awesome-repositories.com
博客
MCP
awesome-repositories.com

通过 AI 驱动的搜索,发现最优秀的开源仓库。

探索精选搜索开源替代品自托管软件博客网站地图
项目MCP 服务器关于排名机制媒体报道
法律隐私政策服务条款
© 2026 Bringes Technology SRL·VAT RO45896025·hello@awesome-repositories.com
·

3 个仓库

Awesome GitHub RepositoriesLinear Transformation Layers

Layers that perform affine transformations via matrix multiplication and bias addition.

Distinct from Linear Mixing Layers: Distinct from Linear Mixing Layers by focusing on general size transformation (input to output) rather than mixing dimensions

Explore 3 awesome GitHub repositories matching artificial intelligence & ml · Linear Transformation Layers. Refine with filters or upvote what's useful.

Awesome Linear Transformation 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。
  • flashlight/flashlightflashlight 的头像

    flashlight/flashlight

    5,443在 GitHub 上查看↗

    Flashlight is a standalone C++ machine learning library and tensor library used for building and training neural networks. It functions as a comprehensive neural network framework and automatic differentiation engine, providing the tools to construct computation graphs and calculate gradients via backpropagation. The project serves as a distributed training framework, utilizing all-reduce operations to synchronize gradients and parameters across multiple compute nodes and devices. It distinguishes itself through deep integration of high-performance tensor manipulation, native device memory in

    Implements linear transformation layers that use matrix multiplication and optional bias to transform input tensor sizes.

    C++
    在 GitHub 上查看↗5,443
  • richzhang/perceptualsimilarityrichzhang 的头像

    richzhang/PerceptualSimilarity

    4,244在 GitHub 上查看↗

    PerceptualSimilarity 是一个深度学习框架,旨在量化和评估图像之间的感知距离。它提供了一个系统,通过使用深度特征表示而不是像素级差异来衡量两张图像或图像块在人类视觉中看起来有多相似。 该项目实现了一个可微分距离度量,作为损失函数,允许通过反向传播优化图像像素以达到目标视觉外观。它包括一个可训练的线性层,可以应用于冻结的深度特征,以学习与人类感知一致的加权距离度量。 该框架涵盖了图像质量评估、相似度度量训练和计算机视觉基准测试方面的广泛功能。模型准确性通过使用诸如二选一强制选择测试等框架,将预测的距离分数与人类判断数据集进行比较来评估。

    Uses a trainable linear layer on top of frozen features to learn weighted human-perceptual distances.

    Python
    在 GitHub 上查看↗4,244
  • deepseek-ai/deepseek-vldeepseek-ai 的头像

    deepseek-ai/DeepSeek-VL

    4,134在 GitHub 上查看↗

    DeepSeek-VL 是一个多模态大型语言模型和图像到文本推理引擎。它作为一个视觉-语言模型和视觉问答系统,集成了视觉感知与语言推理,以理解和描述图像。 该项目支持多模态图像理解和文档图像分析,特别是处理网页截图和技术图表。它提供了视觉对话 AI 的功能,允许用户与视觉数据交互以提取见解,并跨不同类型的视觉信息执行复杂的推理。 该系统利用视觉-语言 Transformer 架构,将视觉 Transformer 与大型语言模型相结合。它采用多模态指令微调和投影层,将视觉特征向量与语言模型的嵌入空间对齐,以进行自回归文本生成。

    Employs a learnable projection layer to align visual feature vectors with the language model's embedding space.

    Python
    在 GitHub 上查看↗4,134
  1. Home
  2. Artificial Intelligence & ML
  3. Machine Learning
  4. Algorithms
  5. Linear Regression Implementations
  6. Linear Transformation Layers

探索子标签

  • Multimodal Alignment LayersLinear layers specifically designed to map visual feature vectors into the embedding space of a language model. **Distinct from Linear Transformation Layers:** Specializes in aligning vision and language modalities, whereas general linear transformation layers are agnostic to the data type.
  • Perceptual Metric HeadsTrainable linear layers that map deep features to a weighted human-perceptual distance metric. **Distinct from Linear Transformation Layers:** Specifically for learning perceptual distance weights, not general affine transformations.