wehub/kornia--kornia
1
0
Fork 0
Code Issues Pull Requests Actions 1 Deployments Models Agent Notes Packages Projects Releases Wiki Activity

docs: make Chinese README the default

Browse Source
This commit is contained in:
wehub-resource-sync
2026-07-13 10:49:09 +00:00
parent e654f09fe6
commit c5fe40e9cc
1 changed files with 81 additions and 221 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+81 -221
View File
@@ -1,11 +1,19 @@
<!-- WEHUB_ZH_README -->
> [!NOTE]
> 本文档由 WeHub 基于上游 README 翻译整理，属于社区翻译，非官方中文文档。
> [English](./README.en.md) · [原始项目](https://github.com/kornia/kornia) · [上游 README](https://github.com/kornia/kornia/blob/HEAD/README.md)
> 原作者、版权与许可证归属以原始项目及本仓库 LICENSE 文件为准。
<div align="center">
<p align="center">
<img width="55%" src="https://github.com/kornia/data/raw/main/kornia_banner_pixie.png" />
<img width="75%" src="https://github.com/kornia/data/raw/main/kornia_banner_pixie.png" />
</p>
**The open-source and Computer Vision 2.0 library**
---
English | [简体中文](README_zh-CN.md)
[English](README.md) | 简体中文
<!-- prettier-ignore -->
<a href="https://kornia.readthedocs.io">Docs</a> •
@@ -25,258 +33,106 @@ English | [简体中文](README_zh-CN.md)
</p>
</div>
**Kornia** is a differentiable computer vision library that provides a rich set of differentiable image processing and geometric vision algorithms. Built on top of [PyTorch](https://pytorch.org), Kornia integrates seamlessly into existing AI workflows, allowing you to leverage powerful [batch transformations](), [auto-differentiation]() and [GPU acceleration](). Whether you're working on image transformations, augmentations, or AI-driven image processing, Kornia equips you with the tools you need to bring your ideas to life.
*Kornia* 是一款基于 [PyTorch](https://pytorch.org) 的可微分的计算机视觉库。
> **📢 Announcement**: Kornia is shifting towards end-to-end vision models. We are focusing on integrating state-of-the-art Vision Language Models (VLM) and Vision Language Agents (VLA) to provide comprehensive end-to-end vision solutions.
它由一组用于解决通用计算机视觉问题的操作模块和可微分模块组成。其核心使用 *PyTorch* 作为主要后端，以提高效率并利用反向模式自动微分来定义和计算复杂函数的梯度。
## Key Components
1. **Differentiable Image Processing**<br>
Kornia provides a comprehensive suite of image processing operators, all differentiable and ready to integrate into deep learning pipelines.
- **Filters**: Gaussian, Sobel, Median, Box Blur, etc.
- **Transformations**: Affine, Homography, Perspective, etc.
- **Enhancements**: Histogram Equalization, CLAHE, Gamma Correction, etc.
- **Edge Detection**: Canny, Laplacian, Sobel, etc.
- ... check our [docs](https://kornia.readthedocs.io) for more.
2. **Advanced Augmentations**<br>
Perform powerful data augmentation with Kornia’s built-in functions, ideal for training AI models with complex augmentation pipelines.
- **Augmentation Pipeline**: AugmentationSequential, PatchSequential, VideoSequential, etc.
- **Automatic Augmentation**: AutoAugment, RandAugment, TrivialAugment.
3. **AI Models**<br>
Leverage pre-trained AI models optimized for a variety of vision tasks, all within the Kornia ecosystem.
- **Face Detection**: YuNet
- **Feature Matching**: LoFTR, LightGlue
- **Feature Descriptor**: DISK, DeDoDe, SOLD2
- **Segmentation**: SAM
- **Classification**: MobileViT, VisionTransformer.
<div align="center">
<img src="https://github.com/kornia/kornia/raw/main/docs/source/_static/img/hakuna_matata.gif" width="75%" height="75%">
</div>
<details>
<summary>See here for some of the methods that we support! (>500 ops in total !)</summary>
<!--<div align="center">
<img src="http://drive.google.com/uc?export=view&id=1KNwaanUdY1MynF0EYfyXjDM3ti09tzaq">
</div>-->
| **Category** | **Methods/Models** |
|----------------------------|---------------------------------------------------------------------------------------------------------------------|
| **Image Processing** | - Color conversions (RGB, Grayscale, HSV, etc.)<br>- Geometric transformations (Affine, Homography, Resizing, etc.)<br>- Filtering (Gaussian blur, Median blur, etc.)<br>- Edge detection (Sobel, Canny, etc.)<br>- Morphological operations (Erosion, Dilation, etc.) |
| **Augmentation** | - Random cropping, Erasing<br> - Random geometric transformations (Affine, flipping, Fish Eye, Perspecive, Thin plate spline, Elastic)<br>- Random noises (Gaussian, Median, Motion, Box, Rain, Snow, Salt and Pepper)<br>- Random color jittering (Contrast, Brightness, CLAHE, Equalize, Gamma, Hue, Invert, JPEG, Plasma, Posterize, Saturation, Sharpness, Solarize)<br> - Random MixUp, CutMix, Mosaic, Transplantation, etc. |
| **Feature Detection** | - Detector (Harris, GFTT, Hessian, DoG, KeyNet, DISK and DeDoDe)<br> - Descriptor (SIFT, HardNet, TFeat, HyNet, SOSNet, and LAFDescriptor)<br>- Matching (nearest neighbor, mutual nearest neighbor, geometrically aware matching, AdaLAM LightGlue, and LoFTR) |
| **Geometry** | - Camera models and calibration<br>- Stereo vision (epipolar geometry, disparity, etc.)<br>- Homography estimation<br>- Depth estimation from disparity<br>- 3D transformations |
| **Deep Learning Layers** | - Custom convolution layers<br>- Recurrent layers for vision tasks<br>- Loss functions (e.g., SSIM, PSNR, etc.)<br>- Vision-specific optimizers |
| **Photometric Functions** | - Photometric loss functions<br>- Photometric augmentations |
| **Filtering** | - Bilateral filtering<br>- DexiNed<br>- Dissolving<br>- Guided Blur<br>- Laplacian<br>- Gaussian<br>- Non-local means<br>- Sobel<br>- Unsharp masking |
| **Color** | - Color space conversions<br>- Brightness/contrast adjustment<br>- Gamma correction |
| **Stereo Vision** | - Disparity estimation<br>- Depth estimation<br>- Rectification |
| **Image Registration** | - Affine and homography-based registration<br>- Image alignment using feature matching |
| **Pose Estimation** | - Essential and Fundamental matrix estimation<br>- PnP problem solvers<br>- Pose refinement |
| **Optical Flow** | - Farneback optical flow<br>- Dense optical flow<br>- Sparse optical flow |
| **3D Vision** | - Depth estimation<br>- Point cloud operations<br> |
| **Image Denoising** | - Gaussian noise removal<br>- Poisson noise removal |
| **Edge Detection** | - Sobel operator<br>- Canny edge detection | |
| **Transformations** | - Rotation<br>- Translation<br>- Scaling<br>- Shearing |
| **Loss Functions** | - SSIM (Structural Similarity Index Measure)<br>- PSNR (Peak Signal-to-Noise Ratio)<br>- Cauchy<br>- Charbonnier<br>- Depth Smooth<br>- Dice<br>- Hausdorff<br>- Tversky<br>- Welsch<br> | |
| **Morphological Operations**| - Dilation<br>- Erosion<br>- Opening<br>- Closing |
## 概览
</details>
受现有开源库的启发，Kornia可以由包含各种可以嵌入神经网络的操作符组成，并可以训练模型来执行图像变换、对极几何、深度估计和低级图像处理，例如过滤和边缘检测。此外，整个库都可以直接对张量进行操作。
## Half-Precision Support
详细来说，Kornia 是一个包含以下组件的库：
| Module | float16 | bfloat16 | Notes |
|--------|:-------:|:--------:|-------|
| `kornia.color` | ⚠️ | ⚠️ | Most conversions work for both; FFT-based ops may fail |
| `kornia.filters` | ⚠️ | ⚠️ | Basic filters work; FFT-based ops may fail on CUDA |
| `kornia.enhance` | ⚠️ | ⚠️ | Histogram eq / gamma / ZCA work (linalg ops use cast helpers) |
| `kornia.morphology` | ✅ | ✅ | Pure conv/pool ops; no dtype restrictions |
| `kornia.augmentation` | ⚠️ | ⚠️ | Most ops work; precision-sensitive transforms may be inaccurate |
| `kornia.geometry.transform` | ⚠️ | ⚠️ | Affine/warp/resize work via cast helpers; thin-plate spline may fail |
| `kornia.geometry.camera` | ⚠️ | ⚠️ | Pinhole model and most camera ops work; `StereoCamera` accepts both |
| `kornia.geometry.calibration` | ❌ | ❌ | Explicitly accepts float32/float64 only (PnP solver) |
| `kornia.geometry.epipolar` | ⚠️ | ⚠️ | SVD/inverse use cast helpers; both dtypes work |
| `kornia.geometry.homography` | ⚠️ | ⚠️ | Uses `_torch_svd_cast` — both dtypes work via casting |
| `kornia.geometry.liegroup` | ⚠️ | ⚠️ | Most ops work via cast helpers; some linalg paths may fail |
| `kornia.geometry.solvers` | ⚠️ | ⚠️ | Uses `_torch_solve_cast` — both dtypes work via casting |
| `kornia.geometry.subpix` | ⚠️ | ⚠️ | Soft-argmax works; precision-sensitive ops may be inaccurate |
| `kornia.losses` | ⚠️ | ⚠️ | Photometric losses work; linalg-based losses may not |
| `kornia.feature` | ⚠️ | ⚠️ | Detectors/descriptors work; matching uses manual cdist fallback |
| `kornia.metrics` | ⚠️ | ⚠️ | Pixel-level metrics work; linalg-based metrics may not |
| `kornia.models` | ⚠️ | ⚠️ | Conv-based models work; attention-based models may have dtype mismatches |
| **Component** | **Description** |
|----------------------------------------------------------------------------------|---------------------------------------------------------------------------------------------------------------------------------------|
| [kornia](https://kornia.readthedocs.io/en/latest/index.html) | 具有强大 GPU 支持的可微计算机视觉库 |
| [kornia.augmentation](https://kornia.readthedocs.io/en/latest/augmentation.html) | 在 GPU 中执行数据增强的模块 |
| [kornia.color](https://kornia.readthedocs.io/en/latest/color.html) | 执行色彩空间转换的模块 |
| [kornia.contrib](https://kornia.readthedocs.io/en/latest/contrib.html) | 未进入稳定版本的实验性模块 |
| [kornia.enhance](https://kornia.readthedocs.io/en/latest/enhance.html) | 执行归一化和像素强度变换的模块 |
| [kornia.feature](https://kornia.readthedocs.io/en/latest/feature.html) | 执行特征检测的模块 |
| [kornia.filters](https://kornia.readthedocs.io/en/latest/filters.html) | 执行图像滤波和边缘检测的模块 |
| [kornia.geometry](https://kornia.readthedocs.io/en/latest/geometry.html) | 执行几何计算的模块，用于使用不同的相机模型执行图像变换、3D线性代数和转换 |
| [kornia.losses](https://kornia.readthedocs.io/en/latest/losses.html) | 损失函数模块 |
| [kornia.morphology](https://kornia.readthedocs.io/en/latest/morphology.html) | 执行形态学操作的模块 |
| [kornia.utils](https://kornia.readthedocs.io/en/latest/utils.html) | 图像/张量常用工具以及metrics |
✅ Supported &nbsp; ⚠️ Partial &nbsp; ❌ Not supported
**Test results** (commit `6131e98`, 2026-03-21):
| Run | Passed | Failed | Skipped | Pass% |
|-----|-------:|-------:|--------:|------:|
| CPU float32 *(baseline)* | 7647 | 3 | 3269 | **99.9%** |
| CUDA float32 *(baseline)* | 7634 | 3 | 3280 | **99.9%** |
| CPU float16 | 6866 | 747 | 3306 | **90.1%** |
| CPU bfloat16 | 6838 | 812 | 3269 | **89.3%** |
| CUDA float16 *(KORNIA_TEST_IN_SUBPROCESS=1)* | 6727 | 643 | 3556 | **91.3%** |
| CUDA bfloat16 *(KORNIA_TEST_IN_SUBPROCESS=1)* | 6695 | 713 | 3518 | **90.4%** |
See the [full precision guide](https://kornia.readthedocs.io/en/stable/get-started/precision.html) for details.
## Sponsorship
Kornia is an open-source project that is developed and maintained by volunteers. Whether you're using it for research or commercial purposes, consider sponsoring or collaborating with us. Your support will help ensure Kornia's growth and ongoing innovation. Reach out to us today and be a part of shaping the future of this exciting initiative!
## 支持我们
<a href="https://opencollective.com/kornia/donate" target="_blank">
<img src="https://opencollective.com/webpack/donate/button@2x.png?color=blue" width=300 />
</a>
## Installation
## 安装说明
[![PyPI python](https://img.shields.io/pypi/pyversions/kornia)](https://pypi.org/project/kornia)
[![pytorch](https://img.shields.io/badge/PyTorch_2.0.0+-ee4c2c?logo=pytorch&logoColor=white)](https://pytorch.org/get-started/locally/)
### From pip
### 通过 pip 安装:
```bash
pip install kornia
```
<details>
<summary>Other installation options</summary>
<summary>其他安装方法</summary>
#### From source with editable mode
#### 通过源码安装（软链接至当前路径）:
```bash
pip install -e .
```
#### For development with Pixi (Recommended)
#### 使用 Pixi 进行开发（推荐）
For development, Kornia uses [pixi](https://pixi.sh) for fast Python package management and environment management. The project includes a `pixi.toml` configuration file for reproducible dependency management.
对于开发，Kornia 使用 [pixi](https://pixi.sh) 进行快速的 Python 包管理和环境管理。项目包含一个 `pixi.toml` 配置文件用于可重现的依赖管理。
```bash
# Install pixi (if not already installed)
# 安装 pixi（如果尚未安装）
curl -fsSL https://pixi.sh/install.sh | bash
# Install dependencies and set up the development environment
# 安装依赖并设置开发环境
pixi install
# Run tests
# 运行测试
pixi run test
# For CUDA development
# 用于 CUDA 开发
pixi run -e cuda install
pixi run -e cuda test-cuda
```
This will set up a complete development environment with all dependencies. For more details on dependency management and available tasks, see [CONTRIBUTING.md](CONTRIBUTING.md).
这将设置一个包含所有依赖的完整开发环境。有关依赖管理和可用任务的更多详细信息，请参阅 [CONTRIBUTING.md](CONTRIBUTING.md)。
#### From Github url (latest version)
#### 通过源码安装（从GIT自动下载最新代码）:
```bash
pip install git+https://github.com/kornia/kornia
```
</details>
## Quick Start
Kornia is not just another computer vision library — it's your gateway to effortless Computer Vision and AI.
## 例子
<details>
<summary>Get started with Kornia image transformation and augmentation!</summary>
可以尝试通过这些 [教程](https://kornia.github.io/tutorials/) 来学习和使用这个库。
```python
import numpy as np
import kornia_rs as kr
from kornia.augmentation import AugmentationSequential, RandomAffine, RandomBrightness
from kornia.filters import StableDiffusionDissolving
# Load and prepare your image
img: np.ndarray = kr.read_image_any("img.jpeg")
img = kr.resize(img, (256, 256), interpolation="bilinear")
# alternatively, load image with PIL
# img = Image.open("img.jpeg").resize((256, 256))
# img = np.array(img)
img = np.stack([img] * 2) # batch images
# Define an augmentation pipeline
augmentation_pipeline = AugmentationSequential(
RandomAffine((-45., 45.), p=1.),
RandomBrightness((0.,1.), p=1.)
)
# Leveraging StableDiffusion models
dslv_op = StableDiffusionDissolving()
img = augmentation_pipeline(img)
dslv_op(img, step_number=500)
dslv_op.save("Kornia-enhanced.jpg")
```
</details>
<details>
<summary>Find out Kornia ONNX models with ONNXSequential!</summary>
```python
import numpy as np
from kornia.onnx import ONNXSequential
# Chain ONNX models from HuggingFace repo and your own local model together
onnx_seq = ONNXSequential(
"hf://operators/kornia.geometry.transform.flips.Hflip",
"hf://models/kornia.models.detection.rtdetr_r18vd_640x640", # Or you may use "YOUR_OWN_MODEL.onnx"
)
# Prepare some input data
input_data = np.random.randn(1, 3, 384, 512).astype(np.float32)
# Perform inference
outputs = onnx_seq(input_data)
# Print the model outputs
print(outputs)
# Export a new ONNX model that chains up all three models together!
onnx_seq.export("chained_model.onnx")
```
</details>
## Multi-framework support
You can now use Kornia with [TensorFlow](https://www.tensorflow.org/), [JAX](https://jax.readthedocs.io/en/latest/index.html), and [NumPy](https://numpy.org/). See [Multi-Framework Support](docs/source/get-started/multi-framework-support.rst) for more details.
```python
import kornia
tf_kornia = kornia.to_tensorflow()
```
<p align="center">
Powered by
<a href="https://github.com/ivy-llc/ivy" target="_blank">
<div class="dark-light" style="display: block;" align="center">
<img class="dark-light" width="15%" src="https://raw.githubusercontent.com/ivy-llc/assets/refs/heads/main/assets/logos/ivy-long.svg"/>
</div>
<div align="center">
<a href="https://colab.sandbox.google.com/github/kornia/tutorials/blob/master/nbs/hello_world_tutorial.ipynb" target="_blank">
<img src="https://raw.githubusercontent.com/kornia/data/main/hello_world_arturito.png" width="75%" height="75%">
</a>
</p>
</div>
## Call For Contributors
:triangular_flag_on_post: **Updates**
- :white_check_mark: 现已通过 [Gradio](https://github.com/gradio-app/gradio) 将Kornia集成进 [Huggingface Spaces](https://huggingface.co/spaces). 可以尝试 [Gradio 在线Demo](https://huggingface.co/spaces/akhaliq/Kornia-LoFTR).
Are you passionate about computer vision, AI, and open-source development? Join us in shaping the future of Kornia! We are actively seeking contributors to help expand and enhance our library, making it even more powerful, accessible, and versatile. Whether you're an experienced developer or just starting, there's a place for you in our community.
## 引用
### Accessible AI Models
We are excited to announce our latest advancement: a new initiative designed to seamlessly integrate lightweight AI models into Kornia.
We aim to run any models as smooth as big models such as StableDiffusion, to support them well in many perspectives.
**Priority Focus: VLM/VLA Models**
Our primary focus is on integrating **Vision Language Models (VLM)** and **Vision Language Agents (VLA)** to enable end-to-end vision solutions. We're actively seeking contributors to help us:
- **VLM/VLA Integration (Priority)**: Implement and integrate state-of-the-art Vision Language Models and Vision Language Agents. This includes models like Qwen2.5-VL, SAM-3, and other cutting-edge VLM/VLA architectures. If you are a researcher working on VLM/VLA models, Kornia is an excellent place for you to promote your model!
- Expand the Model Selection: Import decent models into our library. If you are a researcher, Kornia is an excellent place for you to promote your model!
- Model Optimization: Work on optimizing models to reduce their computational footprint while maintaining accuracy and performance. You may start from offering ONNX support!
- Model Documentation: Create detailed guides and examples to help users get the most out of these models in their projects.
### Documentation And Tutorial Optimization
Kornia's foundation lies in its extensive collection of classic computer vision operators, providing robust tools for image processing, feature extraction, and geometric transformations. We continuously seek for contributors to help us improve our documentation and present nice tutorials to our users.
## Cite
If you are using kornia in your research-related documents, it is recommended that you cite the paper. See more in [CITATION](./CITATION.md).
如果您在与研究相关的文档中使用 Kornia，您可以引用我们的论文。更多信息可以在 [CITATION](https://github.com/kornia/kornia/blob/main/CITATION.md) 看到。
```bibtex
@inproceedings{eriba2019kornia,
@@ -288,33 +144,37 @@ If you are using kornia in your research-related documents, it is recommended th
}
```
## Contributing
## 贡献
我们感谢所有的贡献者为改进和提升 Kornia 所作出的努力。您可以直接修复一个已知的BUG而无需进一步讨论；如果您想要添加一个任何新的或者扩展功能，请务必先通过提交一个Issue来与我们讨论。详情请阅读 [贡献指南](https://github.com/kornia/kornia/blob/main/CONTRIBUTING.md)。开源项目的参与者请务必了解如下 [规范](https://github.com/kornia/kornia/blob/main/CODE_OF_CONDUCT.md)。
We appreciate all contributions. If you are planning to contribute back bug-fixes, please do so without any further discussion. If you plan to contribute new features, utility functions or extensions, please first open an issue and discuss the feature with us. Please, consider reading the [CONTRIBUTING](./CONTRIBUTING.md) notes. The participation in this open source project is subject to [Code of Conduct](./CODE_OF_CONDUCT.md).
### AI 政策
### AI Policy
Kornia 接受 AI 辅助的代码，但严格拒绝提交者仅作为代理的 AI 生成贡献。所有贡献者必须是每一行代码的**唯一责任作者**。在提交 pull request 之前，请查看我们的 [AI 政策](AI_POLICY.md)。主要要求包括：
Kornia accepts AI-assisted code but strictly rejects AI-generated contributions where the submitter acts as a proxy. All contributors must be the **Sole Responsible Author** for every line of code. Please review our [AI Policy](AI_POLICY.md) before submitting pull requests. Key requirements include:
- **验证证据**：PR 必须包含本地测试日志以证明代码已执行
- **事前讨论**：所有 PR 在实施前必须在 Discord 或通过 GitHub issue 进行讨论
- **库引用**：实现必须基于现有库引用（PyTorch、OpenCV 等）
- **使用现有工具**：使用现有的 `kornia` 工具，而不是重新发明轮子
- **解释能力**：您必须能够解释您提交的任何代码
- **Proof of Verification**: PRs must include local test logs proving execution
- **Pre-Discussion**: All PRs must be discussed in Discord or via a GitHub issue before implementation
- **Library References**: Implementations must be based on existing library references (PyTorch, OpenCV, etc.)
- **Use Existing Utilities**: Use existing `kornia` utilities instead of reinventing the wheel
- **Explain It**: You must be able to explain any code you submit
自动化 AI 审查工具（例如 GitHub Copilot）将根据这些政策检查 PR。完整详情请参阅 [AI_POLICY.md](AI_POLICY.md)。
Automated AI reviewers (e.g., GitHub Copilot) will check PRs against these policies. See [AI_POLICY.md](AI_POLICY.md) for complete details.
## Community
- **Discord:** Join our workspace to keep in touch with our core contributors, get latest updates on the industry and be part of our community. [JOIN HERE](https://discord.gg/HfnywwpBnD)
## 社区
- **论坛:** 讨论代码实现，学术研究等。[GitHub Forums](https://github.com/kornia/kornia/discussions)
- **GitHub Issues:** bug reports, feature requests, install issues, RFCs, thoughts, etc. [OPEN](https://github.com/kornia/kornia/issues/new/choose)
- **Forums:** discuss implementations, research, etc. [GitHub Forums](https://github.com/kornia/kornia/discussions)
- **Slack:** 加入我们的Slack社区，与我们的核心贡献者保持联系。 [JOIN HERE](https://join.slack.com/t/kornia/shared_invite/zt-csobk21g-2AQRi~X9Uu6PLMuUZdvfjA)
- 常见信息请访问我们的网站 www.kornia.org
<a href="https://github.com/Kornia/kornia/graphs/contributors">
<img src="https://contrib.rocks/image?repo=Kornia/kornia" width="60%" />
</a>
## 中文社区
扫描下方的二维码可关注 Kornia 的官方交流QQ群（679683070）以及Kornia知乎账号。
Made with [contrib.rocks](https://contrib.rocks).
<div align="center">
<img src="https://github.com/kornia/kornia/raw/main/docs/source/_static/img/cn_community_qq.jpg" height="700px">
<img src="https://github.com/kornia/kornia/raw/main/docs/source/_static/img/cn_community_zhihu.jpg" height="700px">
</div>
## License
我们会在 Kornia 交流社区为大家
Kornia is released under the Apache 2.0 license. See the [LICENSE](./LICENSE) file for more information.
- 📢 更新 Kornia 的最新动态
- 📘 进行更高效的答疑解惑以及意见反馈
- 💻 提供与行业大牛的充分交流的平台