Buckets:

hf-doc-build
/

doc-dev

Files

xet

hf-doc-build/doc-dev / lerobot /pr_3313 /en /act.html

HuggingFaceDocBuilder

about 1 month ago

download

raw

24.6 kB

	<meta charset="utf-8" /><meta name="hf:doc:metadata" content="{"title":"ACT (Action Chunking with Transformers)","local":"act-action-chunking-with-transformers","sections":[{"title":"Model Overview","local":"model-overview","sections":[{"title":"Why ACT is Great for Beginners","local":"why-act-is-great-for-beginners","sections":[],"depth":3},{"title":"Architecture","local":"architecture","sections":[],"depth":3}],"depth":2},{"title":"Installation Requirements","local":"installation-requirements","sections":[],"depth":2},{"title":"Training ACT","local":"training-act","sections":[{"title":"Training Tips","local":"training-tips","sections":[],"depth":3},{"title":"Train using Google Colab","local":"train-using-google-colab","sections":[],"depth":3}],"depth":2},{"title":"Evaluating ACT","local":"evaluating-act","sections":[],"depth":2}],"depth":1}">
	<link href="/docs/lerobot/pr_3313/en/_app/immutable/assets/0.e3b0c442.css" rel="modulepreload">
	<link rel="modulepreload" href="/docs/lerobot/pr_3313/en/_app/immutable/entry/start.d3f1c0f3.js">
	<link rel="modulepreload" href="/docs/lerobot/pr_3313/en/_app/immutable/chunks/scheduler.eb244325.js">
	<link rel="modulepreload" href="/docs/lerobot/pr_3313/en/_app/immutable/chunks/singletons.1f33814c.js">
	<link rel="modulepreload" href="/docs/lerobot/pr_3313/en/_app/immutable/chunks/index.3c23fb4b.js">
	<link rel="modulepreload" href="/docs/lerobot/pr_3313/en/_app/immutable/chunks/paths.17f05d75.js">
	<link rel="modulepreload" href="/docs/lerobot/pr_3313/en/_app/immutable/entry/app.04bb7687.js">
	<link rel="modulepreload" href="/docs/lerobot/pr_3313/en/_app/immutable/chunks/preload-helper.b00aacbc.js">
	<link rel="modulepreload" href="/docs/lerobot/pr_3313/en/_app/immutable/chunks/index.3fe63ad3.js">
	<link rel="modulepreload" href="/docs/lerobot/pr_3313/en/_app/immutable/nodes/0.07fbe93e.js">
	<link rel="modulepreload" href="/docs/lerobot/pr_3313/en/_app/immutable/chunks/each.e59479a4.js">
	<link rel="modulepreload" href="/docs/lerobot/pr_3313/en/_app/immutable/nodes/2.165276e7.js">
	<link rel="modulepreload" href="/docs/lerobot/pr_3313/en/_app/immutable/chunks/CopyLLMTxtMenu.d0c64540.js">
	<link rel="modulepreload" href="/docs/lerobot/pr_3313/en/_app/immutable/chunks/MermaidChart.svelte_svelte_type_style_lang.6453902c.js">
	<link rel="modulepreload" href="/docs/lerobot/pr_3313/en/_app/immutable/chunks/CodeBlock.48dd2cc2.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{"title":"ACT (Action Chunking with Transformers)","local":"act-action-chunking-with-transformers","sections":[{"title":"Model Overview","local":"model-overview","sections":[{"title":"Why ACT is Great for Beginners","local":"why-act-is-great-for-beginners","sections":[],"depth":3},{"title":"Architecture","local":"architecture","sections":[],"depth":3}],"depth":2},{"title":"Installation Requirements","local":"installation-requirements","sections":[],"depth":2},{"title":"Training ACT","local":"training-act","sections":[{"title":"Training Tips","local":"training-tips","sections":[],"depth":3},{"title":"Train using Google Colab","local":"train-using-google-colab","sections":[],"depth":3}],"depth":2},{"title":"Evaluating ACT","local":"evaluating-act","sections":[],"depth":2}],"depth":1}"><!-- HEAD_svelte-u9bgzb_END --> <p></p> <div class="items-center shrink-0 min-w-[100px] max-sm:min-w-[50px] justify-end ml-auto flex" style="float: right; margin-left: 10px; display: inline-flex; position: relative; z-index: 10;"><div class="inline-flex rounded-md max-sm:rounded-sm"><button class="inline-flex items-center gap-1 h-7 max-sm:h-7 px-2 max-sm:px-1.5 text-sm font-medium text-gray-800 border border-r-0 rounded-l-md max-sm:rounded-l-sm border-gray-200 bg-white hover:shadow-inner dark:border-gray-850 dark:bg-gray-950 dark:text-gray-200 dark:hover:bg-gray-800" aria-live="polite"><span class="inline-flex items-center justify-center rounded-md p-0.5 max-sm:p-0 hover:text-gray-800 dark:hover:text-gray-200"><svg class="sm:size-3.5 size-3" 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></span> <span>Copy page</span></button> <button class="inline-flex items-center justify-center w-6 max-sm:w-5 h-7 max-sm:h-7 disabled:pointer-events-none text-sm text-gray-500 hover:text-gray-700 dark:hover:text-white rounded-r-md max-sm:rounded-r-sm border border-l transition border-gray-200 bg-white hover:shadow-inner dark:border-gray-850 dark:bg-gray-950 dark:text-gray-200 dark:hover:bg-gray-800" aria-haspopup="menu" aria-expanded="false" aria-label="Open copy menu"><svg class="transition-transform text-gray-400 overflow-visible sm:size-3.5 size-3 rotate-0" width="1em" height="1em" viewBox="0 0 12 7" fill="none" xmlns="http://www.w3.org/2000/svg"><path d="M1 1L6 6L11 1" stroke="currentColor"></path></svg></button></div> </div> <h1 class="relative group"><a id="act-action-chunking-with-transformers" 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="#act-action-chunking-with-transformers"><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>ACT (Action Chunking with Transformers)</span></h1> <p data-svelte-h="svelte-2rxj3e">ACT is a <strong>lightweight and efficient policy for imitation learning</strong>, especially well-suited for fine-grained manipulation tasks. It’s the <strong>first model we recommend when you’re starting out</strong> with LeRobot due to its fast training time, low computational requirements, and strong performance.</p> <div class="video-container" data-svelte-h="svelte-1h3u8cb"><iframe width="100%" height="415" src="https://www.youtube.com/embed/ft73x0LfGpM" title="LeRobot ACT Tutorial" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture" allowfullscreen=""></iframe></div> <p data-svelte-h="svelte-1fqcgvo"><em>Watch this tutorial from the LeRobot team to learn how ACT works: <a href="https://www.youtube.com/watch?v=ft73x0LfGpM" rel="nofollow">LeRobot ACT Tutorial</a></em></p> <h2 class="relative group"><a id="model-overview" 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="#model-overview"><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>Model Overview</span></h2> <p data-svelte-h="svelte-1h56odq">Action Chunking with Transformers (ACT) was introduced in the paper <a href="https://arxiv.org/abs/2304.13705" rel="nofollow">Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware</a> by Zhao et al. The policy was designed to enable precise, contact-rich manipulation tasks using affordable hardware and minimal demonstration data.</p> <h3 class="relative group"><a id="why-act-is-great-for-beginners" 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="#why-act-is-great-for-beginners"><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>Why ACT is Great for Beginners</span></h3> <p data-svelte-h="svelte-khub2q">ACT stands out as an excellent starting point for several reasons:</p> <ul data-svelte-h="svelte-nxnlib"><li><strong>Fast Training</strong>: Trains in a few hours on a single GPU</li> <li><strong>Lightweight</strong>: Only ~80M parameters, making it efficient and easy to work with</li> <li><strong>Data Efficient</strong>: Often achieves high success rates with just 50 demonstrations</li></ul> <h3 class="relative group"><a id="architecture" 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="#architecture"><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>Architecture</span></h3> <p data-svelte-h="svelte-1824b52">ACT uses a transformer-based architecture with three main components:</p> <ol data-svelte-h="svelte-bt6zwh"><li><strong>Vision Backbone</strong>: ResNet-18 processes images from multiple camera viewpoints</li> <li><strong>Transformer Encoder</strong>: Synthesizes information from camera features, joint positions, and a learned latent variable</li> <li><strong>Transformer Decoder</strong>: Generates coherent action sequences using cross-attention</li></ol> <p data-svelte-h="svelte-1kx3ikv">The policy takes as input:</p> <ul data-svelte-h="svelte-12ohat1"><li>Multiple RGB images (e.g., from wrist cameras, front/top cameras)</li> <li>Current robot joint positions</li> <li>A latent style variable <code>z</code> (learned during training, set to zero during inference)</li></ul> <p data-svelte-h="svelte-hkbv3x">And outputs a chunk of <code>k</code> future action sequences.</p> <h2 class="relative group"><a id="installation-requirements" 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="#installation-requirements"><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>Installation Requirements</span></h2> <ol data-svelte-h="svelte-dngimr"><li>Install LeRobot by following our <a href="./installation">Installation Guide</a>.</li> <li>ACT is included in the base LeRobot installation, so no additional dependencies are needed!</li></ol> <h2 class="relative group"><a id="training-act" 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="#training-act"><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>Training ACT</span></h2> <p data-svelte-h="svelte-11n6yii">ACT works seamlessly with the standard LeRobot training pipeline. Here’s a complete example for training ACT on your dataset:</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 -->lerobot-train \
	--dataset.repo_id=<span class="hljs-variable">${HF_USER}</span>/your_dataset \
	--policy.type=act \
	--output_dir=outputs/train/act_your_dataset \
	--job_name=act_your_dataset \
	--policy.device=cuda \
	--wandb.enable=<span class="hljs-literal">true</span> \
	--policy.repo_id=<span class="hljs-variable">${HF_USER}</span>/act_policy<!-- HTML_TAG_END --></pre></div> <h3 class="relative group"><a id="training-tips" 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="#training-tips"><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>Training Tips</span></h3> <ol data-svelte-h="svelte-1rfexkv"><li><strong>Start with defaults</strong>: ACT’s default hyperparameters work well for most tasks</li> <li><strong>Training duration</strong>: Expect a few hours for 100k training steps on a single GPU</li> <li><strong>Batch size</strong>: Start with batch size 8 and adjust based on your GPU memory</li></ol> <h3 class="relative group"><a id="train-using-google-colab" 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="#train-using-google-colab"><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>Train using Google Colab</span></h3> <p data-svelte-h="svelte-izbhhn">If your local computer doesn’t have a powerful GPU, you can utilize Google Colab to train your model by following the <a href="./notebooks#training-act">ACT training notebook</a>.</p> <h2 class="relative group"><a id="evaluating-act" 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="#evaluating-act"><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>Evaluating ACT</span></h2> <p data-svelte-h="svelte-10yvdsz">Once training is complete, you can evaluate your ACT policy using the <code>lerobot-record</code> command with your trained policy. This will run inference and record evaluation episodes:</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 -->lerobot-record \
	--robot.type=so100_follower \
	--robot.port=/dev/ttyACM0 \
	--robot.id=my_robot \
	--robot.cameras=<span class="hljs-string">"{ front: {type: opencv, index_or_path: 0, width: 640, height: 480, fps: 30}}"</span> \
	--display_data=<span class="hljs-literal">true</span> \
	--dataset.repo_id=<span class="hljs-variable">${HF_USER}</span>/eval_act_your_dataset \
	--dataset.num_episodes=10 \
	--dataset.single_task=<span class="hljs-string">"Your task description"</span> \
	--dataset.streaming_encoding=<span class="hljs-literal">true</span> \
	--dataset.encoder_threads=2 \
	<span class="hljs-comment"># --dataset.vcodec=auto \</span>
	--policy.path=<span class="hljs-variable">${HF_USER}</span>/act_policy<!-- HTML_TAG_END --></pre></div> <a class="!text-gray-400 !no-underline text-sm flex items-center not-prose mt-4" href="https://github.com/huggingface/lerobot/blob/main/docs/source/act.mdx" target="_blank"><svg class="mr-1" 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="M31,16l-7,7l-1.41-1.41L28.17,16l-5.58-5.59L24,9l7,7z"></path><path d="M1,16l7-7l1.41,1.41L3.83,16l5.58,5.59L8,23l-7-7z"></path><path d="M12.419,25.484L17.639,6.552l1.932,0.518L14.351,26.002z"></path></svg> <span data-svelte-h="svelte-zjs2n5"><span class="underline">Update</span> on GitHub</span></a> <p></p>

	<script>
	{
	__sveltekit_9kza6s = {
	assets: "/docs/lerobot/pr_3313/en",
	base: "/docs/lerobot/pr_3313/en",
	env: {}
	};

	const element = document.currentScript.parentElement;

	const data = [null,null];

	Promise.all([
	import("/docs/lerobot/pr_3313/en/_app/immutable/entry/start.d3f1c0f3.js"),
	import("/docs/lerobot/pr_3313/en/_app/immutable/entry/app.04bb7687.js")
	]).then(([kit, app]) => {
	kit.start(app, element, {
	node_ids: [0, 2],
	data,
	form: null,
	error: null
	});
	});
	}
	</script>

Xet Storage Details

Size:: 24.6 kB
Xet hash:: 8b1e9eddda9a07d7373434515dcad75fa72587464c7a4fc59936930ff31b89c4

Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.