course/pr_1021/zh-CN/chapter9/2.html

<meta charset="utf-8" /><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;构建你的第一个演示&quot;,&quot;local&quot;:&quot;构建你的第一个演示&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;🤖 使用模型预测&quot;,&quot;local&quot;:&quot;🤖 使用模型预测&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2}],&quot;depth&quot;:1}">
		<link href="/docs/course/pr_1021/zh-CN/_app/immutable/assets/0.e3b0c442.css" rel="modulepreload">
		<link rel="modulepreload" href="/docs/course/pr_1021/zh-CN/_app/immutable/entry/start.f3a1a511.js">
		<link rel="modulepreload" href="/docs/course/pr_1021/zh-CN/_app/immutable/chunks/scheduler.37c15a92.js">
		<link rel="modulepreload" href="/docs/course/pr_1021/zh-CN/_app/immutable/chunks/singletons.9bf55235.js">
		<link rel="modulepreload" href="/docs/course/pr_1021/zh-CN/_app/immutable/chunks/index.18351ede.js">
		<link rel="modulepreload" href="/docs/course/pr_1021/zh-CN/_app/immutable/chunks/paths.0ba10750.js">
		<link rel="modulepreload" href="/docs/course/pr_1021/zh-CN/_app/immutable/entry/app.c39e37cf.js">
		<link rel="modulepreload" href="/docs/course/pr_1021/zh-CN/_app/immutable/chunks/index.2bf4358c.js">
		<link rel="modulepreload" href="/docs/course/pr_1021/zh-CN/_app/immutable/nodes/0.dad18ce3.js">
		<link rel="modulepreload" href="/docs/course/pr_1021/zh-CN/_app/immutable/chunks/each.e59479a4.js">
		<link rel="modulepreload" href="/docs/course/pr_1021/zh-CN/_app/immutable/nodes/71.d10887aa.js">
		<link rel="modulepreload" href="/docs/course/pr_1021/zh-CN/_app/immutable/chunks/CodeBlock.4e987730.js">
		<link rel="modulepreload" href="/docs/course/pr_1021/zh-CN/_app/immutable/chunks/DocNotebookDropdown.efc1fb7c.js">
		<link rel="modulepreload" href="/docs/course/pr_1021/zh-CN/_app/immutable/chunks/getInferenceSnippets.ebf8be91.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;构建你的第一个演示&quot;,&quot;local&quot;:&quot;构建你的第一个演示&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;🤖 使用模型预测&quot;,&quot;local&quot;:&quot;🤖 使用模型预测&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2}],&quot;depth&quot;:1}"><!-- HEAD_svelte-u9bgzb_END -->      <p></p>  <h1 class="relative group"><a id="构建你的第一个演示" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#构建你的第一个演示"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>构建你的第一个演示</span></h1>  <div class="flex space-x-1 absolute z-10 right-0 top-0"> <a href="https://colab.research.google.com/github/huggingface/notebooks/blob/master/course/chapter9/section2.ipynb" target="_blank"><img alt="Open In Colab" class="!m-0" src="https://colab.research.google.com/assets/colab-badge.svg"></a> <a href="https://studiolab.sagemaker.aws/import/github/huggingface/notebooks/blob/master/course/chapter9/section2.ipynb" target="_blank"><img alt="Open In Studio Lab" class="!m-0" src="https://studiolab.sagemaker.aws/studiolab.svg"></a></div> <p data-svelte-h="svelte-14r1l45">让我们从安装 Gradio 开始吧！与安装其他 Python 包一样，只需运行：</p> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5   text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START -->pip install gradio
<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-11u8tjg">Gradio 支持所有常见的平台，无论是从你最喜欢的 Python IDE、Jupyter notebook 还是 Google Colab 🤯！</p> <p data-svelte-h="svelte-m9srgt">所以无论你在哪里运行 Python，都可以安装 Gradio！</p> <p data-svelte-h="svelte-d8y4tk">让我们从一个简单的“Hello World”示例开始熟悉 Gradio 语法：</p> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5   text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START --><span class="hljs-keyword">import</span> gradio <span class="hljs-keyword">as</span> gr


<span class="hljs-keyword">def</span> <span class="hljs-title function_">greet</span>(<span class="hljs-params">name</span>):
    <span class="hljs-keyword">return</span> <span class="hljs-string">&quot;Hello &quot;</span> + name


demo = gr.Interface(fn=greet, inputs=<span class="hljs-string">&quot;text&quot;</span>, outputs=<span class="hljs-string">&quot;text&quot;</span>)

demo.launch()<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-804y8a">让我们逐步解释上面的代码：</p> <ul data-svelte-h="svelte-1n3kmpd"><li>首先，我们定义一个名为 <code>greet()</code> 的函数。在这个例子中，它是一个在你的名字前添加“Hello”的简单函数，不过它可以被替换为任意的 Python 函数。例如，在机器学习的演示中，该函数可以调用机器学习模型对输入进行预测并返回输出。</li> <li>然后，我们创建一个带有三个参数 <code>fn</code> 、 <code>inputs</code> 和 <code>outputs</code> 的 Gradio <code>Interface</code> 。这些参数定义了预测函数，以及我们想要的输入和输出组件的类型。在我们的这个例子中，输入和输出组件都是简单的文本框。</li> <li>最后我们调用创建的 <code>Interface</code> 上的 <code>launch()</code> 方法。</li></ul> <p data-svelte-h="svelte-13ean5n">如果你运行这段代码，下面的界面会自动出现在 Jupyter/Colab notebook 中，或者如果在一个脚本中运行，会自动在浏览器中弹出 <strong><a href="http://localhost:7860" rel="nofollow">http://localhost:7860</a></strong> 。</p> <iframe src="https://course-demos-hello-world.hf.space" frameborder="0" height="250" title="Gradio app" class="container p-0 flex-grow space-iframe" allow="accelerometer; ambient-light-sensor; autoplay; battery; camera; document-domain; encrypted-media; fullscreen; geolocation; gyroscope; layout-animations; legacy-image-formats; magnetometer; microphone; midi; oversized-images; payment; picture-in-picture; publickey-credentials-get; sync-xhr; usb; vr ; wake-lock; xr-spatial-tracking" sandbox="allow-forms allow-modals allow-popups allow-popups-to-escape-sandbox allow-same-origin allow-scripts allow-downloads"></iframe> <p data-svelte-h="svelte-8eh90z">现在，试着使用你自己的名字或其他的输入来试一试这个 GUI！</p> <p data-svelte-h="svelte-11o2aju">你会注意到，在这个 GUI 中，在这个例子中，Gradio 会根据输入参数的名称（<code>name</code>）自动推断文本框顶部的标签。如果你想改变这个标签怎么办？或者，如果你想自定义这个文本框的其他属性？在这种情况下，你可以实例化一个表示输入组件的类。</p> <p data-svelte-h="svelte-tqqosc">看看下面的例子：</p> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5   text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START --><span class="hljs-keyword">import</span> gradio <span class="hljs-keyword">as</span> gr


<span class="hljs-keyword">def</span> <span class="hljs-title function_">greet</span>(<span class="hljs-params">name</span>):
    <span class="hljs-keyword">return</span> <span class="hljs-string">&quot;Hello &quot;</span> + name


<span class="hljs-comment"># 我们将文本框类实例化</span>
textbox = gr.Textbox(label=<span class="hljs-string">&quot;Type your name here:&quot;</span>, placeholder=<span class="hljs-string">&quot;John Doe&quot;</span>, lines=<span class="hljs-number">2</span>)

gr.Interface(fn=greet, inputs=textbox, outputs=<span class="hljs-string">&quot;text&quot;</span>).launch()<!-- HTML_TAG_END --></pre></div> <iframe src="https://course-demos-hello-world-custom.hf.space" frameborder="0" height="300" title="Gradio app" class="container p-0 flex-grow space-iframe" allow="accelerometer; ambient-light-sensor; autoplay; battery; camera; document-domain; encrypted-media; fullscreen; geolocation; gyroscope; layout-animations; legacy-image-formats; magnetometer; microphone; midi; oversized-images; payment; picture-in-picture; publickey-credentials-get; sync-xhr; usb; vr ; wake-lock; xr-spatial-tracking" sandbox="allow-forms allow-modals allow-popups allow-popups-to-escape-sandbox allow-same-origin allow-scripts allow-downloads"></iframe> <p data-svelte-h="svelte-1mgzc85">在上面的代码中，我们创建了一个带有自定义标签、预设的占位符和固定行数的输入文本框。同时，你也可以自定义输出文本框，但我们现在先不管它。</p> <p data-svelte-h="svelte-1nnnv7h">我们已经看到，只需几行代码，Gradio 就能让你围绕任何函数创建一个简单的界面，同时兼容各种类型的输入或输出。在本节中，我们先从一个简单的文本框开始，但在接下来的节中，我们将介绍其他类型的输入和输出。现在让我们看一下如何在 Gradio 应用中包含一些自然语言处理（NLP）模型。</p>  <h2 class="relative group"><a id="🤖 使用模型预测" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#🤖 使用模型预测"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>🤖 使用模型预测</span></h2> <p data-svelte-h="svelte-1wyvxhu">现在让我们构建一个简单的界面，让你可以在这个界面中演示像 GPT-2 这样的<strong>文本生成</strong>模型。</p> <p data-svelte-h="svelte-10jy9dt">我们将使用 🤗 Transformers 中的 <code>pipeline()</code> 函数加载我们的模型。
如果你需要快速复习，你可以返回到 <a href="/course/chapter1/3#text-generation">第一章</a> 进行回顾。</p> <p data-svelte-h="svelte-1jk7hhy">首先，我们定义一个预测函数，它接收一个文本输入并返回文本生成的结果：</p> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5   text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START --><span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> pipeline

model = pipeline(<span class="hljs-string">&quot;text-generation&quot;</span>)


<span class="hljs-keyword">def</span> <span class="hljs-title function_">predict</span>(<span class="hljs-params">prompt</span>):
    completion = model(prompt)[<span class="hljs-number">0</span>][<span class="hljs-string">&quot;generated_text&quot;</span>]
    <span class="hljs-keyword">return</span> completion<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1772wow">此函数会不断接龙补全输入，你可以自己尝试各种输入来查看它是如何运行的。下面是一个示例（你可能会得到不同的输出结果）：</p> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5   text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START --><span class="hljs-function"><span class="hljs-title">predict</span><span class="hljs-params">(<span class="hljs-string">&quot;My favorite programming language is&quot;</span>)</span></span><!-- HTML_TAG_END --></pre></div> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5   text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START -->&gt;&gt; My favorite programming language <span class="hljs-keyword">is</span> Haskell. I really enjoyed <span class="hljs-keyword">the</span> Haskell language, <span class="hljs-keyword">but</span> <span class="hljs-keyword">it</span> doesn&#x27;t have all <span class="hljs-keyword">the</span> features <span class="hljs-keyword">that</span> can be applied <span class="hljs-keyword">to</span> any other language. For example, all <span class="hljs-keyword">it</span> <span class="hljs-keyword">does</span> <span class="hljs-keyword">is</span> compile <span class="hljs-keyword">to</span> a byte array.<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-o7thcq">现在我们有了一个生成预测的函数，接下来可以像之前一样创建和启动一个 <code>Interface</code> ：</p> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5   text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START --><span class="hljs-keyword">import</span> gradio <span class="hljs-keyword">as</span> gr

gr.Interface(fn=predict, inputs=<span class="hljs-string">&quot;text&quot;</span>, outputs=<span class="hljs-string">&quot;text&quot;</span>).launch()<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-avnz2">就是这样！你现在可以在 Interface 创建的 Web 网页上使用 GPT-2 模型生成文本，如下所示 🤯：</p> <iframe src="https://course-demos-gpt-2.hf.space" frameborder="0" height="300" title="Gradio app" class="container p-0 flex-grow space-iframe" allow="accelerometer; ambient-light-sensor; autoplay; battery; camera; document-domain; encrypted-media; fullscreen; geolocation; gyroscope; layout-animations; legacy-image-formats; magnetometer; microphone; midi; oversized-images; payment; picture-in-picture; publickey-credentials-get; sync-xhr; usb; vr ; wake-lock; xr-spatial-tracking" sandbox="allow-forms allow-modals allow-popups allow-popups-to-escape-sandbox allow-same-origin allow-scripts allow-downloads"></iframe> <p data-svelte-h="svelte-lewjhk">接下来，让我们一起了解一下如何使用 Gradio 构建其他输入输出类型的演示！</p> <a class="!text-gray-400 !no-underline text-sm flex items-center not-prose mt-4" href="https://github.com/huggingface/course/blob/main/chapters/zh-CN/chapter9/2.mdx" target="_blank"><span data-svelte-h="svelte-1kd6by1">&lt;</span> <span data-svelte-h="svelte-x0xyl0">&gt;</span> <span data-svelte-h="svelte-1dajgef"><span class="underline ml-1.5">Update</span> on GitHub</span></a>  <p></p> 
			
			<script>
				{
					__sveltekit_9aawfw = {
						assets: "/docs/course/pr_1021/zh-CN",
						base: "/docs/course/pr_1021/zh-CN",
						env: {}
					};

					const element = document.currentScript.parentElement;

					const data = [null,null];

					Promise.all([
						import("/docs/course/pr_1021/zh-CN/_app/immutable/entry/start.f3a1a511.js"),
						import("/docs/course/pr_1021/zh-CN/_app/immutable/entry/app.c39e37cf.js")
					]).then(([kit, app]) => {
						kit.start(app, element, {
							node_ids: [0, 71],
							data,
							form: null,
							error: null
						});
					});
				}
			</script>