Spaces:
Running
Running
fix: align WR92 course navigation and verified public guidance
Browse filesSafe UI and documentation changes; GPU generation functions preserved. Previous revision: 9d11aee0c2c539b5a5781e12215136c599b01fb0
- README.md +5 -1
- index.html +2 -1
- wr92-language.js +1 -1
README.md
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
---
|
| 2 |
-
title: AI-Powered Object Detection
|
| 3 |
emoji: 🔎
|
| 4 |
colorFrom: blue
|
| 5 |
colorTo: indigo
|
|
@@ -12,6 +12,8 @@ pinned: false
|
|
| 12 |
|
| 13 |
## 中文说明
|
| 14 |
|
|
|
|
|
|
|
| 15 |
这是一个面向 Creative Technology / 入门 AI 课程的小型目标检测教学实验。
|
| 16 |
|
| 17 |
这个项目的重点不是让学生从零重建目标检测器,而是展示:一个已经训练好的 AI 模型,如何把传统计算机视觉任务变成可以直接调用、比较和扩展的能力。
|
|
@@ -97,6 +99,8 @@ App 页面中的 **How to Start** 提供浏览器操作步骤;[PDF guide](./ho
|
|
| 97 |
|
| 98 |
## English
|
| 99 |
|
|
|
|
|
|
|
| 100 |
This is a small teaching mini-lab for a Creative Technology / introductory AI course.
|
| 101 |
|
| 102 |
The point of the project is not to make students rebuild an object detector from scratch. It shows how a pretrained AI model can turn a traditional computer-vision task into a capability that can be directly used, compared, and extended inside an application.
|
|
|
|
| 1 |
---
|
| 2 |
+
title: AI-Powered Object Detection · Legacy Link
|
| 3 |
emoji: 🔎
|
| 4 |
colorFrom: blue
|
| 5 |
colorTo: indigo
|
|
|
|
| 12 |
|
| 13 |
## 中文说明
|
| 14 |
|
| 15 |
+
此地址是旧课程资料的兼容入口。对外展示请访问[正式目标检测实验室](https://huggingface.co/spaces/wr92-course/object-detection-lab);原有交互功能保持不变。
|
| 16 |
+
|
| 17 |
这是一个面向 Creative Technology / 入门 AI 课程的小型目标检测教学实验。
|
| 18 |
|
| 19 |
这个项目的重点不是让学生从零重建目标检测器,而是展示:一个已经训练好的 AI 模型,如何把传统计算机视觉任务变成可以直接调用、比较和扩展的能力。
|
|
|
|
| 99 |
|
| 100 |
## English
|
| 101 |
|
| 102 |
+
This address is retained for older course material. Please share the [official Object Detection Lab](https://huggingface.co/spaces/wr92-course/object-detection-lab); the original interactive features remain available here.
|
| 103 |
+
|
| 104 |
This is a small teaching mini-lab for a Creative Technology / introductory AI course.
|
| 105 |
|
| 106 |
The point of the project is not to make students rebuild an object detector from scratch. It shows how a pretrained AI model can turn a traditional computer-vision task into a capability that can be directly used, compared, and extended inside an application.
|
index.html
CHANGED
|
@@ -36,11 +36,12 @@
|
|
| 36 |
</div>
|
| 37 |
|
| 38 |
<main class="page-shell">
|
| 39 |
-
<section class="wr92-course-nav" aria-label="WR92 Course links and usage limits"><strong>WR92 Course · Related learning spaces</strong><nav class="wr92-nav-row" aria-label="Switch between course demos"><a href="https://huggingface.co/spaces/wr92-course/README" target="
|
| 40 |
|
| 41 |
<nav class="guide-linkbar" aria-label="Course guide">
|
| 42 |
<span>Building your own AI mini app?</span>
|
| 43 |
<a href="./how-to-start.html">How to Start <span aria-hidden="true">→</span></a>
|
|
|
|
| 44 |
<a href="https://huggingface.co/spaces/wr92-course/image-generation-lab" rel="noopener noreferrer">Image Generation <span aria-hidden="true">↗</span></a>
|
| 45 |
</nav>
|
| 46 |
|
|
|
|
| 36 |
</div>
|
| 37 |
|
| 38 |
<main class="page-shell">
|
| 39 |
+
<section class="wr92-course-nav" aria-label="WR92 Course links and usage limits"><strong>WR92 Course · Related learning spaces</strong><nav class="wr92-nav-row" aria-label="Switch between course demos"><a href="https://huggingface.co/spaces/wr92-course/README" target="_blank" rel="noopener noreferrer">WR92 Course</a><a href="https://huggingface.co/spaces/wr92-course/test" target="_blank" rel="noopener noreferrer" aria-current="page">Object Detection</a><a href="https://huggingface.co/spaces/wr92-course/image-generation-lab" target="_blank" rel="noopener noreferrer">Image Generation Lab</a><a href="https://huggingface.co/spaces/miyuki17/creative-technology-image-generation" target="_blank" rel="noopener noreferrer">SDXL Turbo · GPU</a><a href="https://huggingface.co/spaces/miyuki17/creative-technology-sana-sprint" target="_blank" rel="noopener noreferrer">SANA-Sprint · GPU</a></nav><div class="wr92-cap"><strong>No Hugging Face GPU needed</strong><p>Object detection runs in your browser. Hugging Face ZeroGPU minutes and image-generation call caps do NOT apply here. Your device, model downloads, network, and platform availability can still limit usage. <a href="https://huggingface.co/docs/hub/spaces-zerogpu" target="_blank" rel="noopener noreferrer">HF ZeroGPU policy ↗</a></p></div></section>
|
| 40 |
|
| 41 |
<nav class="guide-linkbar" aria-label="Course guide">
|
| 42 |
<span>Building your own AI mini app?</span>
|
| 43 |
<a href="./how-to-start.html">How to Start <span aria-hidden="true">→</span></a>
|
| 44 |
+
<a href="https://huggingface.co/spaces/wr92-course/object-detection-lab" target="_blank" rel="noopener noreferrer">Official course page <span aria-hidden="true">↗</span></a>
|
| 45 |
<a href="https://huggingface.co/spaces/wr92-course/image-generation-lab" rel="noopener noreferrer">Image Generation <span aria-hidden="true">↗</span></a>
|
| 46 |
</nav>
|
| 47 |
|
wr92-language.js
CHANGED
|
@@ -2,7 +2,7 @@
|
|
| 2 |
The original student lab's DOM and its event listeners are preserved. */
|
| 3 |
(() => {
|
| 4 |
"use strict";
|
| 5 |
-
const dictionary = {"WR92 Course · Related learning spaces / 课程联动":"WR92 Course · 教学实验室联动","WR92 Course · Related learning spaces":"WR92 Course · 课程实验室","Object Detection":"目标检测","Image Generation Lab":"图像生成实验室","SDXL Turbo · GPU":"SDXL Turbo · 实时生成","SANA-Sprint · GPU":"SANA-Sprint · 实时生成","No HF GPU needed · 不消耗 HF GPU":"本页不消耗 Hugging Face GPU","No Hugging Face GPU needed":"本页不消耗 Hugging Face GPU","Object detection runs in your browser. Hugging Face ZeroGPU minutes and image-generation call caps do NOT apply here. Your device, model downloads, network, and platform availability can still limit usage. / 目标检测在浏览器本地执行;无 HF ZeroGPU 每日分钟或生成次数限制,但受设备、下载与网络影响。":"目标检测在你自己的浏览器中运行,不调用 Hugging Face ZeroGPU,因此不受 ZeroGPU GPU 分钟或生成次数限制;但设备性能、模型下载、网络及平台服务仍可能影响体验。","Object detection runs in your browser. Hugging Face ZeroGPU minutes and image-generation call caps do NOT apply here. Your device, model downloads, network, and platform availability can still limit usage.":"目标检测在你自己的浏览器中运行,不调用 Hugging Face ZeroGPU,因此不受 ZeroGPU GPU 分钟或生成次数限制;但设备性能、模型下载、网络及平台服务仍可能影响体验。","HF ZeroGPU policy ↗":"HF ZeroGPU 官方说明 ↗","Building your own AI mini app?":"想制作自己的 AI 小应用?","How to Start":"入门指南","Image Generation":"图像生成","Creative Technology · Computer Vision":"创意科技 · 计算机视觉","AI-Powered":"AI 驱动的","Pick a COCO example or upload your own image. Then choose a pretrained detector and let AI answer:":"选择一张 COCO 示例图片或上传自己的照片,再选择一个预训练检测模型,让 AI 回答:","what objects are here, and where are they?":"图中有哪些物体?它们位于哪里?","Task":"任务","Object detection":"目标检测","Data":"数据","COCO validation examples":"COCO 验证集示例","Models":"模型","Choose an image":"选择图片","Start with a tested COCO example, or try a photo of your own.":"可以先用已验证的 COCO 示例,也可以上传自己的照片。","Start here · COCO examples":"从这里开始 · COCO 示例","Four images are drawn at random from 100 bundled COCO validation examples.":"从内置的 100 张 COCO 验证集图片中随机显示四张。","Shuffle":"随机换图","or try your own":"或者试试自己的图片","Upload an image":"上传图片","Useful for seeing where the model generalizes well—and where it does not.":"观察模型在哪些图片上表现良好、又会在哪些情况下失败。","Choose detector":"选择检测模型","RT-DETR is the recommended classroom default.":"课堂演示建议先选择 RT-DETR。","Confidence threshold":"置信度阈值","Higher values only keep predictions the model is more confident about.":"阈值越高,只保留模型更有把握的预测。","Run AI Detection":"运行目
|
| 6 |
const normalized = s => String(s).trim().replace(/\s+/g, " ");
|
| 7 |
const enToZh = new Map(Object.entries(dictionary));
|
| 8 |
const zhToEn = new Map(Object.entries(dictionary).map(([en, zh]) => [zh, en]));
|
|
|
|
| 2 |
The original student lab's DOM and its event listeners are preserved. */
|
| 3 |
(() => {
|
| 4 |
"use strict";
|
| 5 |
+
const dictionary = {"WR92 Course · Related learning spaces / 课程联动":"WR92 Course · 教学实验室联动","WR92 Course · Related learning spaces":"WR92 Course · 课程实验室","Object Detection":"目标检测","Image Generation Lab":"图像生成实验室","SDXL Turbo · GPU":"SDXL Turbo · 实时生成","SANA-Sprint · GPU":"SANA-Sprint · 实时生成","No HF GPU needed · 不消耗 HF GPU":"本页不消耗 Hugging Face GPU","No Hugging Face GPU needed":"本页不消耗 Hugging Face GPU","Object detection runs in your browser. Hugging Face ZeroGPU minutes and image-generation call caps do NOT apply here. Your device, model downloads, network, and platform availability can still limit usage. / 目标检测在浏览器本地执行;无 HF ZeroGPU 每日分钟或生成次数限制,但受设备、下载与网络影响。":"目标检测在你自己的浏览器中运行,不调用 Hugging Face ZeroGPU,因此不受 ZeroGPU GPU 分钟或生成次数限制;但设备性能、模型下载、网络及平台服务仍可能影响体验。","Object detection runs in your browser. Hugging Face ZeroGPU minutes and image-generation call caps do NOT apply here. Your device, model downloads, network, and platform availability can still limit usage.":"目标检测在你自己的浏览器中运行,不调用 Hugging Face ZeroGPU,因此不受 ZeroGPU GPU 分钟或生成次数限制;但设备性能、模型下载、网络及平台服务仍可能影响体验。","HF ZeroGPU policy ↗":"HF ZeroGPU 官方说明 ↗","Building your own AI mini app?":"想制作自己的 AI 小应用?","How to Start":"入门指南","Image Generation":"图像生成","Creative Technology · Computer Vision":"创意科技 · 计算机视觉","AI-Powered":"AI 驱动的","Pick a COCO example or upload your own image. Then choose a pretrained detector and let AI answer:":"选择一张 COCO 示例图片或上传自己的照片,再选择一个预训练检测模型,让 AI 回答:","what objects are here, and where are they?":"图中有哪些物体?它们位于哪里?","Task":"任务","Object detection":"目标检测","Data":"数据","COCO validation examples":"COCO 验证集示例","Models":"模型","Choose an image":"选择图片","Start with a tested COCO example, or try a photo of your own.":"可以先用已验证的 COCO 示例,也可以上传自己的照片。","Start here · COCO examples":"从这里开始 · COCO 示例","Four images are drawn at random from 100 bundled COCO validation examples.":"从内置的 100 张 COCO 验证集图片中随机显示四张。","Shuffle":"随机换图","or try your own":"或者试试自己的图片","Upload an image":"上传图片","Useful for seeing where the model generalizes well—and where it does not.":"观察模型在哪些图片上表现良好、又会在哪些情况下失败。","Choose detector":"选择检测模型","RT-DETR is the recommended classroom default.":"课堂演示建议先选择 RT-DETR。","Confidence threshold":"置信度阈值","Higher values only keep predictions the model is more confident about.":"阈值越高,只保留模型更有把握的预测。","Run AI Detection":"运行目���检测","Choose a COCO example or upload your own image.":"请选择 COCO 示例或上传图片。","AI prediction":"AI 预测结果","What did the detector find?":"检测模型找到了什么?","Waiting":"等待开始","Choose an image first. The original image appears here before detection.":"先选择图片,检测前会在这里显示原图。","No detections yet.":"尚无检测结果。","Object":"物体","Confidence":"置信度","Bounding box":"边界框","Run the detector to see details.":"运行目标检测后在这里查看结果。","What you are doing":"你正在完成的任务","Use a learned AI capability instead of rebuilding the traditional task from scratch.":"调用已经学会目标检测的预训练模型,无需从零训练。","COCO contains everyday-object images with annotations. The selected pretrained detector has already learned the object-detection task from labeled data. In this mini-lab, you can switch models and compare how their predictions differ on the same image.":"COCO 包含带有标注的日常物体图片。这里使用已经通过有标签数据训练的模型,你可以固定同一张图片、切换不同检测模型,观察预测结果的差异。","COCO example or your image":"COCO 示例或你的图片","Selected pretrained detector":"已选的预训练模型","Boxes + labels + confidence":"位置框 + 类别标签 + 置信度","Compare models:":"比较不同模型:","keep the image fixed, switch detector, and observe how predictions, confidence, and speed change.":"保持图片不变,切换检测模型,观察预测内容、置信度与速度如何变化。","Hosted as a Hugging Face Static Space · Powered by Transformers.js":"使用 Hugging Face Static Space 托管 · 基于 Transformers.js","Bedroom furniture":"卧室家具","Kitchen objects":"厨房物品","Cats & remotes":"猫和遥控器","Cake & person":"蛋糕和人物","Skate park":"滑板场","Double-decker buses":"双层巴士","Snowboarder":"单板滑雪者","Bathroom sink & toilet":"浴室洗手池与马桶","Bike & traffic":"自行车与交通","Herd & person":"动物群与人物","Cat & dog at home":"家里的猫与狗","Surfer":"冲浪者","Dining table":"餐桌","Street scene":"街景","Packed suitcase":"装满的行李箱","Person & cell phone":"人物与手机","Bathroom objects":"浴室物品","Busy kitchen":"繁忙的厨房","Bananas at market":"市场上的香蕉","Horses & riders":"马与骑手","Passenger train":"旅客列车","Skateboarder":"滑板运动员","Airplane landing":"飞机降落","Boat at the beach":"海边的小船","Could not read that image.":"无法读取这张图片。","Loading sample":"正在加载样例","COCO val2017":"COCO 验证集 2017","Could not load that COCO example. Try another one.":"无法加载该 COCO 示例,请更换图片。","No objects passed the current confidence threshold.":"没有物体通过当前置信度阈值。","Please choose an image file.":"请选择图片文件。","Model ready":"模型已就绪","Preparing model":"正在准备模型","Loading model":"正在加载模型","Recommended classroom default: modern real-time transformer-style detector.":"课堂推荐的默认模型:采用现代 Transformer 架构的实时检测器。","Representative DETR-family detector. Larger download; useful for comparison.":"典型 DETR 系列模型,下载文件较大,适合对照不同架构。","Small browser-friendly detector. Useful for showing that model choice changes results.":"适合浏览器运行的小型检测模型,可观察选择不同模型如何影响结果。","Image ready":"图片已就绪","Image error":"图片出错","Selected image ready":"已选择图片","Official course page":"正式课程页面"};
|
| 6 |
const normalized = s => String(s).trim().replace(/\s+/g, " ");
|
| 7 |
const enToZh = new Map(Object.entries(dictionary));
|
| 8 |
const zhToEn = new Map(Object.entries(dictionary).map(([en, zh]) => [zh, en]));
|