25 packages tagged with “Deep-learning”
SciSharp.TensorFlow.Redist is a package contains Google TensorFlow C library CPU version 2.16.0 redistributed as a NuGet package.
Contains neural learning algorithms such as Levenberg-Marquardt, Parallel Resilient Backpropagation, initialization procedures such as Nguyen-Widrow and other neural network related methods. This package is part of the Accord.NET Framework.
FULL TensorFlow 1.15 for .NET with Keras. Build, train, checkpoint, execute models. Samples: https://github.com/losttech/Gradient-Samples, https://github.com/losttech/YOLOv4, https://github.com/losttech/Siren Deep learning with .NET blog: https://ml.blogs.losttech.software/ Comparison with TensorFlowSharp: https://github.com/losttech/Gradient/#why-not-tensorflowsharp Comparison with TensorFlow.NET: https://github.com/losttech/Gradient/#why-not-tensorflow-net Allows building arbitrary machine learning models, training them, and loading and executing pre-trained models using the most popular machine learning framework out there: TensorFlow. All from your favorite comfy .NET language. Supports both CPU and GPU training (the later requires CUDA or a special build of TensorFlow). Provides access to full tf.keras and tf.contrib APIs, estimators and many more. Free for non-commercial use. For licensing options see https://losttech.software/buy_gradient.html !!NOTE!! This version requires Python 3.x x64 to be installed with tensorflow 1.15.x. See the official installation instructions in https://www.tensorflow.org/install/pip#older-versions-of-tensorflow (ensure you are installing version 1.15 to avoid hard-to-debug issues). Please, report any issues to https://github.com/losttech/Gradient/issues For community support use https://stackoverflow.com/ with tags (must be all 3 together) tensorflow, gradient, and .net. For support email contact@losttech.software . More information in NuGet package release notes and on the project web page: https://github.com/losttech/Gradient . TensorFlow, the TensorFlow logo and any related marks are trademarks of Google Inc.
A lightweight library for neural networks that runs anywhere
SciSharp.TensorFlow.Redist is a package contains Google TensorFlow C library CPU version 2.15.0 redistributed as a NuGet package.
FULL TensorFlow 1.15 for .NET with Keras. Build, train, checkpoint, execute models. Comparison with TensorFlowSharp: https://github.com/losttech/Gradient/#why-not-tensorflowsharp Comparison with TensorFlow.NET: https://github.com/losttech/Gradient/#why-not-tensorflow-net Allows building arbitrary machine learning models, training them, and loading and executing pre-trained models using the most popular machine learning framework out there: TensorFlow. All from your favorite comfy .NET language. Supports both CPU and GPU training (the later requires CUDA or a special build of TensorFlow). Provides access to full tf.keras and tf.contrib APIs, including estimators. This preview will expire. !!NOTE!! This version requires Python 3.x x64 to be installed with tensorflow or tensorflow-gpu 1.15. See the official installation instructions in https://www.tensorflow.org/install/ (ensure you are installing version 1.15 to avoid hard-to-debug issues). Please, report any issues to https://github.com/losttech/Gradient/issues For community support use https://stackoverflow.com/ with tags (must be all 3 together) tensorflow, gradient, and .net. For on-site/remote support for this preview email contact@losttech.software . More information in NuGet package release notes and at the project web page: https://github.com/losttech/Gradient .
F# extensions to simplify CNTK usage
Deep Learning pure .NET library.
C# library for easy Deep Learning and Deep Reinforcement Learning. It is wrapper over C# CNTK API. Has implementation of layers (LSTM, Convolution etc.), optimizers, losses, shortcut-connections, sequential model, sequential multi-output model, agent teachers, policy gradients, actor-critic etc. Contains helpers for work with dataset (split, statistics, SMOTE etc). Allows train, evaluate and inference deep neural networks in style similar to Keras.
Implementing the Florence-2-base model for image understanding. Supports captioning, OCR, and object detection with optional phrase grounding. Uses ONNX models from huggingface.co/onnx-community/Florence-2-base. Enables various output tasks including detailed captioning, region-based OCR, and flexible object detection.
Road markings detection using custom yolov5 model based on ONNX, .NET 8.0 by Aliardan
Native Intel oneDNN (Deep Neural Network Library) binaries for CPU-accelerated deep learning operations. This package provides the dnnl native library required by AiDotNet.Tensors for optimized convolution, ReLU, sigmoid, and element-wise operations on CPU.
Scorer for RoadMarkingDetection
Seq2SeqSharp is a tensor based fast & flexible encoder-decoder deep neural network framework written by .NET (C#). It can be used for sequence-to-sequence task, sequence-labeling task and sequence-classification task and other NLP tasks. Seq2SeqSharp supports both CPUs (x86, x64 and ARM64) and GPUs. It's powered by .NET core, so Seq2SeqSharp can run on both Windows and Linux without any modification and recompilation.
C# + TorchSharp implementation of GPT
High-level CUDA API for .NET - GPU computing made easy
Real-Time Object Detection network. TensorFlow-based implementation with support for fine-tuning and training from scratch.
GPT-2 neural network (https://openai.com/blog/better-language-models/). GPT-2 translates text, answers questions, summarizes passages, and generates text output on a level is sometimes indistinguishable from that of humans. A .NET port of open-source artificial intelligence created by OpenAI.
.NET wrapper for waifu2x-ncnn-vulkan - Image Super-Resolution for Anime-style art using Deep Convolutional Neural Networks.
SIREN neural network (https://vsitzmann.github.io/siren/). Network with sine activations, perfect for neural representations of various signals: images, video, audio. SOTA 2020. See project page for usage example.
Community-maintained C# wrapper for OpenVINO GenAI, providing idiomatic .NET APIs for LLM inference. Includes async/await support, streaming generation, and automatic native library management.
TensorRT10 wrapper for .NET - 为.NET平台提供的NVIDIA TensorRT10封装库
Welvet - LOOM Neural Network Framework for .NET. 12 layer types (Dense, LSTM, RNN, Conv2D, Conv1D, MHA, LayerNorm, RMSNorm, SwiGLU, Softmax, Embedding, Parallel), transformer/LLM inference with streaming, neural tweening, K-Means clustering, Pearson/Spearman correlation, network grafting, step-based forward pass, 7 LR schedulers, 3 optimizers (SGD/AdamW/RMSprop), ensemble features, and bit-for-bit model sharing with Python/TypeScript/Go. Multi-platform: Linux, Windows, macOS, Android, iOS.
ThreeN Neural Network Library for .NET - A versatile neural network library that simplifies creating and training neural networks with support for various activation functions, weight initialization methods (Xavier, He), and optimizers (SGD, Adam, RMSProp, Momentum). Includes backpropagation and matrix operations.