4 个仓库
Awesome GitHub RepositoriesConvolutional Layers
Neural network layers that apply sliding window filters to extract spatial features from multi-dimensional tensors.
Distinct from Spatially-Varying Convolutions: The candidates focus on geospatial filtering or specific varying convolutions rather than the general architectural concept of convolutional filtering.
Explore 4 awesome GitHub repositories matching artificial intelligence & ml · Convolutional Layers. Refine with filters or upvote what's useful.
Awesome Convolutional Layers GitHub Repositories
用 AI 发现最棒的仓库。我们将通过 AI 为您搜索最匹配的仓库。
- udacity/deep-learning-v2-pytorch
udacity/deep-learning-v2-pytorch
5,505在 GitHub 上查看本项目是一系列 PyTorch 深度学习课程，包含实践项目和编程练习。它专注于实现神经网络架构和模型训练，以解决复杂的数据问题。 该仓库包含一个计算机视觉项目套件，用于构建图像分类器、自动编码器和风格迁移应用。它具有用于创建合成图像的生成对抗网络（GAN）实验室，以及用于将预训练权重适配到新任务的迁移学习实现。 代码库涵盖了使用循环神经网络和词嵌入进行自然语言处理的序列数据分析。其他功能包括图像数据预处理、模型性能评估以及将训练好的模型部署到云基础设施。 这些材料以一系列 Jupyter Notebook 的形式提供。
Uses convolutional layers to apply spatial filters and extract hierarchical features from image data.
Jupyter Notebookconvolutional-networksdeep-learningneural-network - facebookresearch/flashlight
facebookresearch/flashlight
5,443在 GitHub 上查看Flashlight is a C++ machine learning library and deep learning framework designed for building and training neural networks. It functions as a tensor manipulation library and an automatic differentiation engine that tracks operations to calculate gradients via backpropagation for model optimization. The project is distinguished by its role as a distributed training framework, utilizing all-reduce gradient synchronization and distributed environments to scale machine learning workloads across multiple nodes and devices. It features a backend-agnostic memory interface and RAII-based management
Implements 2D convolutional layers that slide filters over 4D inputs to extract spatial features.
C++ - hunkim/deeplearningzerotoall
hunkim/DeepLearningZeroToAll
4,494在 GitHub 上查看DeepLearningZeroToAll 是一个专注于深度学习和机器学习的综合教育资源和实现集合。它提供了一条使用 TensorFlow 的结构化学习路径，从基础线性模型过渡到复杂的神经网络架构。 该项目以其各种网络类型的实际实现而著称，包括用于逻辑问题的多层感知器、用于空间数据和图像识别的卷积神经网络，以及使用 LSTM 单元进行时间序列预测和字符序列预测的循环神经网络。它还包括通过批量归一化和 Dropout 技术进行模型正则化的详细演示。 该存储库涵盖了广泛的功能，包括线性回归和逻辑回归的监督机器学习、用于张量操作和缩放的数据工程，以及通过梯度下降和手动反向传播计算进行模型优化。它还包括用于模型评估、权重持久化以及通过代价函数可视化和指标记录进行训练可观测性的工具。 内容通过一系列 Jupyter Notebooks 提供。
Provides convolutional layers that apply filters to extract spatial features from image data.
Jupyter Notebookkeraslabmxnet - jfzhang95/pytorch-video-recognition
jfzhang95/pytorch-video-recognition
1,238在 GitHub 上查看This project is a deep learning computer vision library designed for video action recognition. It provides a framework for training and evaluating neural networks that identify and categorize human activities within recorded footage by processing temporal sequences of frames. The library focuses on the implementation of three-dimensional neural network architectures, specifically utilizing three-dimensional convolutional layers to capture both spatial and temporal patterns. By aggregating features across consecutive frame sequences, the models learn to represent the evolution of actions over
Applies sliding window filters across spatial and temporal dimensions to extract motion patterns from video data.
Pythonc3dr2plus1dr3d
