8 个仓库
Neural network layers that perform linear transformations using matrix multiplication and bias offsets.
Distinguishing note: No candidate provided describes the basic operation of a dense/fully connected layer in a DL context.
Explore 8 awesome GitHub repositories matching artificial intelligence & ml · Fully Connected Layers. Refine with filters or upvote what's useful.
This project is a static educational website and comprehensive curriculum focused on computer vision and deep learning. It serves as a public repository of instructional materials, lecture notes, and technical guides specifically detailing convolutional neural networks and visual recognition. The site is developed using static-site generation to host course documentation and student project directories. It provides structured academic resources that guide learners through image classification, generative modeling, and the implementation of various neural network architectures. The curriculum
Teaches the implementation of fully connected layers to transform input activations into final class scores.
This project is a comprehensive collection of educational examples and reference implementations for building vision and language models using PyTorch. It serves as a deep learning tutorial covering the end-to-end process of developing neural networks, from initial architecture definition to final production deployment. The repository provides detailed guides on implementing a wide range of domain-specific models, including convolutional neural networks for object detection and segmentation, as well as transformer and recurrent architectures for natural language processing. It emphasizes gene
Constructs fully connected layers using matrix multiplication to achieve dense connectivity between neurons.
Liger-Kernel is a collection of pre-built fused Triton kernels and patching utilities designed to accelerate large language model training. It provides drop-in kernel replacements for common LLM operations such as RMSNorm, cross-entropy loss, and attention, enabling increased throughput and reduced memory usage while preserving bitwise-exact gradients. The project serves as a toolkit for composing custom model architectures from individual optimized kernels and for patching pre-existing models with minimal code changes. The project distinguishes itself through its ability to perform runtime m
Wraps arbitrary layers with doubly-stochastic residual streams to stabilize deep network training.
Publication-ready NN-architecture schematics.
Generates publication-ready SVG diagrams of fully connected neural networks with configurable layer sizes.
该项目是一个用于文本分类的卷积神经网络的 TensorFlow 实现。它作为一个深度学习文本分类器,通过识别和分析训练集中的学习模式,将预定义标签分配给文本文档。 该模型利用嵌入层向量化、用于特征提取的卷积层和用于处理文本数据的最大池化下采样序列。最终类别概率通过密集层分类系统确定。 该工作流涵盖了端到端的机器学习生命周期,包括监督文本学习、具有可配置嵌入维度和过滤器大小的模型训练,以及使用验证数据集和基于检查点的模型持久化进行的性能评估。
Employs fully connected dense layers to map extracted features to final category probabilities.
Tensorspace 是一个基于 WebGL 的 3D 可视化框架与渲染器,旨在将深度学习模型架构与张量数据映射到交互式三维空间中。它作为神经网络架构可视化工具与模型检查器,允许用户在 Web 浏览器中渲染模型拓扑并分析数据流。 该项目通过其将预训练的 Keras 与 TensorFlow 模型转换为空间表示的能力脱颖而出。它与 TensorFlow.js 集成以在浏览器中执行推理,从而实现对中间激活、前向传播与内部张量数据的实时可视化。 该框架为 1D 与 2D 层提供了广泛的渲染原语,包括卷积、池化、全连接层以及各种张量合并操作。它涵盖了广泛的能力范围,包括模型拓扑映射、层状态动画,以及生成式模型输出与目标检测网格的可视化。 该系统包括用于导入现有架构的模型格式转换工具,以及用于在渲染期间监控系统健康状况与帧率的性能追踪面板。
Renders fully connected neural network layers with configurable node counts and interactive animations.
本项目是使用 TensorFlow 进行神经网络开发的教育资源和参考实现集合。它作为一个全面的学习课程、机器学习课程大纲和构建深度学习架构的实践指南。 该代码库提供了涵盖广泛模型类型的教学材料和示例,包括用于图像分类的卷积神经网络、用于序列数据的循环网络和长短期记忆单元,以及用于生成式建模的自动编码器。它还包括用于深度强化学习智能体和将预训练模型适配到新任务的迁移学习技术的实现。 该项目涵盖了完整的开发生命周期,包括数据预处理、计算图定义和权重优化。它提供了用于模型评估和训练优化的实用工具(如 Dropout 和正则化),以及用于可视化网络架构和监控训练指标的工具。
Implements dense layers that perform linear transformations using matrix multiplication and bias offsets for predictions.
这是一个使用 TensorFlow 框架构建的生成模型架构库。它提供了用于生成合成数据和逼真图像的实现,特别关注变分自编码器(VAE)和各种生成对抗网络(GAN)变体。 该集合包括特定的 GAN 架构,如 WGAN-GP、LSGAN、InfoGAN 和 EBGAN。它还具有旨在学习潜在表示并从学习到的分布中合成新样本的变分自编码器。 该项目涵盖了用于归一化和裁剪数据的图像处理管道,以及包括 2D 卷积和线性变换在内的神经网络层工具包。它提供了潜在空间操作、条件向量注入以及通过特定损失函数进行模型稳定的功能。
Implements fully connected layers for linear transformations of feature vectors.