Buckets:
| <meta charset="utf-8" /><meta name="hf:doc:metadata" content="{"title":"Export to ONNX","local":"export-to-onnx","sections":[{"title":"Export to ONNX","local":"export-to-onnx","sections":[{"title":"Exporting a 🤗 Transformers model to ONNX with CLI","local":"exporting-a--transformers-model-to-onnx-with-cli","sections":[],"depth":3},{"title":"Exporting a 🤗 Transformers model to ONNX with optimum.onnxruntime","local":"exporting-a--transformers-model-to-onnx-with-optimumonnxruntime","sections":[],"depth":3},{"title":"Exporting a model for an unsupported architecture","local":"exporting-a-model-for-an-unsupported-architecture","sections":[],"depth":3},{"title":"Exporting a model with transformers.onnx","local":"exporting-a-model-with-transformersonnx","sections":[],"depth":3}],"depth":2}],"depth":1}"> | |
| <link href="/docs/transformers/pr_33913/ja/_app/immutable/assets/0.e3b0c442.css" rel="modulepreload"> | |
| <link rel="modulepreload" href="/docs/transformers/pr_33913/ja/_app/immutable/entry/start.17a8f5f1.js"> | |
| <link rel="modulepreload" href="/docs/transformers/pr_33913/ja/_app/immutable/chunks/scheduler.9bc65507.js"> | |
| <link rel="modulepreload" href="/docs/transformers/pr_33913/ja/_app/immutable/chunks/singletons.01391f4e.js"> | |
| <link rel="modulepreload" href="/docs/transformers/pr_33913/ja/_app/immutable/chunks/index.3b203c72.js"> | |
| <link rel="modulepreload" href="/docs/transformers/pr_33913/ja/_app/immutable/chunks/paths.d7050e6d.js"> | |
| <link rel="modulepreload" href="/docs/transformers/pr_33913/ja/_app/immutable/entry/app.ec1e8c3e.js"> | |
| <link rel="modulepreload" href="/docs/transformers/pr_33913/ja/_app/immutable/chunks/index.707bf1b6.js"> | |
| <link rel="modulepreload" href="/docs/transformers/pr_33913/ja/_app/immutable/nodes/0.29a283e1.js"> | |
| <link rel="modulepreload" href="/docs/transformers/pr_33913/ja/_app/immutable/chunks/each.e59479a4.js"> | |
| <link rel="modulepreload" href="/docs/transformers/pr_33913/ja/_app/immutable/nodes/133.1712f367.js"> | |
| <link rel="modulepreload" href="/docs/transformers/pr_33913/ja/_app/immutable/chunks/Tip.c2ecdbf4.js"> | |
| <link rel="modulepreload" href="/docs/transformers/pr_33913/ja/_app/immutable/chunks/CodeBlock.54a9f38d.js"> | |
| <link rel="modulepreload" href="/docs/transformers/pr_33913/ja/_app/immutable/chunks/EditOnGithub.922df6ba.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{"title":"Export to ONNX","local":"export-to-onnx","sections":[{"title":"Export to ONNX","local":"export-to-onnx","sections":[{"title":"Exporting a 🤗 Transformers model to ONNX with CLI","local":"exporting-a--transformers-model-to-onnx-with-cli","sections":[],"depth":3},{"title":"Exporting a 🤗 Transformers model to ONNX with optimum.onnxruntime","local":"exporting-a--transformers-model-to-onnx-with-optimumonnxruntime","sections":[],"depth":3},{"title":"Exporting a model for an unsupported architecture","local":"exporting-a-model-for-an-unsupported-architecture","sections":[],"depth":3},{"title":"Exporting a model with transformers.onnx","local":"exporting-a-model-with-transformersonnx","sections":[],"depth":3}],"depth":2}],"depth":1}"><!-- HEAD_svelte-u9bgzb_END --> <p></p> <h1 class="relative group"><a id="export-to-onnx" 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-onnx"><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>Export to ONNX</span></h1> <p data-svelte-h="svelte-qc94t0">🤗 Transformersモデルを本番環境に展開する際には、モデルを特殊なランタイムおよびハードウェアで読み込み、実行できるように、モデルをシリアライズされた形式にエクスポートすることが必要であるか、その恩恵を受けることができることがあります。</p> <p data-svelte-h="svelte-1557kk1">🤗 Optimumは、Transformersの拡張機能であり、PyTorchまたはTensorFlowからモデルをONNXやTFLiteなどのシリアライズされた形式にエクスポートすることを可能にする「exporters」モジュールを提供しています。また、🤗 Optimumは、最大の効率でターゲットハードウェアでモデルをトレーニングおよび実行するためのパフォーマンス最適化ツールも提供しています。</p> <p data-svelte-h="svelte-ht5c1x">このガイドでは、🤗 Transformersモデルを🤗 Optimumを使用してONNXにエクスポートする方法を示しており、モデルをTFLiteにエクスポートする方法については<a href="tflite">Export to TFLiteページ</a>を参照してください。</p> <h2 class="relative group"><a id="export-to-onnx" 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-onnx"><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>Export to ONNX</span></h2> <p data-svelte-h="svelte-1jftxm"><a href="http://onnx.ai" rel="nofollow">ONNX（Open Neural Network eXchange）</a>は、PyTorchおよびTensorFlowを含むさまざまなフレームワークで深層学習モデルを表現するための共通の一連の演算子とファイル形式を定義するオープンスタンダードです。モデルがONNX形式にエクスポートされると、これらの演算子はニューラルネットワークを介するデータの流れを表す計算グラフ（一般的には「中間表現」と呼ばれる）を構築するために使用されます。</p> <p data-svelte-h="svelte-r6157j">標準化された演算子とデータ型を備えたグラフを公開することで、ONNXはフレームワーク間の切り替えを容易にします。たとえば、PyTorchでトレーニングされたモデルはONNX形式にエクスポートし、それをTensorFlowでインポートすることができます（逆も同様です）。</p> <p data-svelte-h="svelte-7mahc9">ONNX形式にエクスポートされたモデルは、以下のように使用できます：</p> <ul data-svelte-h="svelte-18iooio"><li><a href="https://huggingface.co/docs/optimum/onnxruntime/usage_guides/optimization" rel="nofollow">グラフ最適化</a>や<a href="https://huggingface.co/docs/optimum/onnxruntime/usage_guides/quantization" rel="nofollow">量子化</a>などのテクニックを使用して推論のために最適化。</li> <li><a href="https://huggingface.co/docs/optimum/onnxruntime/package_reference/modeling_ort" rel="nofollow"><code>ORTModelForXXX</code>クラス</a>を介してONNX Runtimeで実行し、🤗 Transformersでおなじみの<code>AutoModel</code> APIに従います。</li> <li><a href="https://huggingface.co/docs/optimum/main/en/onnxruntime/usage_guides/pipelines" rel="nofollow">最適化された推論パイプライン</a>を介して実行し、🤗 Transformersの<a href="/docs/transformers/pr_33913/ja/main_classes/pipelines#transformers.pipeline">pipeline()</a>関数と同じAPIを持っています。</li></ul> <p data-svelte-h="svelte-1c7xacs">🤗 Optimumは、設定オブジェクトを活用してONNXエクスポートをサポートしており、これらの設定オブジェクトは多くのモデルアーキテクチャ用に事前に作成されており、他のアーキテクチャにも簡単に拡張できるように設計されています。</p> <p data-svelte-h="svelte-td5fmw">事前に作成された設定のリストについては、<a href="https://huggingface.co/docs/optimum/exporters/onnx/overview" rel="nofollow">🤗 Optimumドキュメント</a>を参照してください。</p> <p data-svelte-h="svelte-hejyb2">🤗 TransformersモデルをONNXにエクスポートする方法は2つあります。以下では両方の方法を示します：</p> <ul data-svelte-h="svelte-18tahix"><li>export with 🤗 Optimum via CLI.</li> <li>export with 🤗 Optimum with <code>optimum.onnxruntime</code>.</li></ul> <h3 class="relative group"><a id="exporting-a--transformers-model-to-onnx-with-cli" 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="#exporting-a--transformers-model-to-onnx-with-cli"><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>Exporting a 🤗 Transformers model to ONNX with CLI</span></h3> <p data-svelte-h="svelte-ql60kh">🤗 TransformersモデルをONNXにエクスポートするには、まず追加の依存関係をインストールしてください：</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]<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-g5msyl">すべての利用可能な引数を確認するには、<a href="https://huggingface.co/docs/optimum/exporters/onnx/usage_guides/export_a_model#exporting-a-model-to-onnx-using-the-cli" rel="nofollow">🤗 Optimumドキュメント</a>を参照してください。または、コマンドラインでヘルプを表示することもできます：</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> onnx --<span class="hljs-built_in">help</span><!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1xswql7">🤗 Hubからモデルのチェックポイントをエクスポートするには、例えば <code>distilbert/distilbert-base-uncased-distilled-squad</code> を使いたい場合、以下のコマンドを実行してください：</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> onnx --model distilbert/distilbert-base-uncased-distilled-squad distilbert_base_uncased_squad_onnx/<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-e4t3p2">進行状況を示し、結果の <code>model.onnx</code> が保存される場所を表示するログは、以下のように表示されるはずです：</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 ONNX model distilbert_base_uncased_squad_onnx/model.onnx... | |
| -[✓] ONNX model output names match reference model (start_logits, end_logits) | |
| - Validating ONNX Model output <span class="hljs-string">"start_logits"</span>: | |
| -[✓] (2, 16) matches (2, 16) | |
| -[✓] all values close (atol: 0.0001) | |
| - Validating ONNX Model output <span class="hljs-string">"end_logits"</span>: | |
| -[✓] (2, 16) matches (2, 16) | |
| -[✓] all values close (atol: 0.0001) | |
| The ONNX <span class="hljs-built_in">export</span> succeeded and the exported model was saved at: distilbert_base_uncased_squad_onnx<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1de804l">上記の例は🤗 Hubからのチェックポイントのエクスポートを示しています。ローカルモデルをエクスポートする場合、まずモデルの重みとトークナイザのファイルを同じディレクトリ（<code>local_path</code>）に保存してください。CLIを使用する場合、🤗 Hubのチェックポイント名の代わりに<code>model</code>引数に<code>local_path</code>を渡し、<code>--task</code>引数を指定してください。<a href="https://huggingface.co/docs/optimum/exporters/task_manager" rel="nofollow">🤗 Optimumドキュメント</a>でサポートされているタスクのリストを確認できます。<code>task</code>引数が指定されていない場合、タスク固有のヘッドを持たないモデルアーキテクチャがデフォルトで選択されます。</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> onnx --model local_path --task question-answering distilbert_base_uncased_squad_onnx/<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1rwgg53">エクスポートされた <code>model.onnx</code> ファイルは、ONNX標準をサポートする<a href="https://onnx.ai/supported-tools.html#deployModel" rel="nofollow">多くのアクセラレータ</a>の1つで実行できます。たとえば、<a href="https://onnxruntime.ai/" rel="nofollow">ONNX Runtime</a>を使用してモデルを読み込み、実行する方法は以下の通りです：</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-meta">>>> </span><span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> AutoTokenizer | |
| <span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> optimum.onnxruntime <span class="hljs-keyword">import</span> ORTModelForQuestionAnswering | |
| <span class="hljs-meta">>>> </span>tokenizer = AutoTokenizer.from_pretrained(<span class="hljs-string">"distilbert_base_uncased_squad_onnx"</span>) | |
| <span class="hljs-meta">>>> </span>model = ORTModelForQuestionAnswering.from_pretrained(<span class="hljs-string">"distilbert_base_uncased_squad_onnx"</span>) | |
| <span class="hljs-meta">>>> </span>inputs = tokenizer(<span class="hljs-string">"What am I using?"</span>, <span class="hljs-string">"Using DistilBERT with ONNX Runtime!"</span>, return_tensors=<span class="hljs-string">"pt"</span>) | |
| <span class="hljs-meta">>>> </span>outputs = model(**inputs)<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1e2boax">🤗 HubからTensorFlowのチェックポイントをエクスポートするプロセスは、同様です。例えば、<a href="https://huggingface.co/keras-io" rel="nofollow">Keras organization</a>から純粋なTensorFlowのチェックポイントをエクスポートする方法は以下の通りです：</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> onnx --model keras-io/transformers-qa distilbert_base_cased_squad_onnx/<!-- HTML_TAG_END --></pre></div> <h3 class="relative group"><a id="exporting-a--transformers-model-to-onnx-with-optimumonnxruntime" 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="#exporting-a--transformers-model-to-onnx-with-optimumonnxruntime"><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>Exporting a 🤗 Transformers model to ONNX with optimum.onnxruntime</span></h3> <p data-svelte-h="svelte-15ogace">CLIの代わりに、🤗 TransformersモデルをONNXにプログラム的にエクスポートすることもできます。以下のように行います：</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-meta">>>> </span><span class="hljs-keyword">from</span> optimum.onnxruntime <span class="hljs-keyword">import</span> ORTModelForSequenceClassification | |
| <span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> AutoTokenizer | |
| <span class="hljs-meta">>>> </span>model_checkpoint = <span class="hljs-string">"distilbert_base_uncased_squad"</span> | |
| <span class="hljs-meta">>>> </span>save_directory = <span class="hljs-string">"onnx/"</span> | |
| <span class="hljs-meta">>>> </span><span class="hljs-comment"># Load a model from transformers and export it to ONNX</span> | |
| <span class="hljs-meta">>>> </span>ort_model = ORTModelForSequenceClassification.from_pretrained(model_checkpoint, export=<span class="hljs-literal">True</span>) | |
| <span class="hljs-meta">>>> </span>tokenizer = AutoTokenizer.from_pretrained(model_checkpoint) | |
| <span class="hljs-meta">>>> </span><span class="hljs-comment"># Save the onnx model and tokenizer</span> | |
| <span class="hljs-meta">>>> </span>ort_model.save_pretrained(save_directory) | |
| <span class="hljs-meta">>>> </span>tokenizer.save_pretrained(save_directory)<!-- HTML_TAG_END --></pre></div> <h3 class="relative group"><a id="exporting-a-model-for-an-unsupported-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="#exporting-a-model-for-an-unsupported-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>Exporting a model for an unsupported architecture</span></h3> <p data-svelte-h="svelte-6051gd">現在エクスポートできないモデルをサポートするために貢献したい場合、まず<a href="https://huggingface.co/docs/optimum/exporters/onnx/overview" rel="nofollow"><code>optimum.exporters.onnx</code></a>でサポートされているかどうかを確認し、サポートされていない場合は<a href="https://huggingface.co/docs/optimum/exporters/onnx/usage_guides/contribute" rel="nofollow">🤗 Optimumに貢献</a>してください。</p> <h3 class="relative group"><a id="exporting-a-model-with-transformersonnx" 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="#exporting-a-model-with-transformersonnx"><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>Exporting a model with transformers.onnx</span></h3> <div class="course-tip course-tip-orange bg-gradient-to-br dark:bg-gradient-to-r before:border-orange-500 dark:before:border-orange-800 from-orange-50 dark:from-gray-900 to-white dark:to-gray-950 border border-orange-50 text-orange-700 dark:text-gray-400"><p data-svelte-h="svelte-haasss"><code>transformers.onnx</code>はもはやメンテナンスされていないため、モデルを上記で説明したように🤗 Optimumでエクスポートしてください。このセクションは将来のバージョンで削除されます。</p></div> <p data-svelte-h="svelte-f5cz41">🤗 TransformersモデルをONNXにエクスポートするには、追加の依存関係をインストールしてください：</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 transformers[onnx]<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-foxlz0"><code>transformers.onnx</code>パッケージをPythonモジュールとして使用して、事前に用意された設定を使用してチェックポイントをエクスポートする方法は以下の通りです：</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 -->python -m transformers.onnx --model=distilbert/distilbert-base-uncased onnx/<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-kw829a">この方法は、<code>--model</code>引数で定義されたチェックポイントのONNXグラフをエクスポートします。🤗 Hubのいずれかのチェックポイントまたはローカルに保存されたチェックポイントを渡すことができます。エクスポートされた<code>model.onnx</code>ファイルは、ONNX標準をサポートする多くのアクセラレータで実行できます。例えば、ONNX Runtimeを使用してモデルを読み込んで実行する方法は以下の通りです：</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-meta">>>> </span><span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> AutoTokenizer | |
| <span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> onnxruntime <span class="hljs-keyword">import</span> InferenceSession | |
| <span class="hljs-meta">>>> </span>tokenizer = AutoTokenizer.from_pretrained(<span class="hljs-string">"distilbert/distilbert-base-uncased"</span>) | |
| <span class="hljs-meta">>>> </span>session = InferenceSession(<span class="hljs-string">"onnx/model.onnx"</span>) | |
| <span class="hljs-meta">>>> </span><span class="hljs-comment"># ONNX Runtime expects NumPy arrays as input</span> | |
| <span class="hljs-meta">>>> </span>inputs = tokenizer(<span class="hljs-string">"Using DistilBERT with ONNX Runtime!"</span>, return_tensors=<span class="hljs-string">"np"</span>) | |
| <span class="hljs-meta">>>> </span>outputs = session.run(output_names=[<span class="hljs-string">"last_hidden_state"</span>], input_feed=<span class="hljs-built_in">dict</span>(inputs))<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-xs9tjx">必要な出力名（例: <code>["last_hidden_state"]</code>）は、各モデルのONNX構成を確認することで取得できます。例えば、DistilBERTの場合、次のようになります：</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-meta">>>> </span><span class="hljs-keyword">from</span> transformers.models.distilbert <span class="hljs-keyword">import</span> DistilBertConfig, DistilBertOnnxConfig | |
| <span class="hljs-meta">>>> </span>config = DistilBertConfig() | |
| <span class="hljs-meta">>>> </span>onnx_config = DistilBertOnnxConfig(config) | |
| <span class="hljs-meta">>>> </span><span class="hljs-built_in">print</span>(<span class="hljs-built_in">list</span>(onnx_config.outputs.keys())) | |
| [<span class="hljs-string">"last_hidden_state"</span>]<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1qs89on">ハブから純粋なTensorFlowのチェックポイントをプログラム的にエクスポートするプロセスは、以下のように同様です：</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 -->python -m transformers.onnx --model=keras-io/transformers-qa onnx/<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1c2zce8">ローカルに保存されたモデルをエクスポートする場合、モデルの重みとトークナイザのファイルを同じディレクトリに保存してください（例： <code>local-pt-checkpoint</code>）。その後、<code>transformers.onnx</code>パッケージの <code>--model</code>引数を希望するディレクトリに向けて設定して、ONNXにエクスポートします：</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 -->python -m transformers.onnx --model=local-pt-checkpoint onnx/<!-- 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/transformers/blob/main/docs/source/ja/serialization.md" target="_blank"><span data-svelte-h="svelte-1kd6by1"><</span> <span data-svelte-h="svelte-x0xyl0">></span> <span data-svelte-h="svelte-1dajgef"><span class="underline ml-1.5">Update</span> on GitHub</span></a> <p></p> | |
| <script> | |
| { | |
| __sveltekit_17iw4ji = { | |
| assets: "/docs/transformers/pr_33913/ja", | |
| base: "/docs/transformers/pr_33913/ja", | |
| env: {} | |
| }; | |
| const element = document.currentScript.parentElement; | |
| const data = [null,null]; | |
| Promise.all([ | |
| import("/docs/transformers/pr_33913/ja/_app/immutable/entry/start.17a8f5f1.js"), | |
| import("/docs/transformers/pr_33913/ja/_app/immutable/entry/app.ec1e8c3e.js") | |
| ]).then(([kit, app]) => { | |
| kit.start(app, element, { | |
| node_ids: [0, 133], | |
| data, | |
| form: null, | |
| error: null | |
| }); | |
| }); | |
| } | |
| </script> | |
Xet Storage Details
- Size:
- 44.6 kB
- Xet hash:
- f200ca0c7bd5e8fa12b9f5e65c57614dbd9f52da14ee796f9076da3304bff079
·
Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.