Buckets:

rtrm's picture
download
raw
12 kB
<meta charset="utf-8" /><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;TFLite로 내보내기&quot;,&quot;local&quot;:&quot;export-to-tflite&quot;,&quot;sections&quot;:[],&quot;depth&quot;:1}">
<link href="/docs/transformers/main/ko/_app/immutable/assets/0.e3b0c442.css" rel="modulepreload">
<link rel="modulepreload" href="/docs/transformers/main/ko/_app/immutable/entry/start.9aa88961.js">
<link rel="modulepreload" href="/docs/transformers/main/ko/_app/immutable/chunks/scheduler.9bc65507.js">
<link rel="modulepreload" href="/docs/transformers/main/ko/_app/immutable/chunks/singletons.9eec45c3.js">
<link rel="modulepreload" href="/docs/transformers/main/ko/_app/immutable/chunks/index.3b203c72.js">
<link rel="modulepreload" href="/docs/transformers/main/ko/_app/immutable/chunks/paths.566078f7.js">
<link rel="modulepreload" href="/docs/transformers/main/ko/_app/immutable/entry/app.84fb67c3.js">
<link rel="modulepreload" href="/docs/transformers/main/ko/_app/immutable/chunks/index.707bf1b6.js">
<link rel="modulepreload" href="/docs/transformers/main/ko/_app/immutable/nodes/0.1c99376b.js">
<link rel="modulepreload" href="/docs/transformers/main/ko/_app/immutable/chunks/each.e59479a4.js">
<link rel="modulepreload" href="/docs/transformers/main/ko/_app/immutable/nodes/90.c8a9191d.js">
<link rel="modulepreload" href="/docs/transformers/main/ko/_app/immutable/chunks/CodeBlock.54a9f38d.js">
<link rel="modulepreload" href="/docs/transformers/main/ko/_app/immutable/chunks/EditOnGithub.922df6ba.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;TFLite로 내보내기&quot;,&quot;local&quot;:&quot;export-to-tflite&quot;,&quot;sections&quot;:[],&quot;depth&quot;:1}"><!-- HEAD_svelte-u9bgzb_END --> <p></p> <h1 class="relative group"><a id="export-to-tflite" 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="#export-to-tflite"><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>TFLite로 내보내기</span></h1> <p data-svelte-h="svelte-rtedjj"><a href="https://www.tensorflow.org/lite/guide" rel="nofollow">TensorFlow Lite</a>는 자원이 제한된 휴대폰, 임베디드 시스템, 사물인터넷(IoT) 기기에서
기계학습 모델을 배포하기 위한 경량 프레임워크입니다.
TFLite는 연산 능력, 메모리, 전력 소비가 제한된 기기에서 모델을 효율적으로 최적화하고 실행하기 위해
설계되었습니다.
TensorFlow Lite 모델은 <code>.tflite</code> 파일 확장자로 식별되는 특수하고 효율적인 휴대용 포맷으로 표현됩니다.</p> <p data-svelte-h="svelte-1el6uae">🤗 Optimum은 <code>exporters.tflite</code> 모듈로 🤗 Transformers 모델을 TFLite로 내보내는 기능을 제공합니다.
지원되는 모델 아키텍처 목록은 <a href="https://huggingface.co/docs/optimum/exporters/tflite/overview" rel="nofollow">🤗 Optimum 문서</a>를 참고하세요.</p> <p data-svelte-h="svelte-lou0zf">모델을 TFLite로 내보내려면, 필요한 종속성을 설치하세요:</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 optimum[exporters-tf]<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-yqbvuw">모든 사용 가능한 인수를 확인하려면, <a href="https://huggingface.co/docs/optimum/main/en/exporters/tflite/usage_guides/export_a_model" rel="nofollow">🤗 Optimum 문서</a>를 참고하거나
터미널에서 도움말을 살펴보세요:</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 -->optimum-cli <span class="hljs-built_in">export</span> tflite --<span class="hljs-built_in">help</span><!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1g0t3kf">예를 들어 🤗 Hub에서의 <code>google-bert/bert-base-uncased</code> 모델 체크포인트를 내보내려면, 다음 명령을 실행하세요:</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 -->optimum-cli <span class="hljs-built_in">export</span> tflite --model google-bert/bert-base-uncased --sequence_length 128 bert_tflite/<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-167y084">다음과 같이 진행 상황을 나타내는 로그와 결과물인 <code>model.tflite</code>가 저장된 위치를 보여주는 로그가 표시됩니다:</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 -->Validating TFLite model...
-[✓] TFLite model output names match reference model (logits)
- Validating TFLite Model output <span class="hljs-string">&quot;logits&quot;</span>:
-[✓] (1, 128, 30522) matches (1, 128, 30522)
-[x] values not close enough, max diff: 5.817413330078125e-05 (atol: 1e-05)
The TensorFlow Lite <span class="hljs-built_in">export</span> succeeded with the warning: The maximum absolute difference between the output of the reference model and the TFLite exported model is not within the <span class="hljs-built_in">set</span> tolerance 1e-05:
- logits: max diff = 5.817413330078125e-05.
The exported model was saved at: bert_tflite<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-drx2q5">위 예제는 🤗 Hub에서의 체크포인트를 내보내는 방법을 보여줍니다.
로컬 모델을 내보낸다면, 먼저 모델 가중치와 토크나이저 파일이 모두 같은 디렉터리( <code>local_path</code> )에 저장됐는지 확인하세요.
CLI를 사용할 때, 🤗 Hub에서의 체크포인트 이름 대신 <code>model</code> 인수에 <code>local_path</code>를 전달하면 됩니다.</p> <a class="!text-gray-400 !no-underline text-sm flex items-center not-prose mt-4" href="https://github.com/huggingface/transformers/blob/main/docs/source/ko/tflite.md" 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_1hrx8 = {
assets: "/docs/transformers/main/ko",
base: "/docs/transformers/main/ko",
env: {}
};
const element = document.currentScript.parentElement;
const data = [null,null];
Promise.all([
import("/docs/transformers/main/ko/_app/immutable/entry/start.9aa88961.js"),
import("/docs/transformers/main/ko/_app/immutable/entry/app.84fb67c3.js")
]).then(([kit, app]) => {
kit.start(app, element, {
node_ids: [0, 90],
data,
form: null,
error: null
});
});
}
</script>

Xet Storage Details

Size:
12 kB
·
Xet hash:
680c74ad54290b4d710cbeecb299a4f7401b8bb288c0e0a4a8500870addee6b7

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