structures.DotTorch.Layers is designed to build deep neural architectures with full autograd support using .NET.
DotTorch.Layers ist eine modulare Bibliothek für neuronale Netzwerkschichten auf der .NET-Plattform. Sie erweitert DotTorch.Core um grundlegende Bausteine für die Modellarchitektur mit vollständiger Unterstützung für Broadcasting und automatische Differenzierung.
Linear, ReLU, Sequential usw.DotTorch.Core: Tensoren, Rechengraphen, Autograd.Module-Interface mit verschachtelten Strukturen und Parameterverwaltung.DotTorch.Layers wurde für den Aufbau komplexer neuronaler Netzwerke mit Autograd-Unterstützung in .NET entwickelt.
DotTorch.Layers 是一个用于 .NET 平台的模块化神经网络层库。它扩展了 DotTorch.Core,提供神经网络构建的核心组件,支持广播机制和自动微分。
Linear、ReLU、Sequential 等。Module 接口,支持嵌套结构与参数管理。DotTorch.Layers 致力于在 .NET 中高效构建支持自动微分的深度神经网络架构。