🏷️sec_code
- 依赖包安装
pip3 install -r requirements.txt
- 安装 Jupyter
python3 -m pip install --upgrade pip
python3 -m pip install jupyter
- 查看并运行jupyter
请在终端(Mac / Linux)或命令提示符(Windows)上运行以下命令:
cd notebooks
jupyter notesbook
图3 例子:12.3.3 样式迁移 Colab 点击 [Copy to Drive]
按书中内容先后顺序逐章阅读,或者选取特定章节祥读 📁 docs/
1,动手实践章节代码,在代码文件 📁 code/
2 下找到对应代码,本地测试或者Colab 📁 notebooks/
3 在线测试,方法如下面的示例。
Scenario | Description |
---|---|
- [ ] Classification | Image Classification is a supervised machine learning technique to learn and predict the category of a given image. |
- [ ] Similarity | Image Similarity is a way to compute a similarity score given a pair of images. Given an image, it allows you to identify the most similar image in a given dataset. |
- [ ] Detection | Object Detection is a technique that allows you to detect the bounding box of an object within an image. |
- [ ] Keypoints | Keypoint Detection can be used to detect specific points on an object. A pre-trained model is provided to detect body joints for human pose estimation. |
- [ ] Segmentation | Image Segmentation assigns a category to each pixel in an image. |
- [ ] Action Recognition | Action Recognition (also known as activity recognition) consists of classifying various actions from a sequence of frames, such as "reading" or "drinking". |
- [ ] Tracking | Tracking allows to detect and track multiple objects in a video sequence over time. |
*Cite from microsoft/computervision-recipes
-
We have a discord server! This should be your first stop to talk with other friends in ACTION. Why don't you introduce yourself right now? Join the ACTION channel in L0CV Discord
-
L0CV-微信读者交流群 关注公众号迈微AI研习社,然后回复关键词“计算机视觉实战教程”,即可加入“读者交流群”
-
L0CV
代码部分采用 Apache 2.0协议 进行许可,包括名为 L0CV 的原创第三方库、/code
和/notebook
下的源代码。遵循许可的前提下,你可以自由地对代码进行修改,再发布,可以将代码用作商业用途。但要求你:- 署名:在原有代码和衍生代码中,保留原作者署名及代码来源信息。
- 保留许可证:在原有代码和衍生代码中,保留
Apache 2.0
协议文件。
-
L0CV
文档部分采用 知识共享署名 4.0 国际许可协议 进行许可。 遵循许可的前提下,你可以自由地共享,包括在任何媒介上以任何形式复制、发行本作品,亦可以自由地演绎、修改、转换或以本作品为基础进行二次创作。但要求你:- 署名:应在使用本文档的全部或部分内容时候,注明原作者及来源信息。
- 非商业性使用:不得用于商业出版或其他任何带有商业性质的行为。如需商业使用,请联系作者。
- 相同方式共享的条件:在本文档基础上演绎、修改的作品,应当继续以知识共享署名 4.0国际许可协议进行许可。