Hugging Face's logo

Buckets:
hf-doc-build
/
doc

Files
xet
hf-doc-build/doc / diffusers /v0.43.0 /ru /tutorials /basic_training.html
mishig's picture
mishig
download
raw
77.3 kB
<meta charset="utf-8" /><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;Обучение диффузионной модели&quot;,&quot;local&quot;:&quot;train-a-diffusion-model&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;Конфигурация обучения&quot;,&quot;local&quot;:&quot;training-configuration&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Загрузите набор данных&quot;,&quot;local&quot;:&quot;load-the-dataset&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Создание UNet2DModel&quot;,&quot;local&quot;:&quot;create-a-unet2dmodel&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Создание планировщика&quot;,&quot;local&quot;:&quot;create-a-scheduler&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Обучение модели&quot;,&quot;local&quot;:&quot;train-the-model&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Дальнейшие шаги&quot;,&quot;local&quot;:&quot;next-steps&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2}],&quot;depth&quot;:1}"/>
<link href="/docs/diffusers/v0.43.0/en/_app/immutable/entry/start.1gaXe03k.js" rel="modulepreload">
<link href="/docs/diffusers/v0.43.0/en/_app/immutable/chunks/BObs6oQO.js" rel="modulepreload">
<link href="/docs/diffusers/v0.43.0/en/_app/immutable/chunks/DPnyVmXs.js" rel="modulepreload">
<link href="/docs/diffusers/v0.43.0/en/_app/immutable/entry/app.BwdYRbCn.js" rel="modulepreload">
<link href="/docs/diffusers/v0.43.0/en/_app/immutable/chunks/DSGUT_OW.js" rel="modulepreload">
<link href="/docs/diffusers/v0.43.0/en/_app/immutable/chunks/C045MWWx.js" rel="modulepreload">
<link href="/docs/diffusers/v0.43.0/en/_app/immutable/chunks/6tuJ3nyi.js" rel="modulepreload">
<link href="/docs/diffusers/v0.43.0/en/_app/immutable/chunks/DsnmJJEf.js" rel="modulepreload">
<link href="/docs/diffusers/v0.43.0/en/_app/immutable/nodes/0.CornNeQR.js" rel="modulepreload">
<link href="/docs/diffusers/v0.43.0/en/_app/immutable/chunks/IaDvMxLQ.js" rel="modulepreload">
<link href="/docs/diffusers/v0.43.0/en/_app/immutable/nodes/318.DclWbDd-.js" rel="modulepreload">
<link href="/docs/diffusers/v0.43.0/en/_app/immutable/chunks/bKdwVYpU.js" rel="modulepreload">
<!--hfx23e--><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;Train a diffusion model&quot;,&quot;local&quot;:&quot;train-a-diffusion-model&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;Training configuration&quot;,&quot;local&quot;:&quot;training-configuration&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Load the dataset&quot;,&quot;local&quot;:&quot;load-the-dataset&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Create a UNet2DModel&quot;,&quot;local&quot;:&quot;create-a-unet2dmodel&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Create a scheduler&quot;,&quot;local&quot;:&quot;create-a-scheduler&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Train the model&quot;,&quot;local&quot;:&quot;train-the-model&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Next steps&quot;,&quot;local&quot;:&quot;next-steps&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2}],&quot;depth&quot;:1}"/><!---->
<link href="/docs/diffusers/v0.43.0/en/_app/immutable/assets/0.tn0RQdqM.css" rel="modulepreload"> <!--[--><!--[0--><!--[--><!--[0--><!--[--><p></p> <div class="items-center shrink-0 min-w-[100px] max-sm:min-w-[50px] justify-end ml-auto flex" style="float: inline-end; margin-inline-start: 10px; display: inline-flex; position: relative; z-index: 10;"><div dir="ltr" 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 dir="auto">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> <!--[-1--><!--]--></div><!----> <div class="flex space-x-1 " style="float: inline-end; margin-inline-start: 10px; display: inline-flex; position: relative; z-index: 10;" dir="ltr"><!----> <!--[1--><div class="relative colab-dropdown "><button class=" " type="button"><!--[0--><!--[-1--><img alt="Open In Colab" class="!m-0" src="https://colab.research.google.com/assets/colab-badge.svg"/><!--]--><!----><!--]--></button> <!--[-1--><!--]--></div><!--]--> <!--[1--><div class="relative colab-dropdown "><button class=" " type="button"><!--[0--><!--[-1--><img alt="Open In Studio Lab" class="!m-0" src="https://studiolab.sagemaker.aws/studiolab.svg"/><!--]--><!----><!--]--></button> <!--[-1--><!--]--></div><!--]--></div><!----> <!--[0--><h1 class="relative group"><a id="train-a-diffusion-model" 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-a-diffusion-model"><span><svg 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><!---->Обучение диффузионной модели<!----></span></h1><!--]--><!----> <p>Безусловная генерация изображений — популярное применение диффузионных моделей, которое создаёт изображения, похожие на те, что использовались в датасете для обучения. Как правило, наилучшие результаты достигаются при дообучении предобученной модели на конкретном датасете. Многие такие чекпоинты можно найти на <a href="https://huggingface.co/search/full-text?q=unconditional-image-generation&amp;type=model" rel="nofollow">Hub</a>, но если вы не найдёте подходящий, всегда можно обучить собственную модель!</p> <p>В этом учебнике вы узнаете, как обучить <a href="/docs/diffusers/v0.43.0/ru/api/models/unet2d#diffusers.UNet2DModel">UNet2DModel</a> с нуля на подмножестве набора данных <a href="https://huggingface.co/datasets/huggan/smithsonian_butterflies_subset" rel="nofollow">Smithsonian Butterflies</a>, чтобы генерировать собственных 🦋 бабочек 🦋.</p> <blockquote class="tip"><p>💡 Это учебное пособие по обучению основано на ноутбуке <a href="https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/training_example.ipynb" rel="nofollow">Обучение с 🧨 Diffusers</a>. Дополнительные детали и контекст о диффузионных моделях, например, о том, как они работают, можно найти в ноутбуке!</p></blockquote> <p>Прежде чем начать, убедитесь, что у вас установлены 🤗 Datasets для загрузки и предобработки наборов данных изображений, а также 🤗 Accelerate для упрощения обучения на любом количестве GPU. Следующая команда также установит <a href="https://www.tensorflow.org/tensorboard" rel="nofollow">TensorBoard</a> для визуализации метрик обучения (вы также можете использовать <a href="https://docs.wandb.ai/" rel="nofollow">Weights &amp; Biases</a> для отслеживания обучения).</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 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> Скопировано</div><!----></button><!----></div> <pre class="language-py "><!----><span class="hljs-comment"># uncomment to install the necessary libraries in Colab</span>
<span class="hljs-comment">#!pip install diffusers[training]</span><!----></pre></div><!----> <p>Мы рекомендуем делиться вашей моделью с сообществом. Для этого необходимо войти в свой аккаунт Hugging Face (создайте его <a href="https://hf.co/join" rel="nofollow">здесь</a>, если у вас его ещё нет!). Вы можете войти из notebook и ввести свой токен, когда система попросит. Убедитесь, что у вашего токена есть роль write.</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 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> Скопировано</div><!----></button><!----></div> <pre class="language-py "><!----><span class="hljs-meta">&gt;&gt;&gt; </span><span class="hljs-keyword">from</span> huggingface_hub <span class="hljs-keyword">import</span> notebook_login
<span class="hljs-meta">&gt;&gt;&gt; </span>notebook_login()<!----></pre></div><!----> <p>Или войдите в систему из терминала:</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 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> Скопировано</div><!----></button><!----></div> <pre class="language-bash "><!---->hf auth login<!----></pre></div><!----> <p>Поскольку контрольные точки моделей довольно большие, установите <a href="https://git-lfs.com/" rel="nofollow">Git-LFS</a> для версионирования этих крупных файлов:</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 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> Скопировано</div><!----></button><!----></div> <pre class="language-bash "><!---->!<span class="hljs-built_in">sudo</span> apt -qq install git-lfs
!git config --global credential.helper store<!----></pre></div><!----> <!--[1--><h2 class="relative group"><a id="training-configuration" 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-configuration"><span><svg 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><!---->Конфигурация обучения<!----></span></h2><!--]--><!----> <p>Для удобства создайте класс <code>TrainingConfig</code>, содержащий гиперпараметры обучения (при необходимости их можно изменить):</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 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> Скопировано</div><!----></button><!----></div> <pre class="language-py "><!----><span class="hljs-meta">&gt;&gt;&gt; </span><span class="hljs-keyword">from</span> dataclasses <span class="hljs-keyword">import</span> dataclass
<span class="hljs-meta">&gt;&gt;&gt; </span>@dataclass
<span class="hljs-meta">... </span><span class="hljs-keyword">class</span> <span class="hljs-title class_">TrainingConfig</span>:
<span class="hljs-meta">... </span> image_size = <span class="hljs-number">128</span> <span class="hljs-comment"># the generated image resolution</span>
<span class="hljs-meta">... </span> train_batch_size = <span class="hljs-number">16</span>
<span class="hljs-meta">... </span> eval_batch_size = <span class="hljs-number">16</span> <span class="hljs-comment"># how many images to sample during evaluation</span>
<span class="hljs-meta">... </span> num_epochs = <span class="hljs-number">50</span>
<span class="hljs-meta">... </span> gradient_accumulation_steps = <span class="hljs-number">1</span>
<span class="hljs-meta">... </span> learning_rate = <span class="hljs-number">1e-4</span>
<span class="hljs-meta">... </span> lr_warmup_steps = <span class="hljs-number">500</span>
<span class="hljs-meta">... </span> save_image_epochs = <span class="hljs-number">10</span>
<span class="hljs-meta">... </span> save_model_epochs = <span class="hljs-number">30</span>
<span class="hljs-meta">... </span> mixed_precision = <span class="hljs-string">&quot;fp16&quot;</span> <span class="hljs-comment"># `no` for float32, `fp16` for automatic mixed precision</span>
<span class="hljs-meta">... </span> output_dir = <span class="hljs-string">&quot;ddpm-butterflies-128&quot;</span> <span class="hljs-comment"># the model name locally and on the HF Hub</span>
<span class="hljs-meta">... </span> push_to_hub = <span class="hljs-literal">True</span> <span class="hljs-comment"># whether to upload the saved model to the HF Hub</span>
<span class="hljs-meta">... </span> hub_model_id = <span class="hljs-string">&quot;&lt;your-username&gt;/&lt;my-awesome-model&gt;&quot;</span> <span class="hljs-comment"># the name of the repository to create on the HF Hub</span>
<span class="hljs-meta">... </span> hub_private_repo = <span class="hljs-literal">None</span>
<span class="hljs-meta">... </span> overwrite_output_dir = <span class="hljs-literal">True</span> <span class="hljs-comment"># overwrite the old model when re-running the notebook</span>
<span class="hljs-meta">... </span> seed = <span class="hljs-number">0</span>
<span class="hljs-meta">&gt;&gt;&gt; </span>config = TrainingConfig()<!----></pre></div><!----> <!--[1--><h2 class="relative group"><a id="load-the-dataset" 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="#load-the-dataset"><span><svg 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><!---->Загрузите набор данных<!----></span></h2><!--]--><!----> <p>Вы можете легко загрузить набор данных <a href="https://huggingface.co/datasets/huggan/smithsonian_butterflies_subset" rel="nofollow">Smithsonian Butterflies</a> с помощью библиотеки 🤗 Datasets:</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 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> Скопировано</div><!----></button><!----></div> <pre class="language-py "><!----><span class="hljs-meta">&gt;&gt;&gt; </span><span class="hljs-keyword">from</span> datasets <span class="hljs-keyword">import</span> load_dataset
<span class="hljs-meta">&gt;&gt;&gt; </span>config.dataset_name = <span class="hljs-string">&quot;huggan/smithsonian_butterflies_subset&quot;</span>
<span class="hljs-meta">&gt;&gt;&gt; </span>dataset = load_dataset(config.dataset_name, split=<span class="hljs-string">&quot;train&quot;</span>)<!----></pre></div><!----> <blockquote class="tip"><p>💡 Дополнительные наборы данных можно найти в рамках <a href="https://huggingface.co/huggan" rel="nofollow">HugGan Community Event</a> или использовать собственный набор данных, создав локальный <a href="https://huggingface.co/docs/datasets/image_dataset#imagefolder" rel="nofollow"><code>ImageFolder</code></a>. Установите <code>config.dataset_name</code> в идентификатор репозитория набора данных, если он взят из HugGan Community Event, или <code>imagefolder</code>, если вы используете собственные изображения.</p></blockquote> <p>🤗 Datasets использует функцию <a href="https://huggingface.co/docs/datasets/v5.2.0/en/package_reference/main_classes#datasets.Image" rel="nofollow">Image</a> для автоматического декодирования данных изображения и загрузки его в виде <a href="https://pillow.readthedocs.io/en/stable/reference/Image.html" rel="nofollow"><code>PIL.Image</code></a>, что позволяет визуализировать его:</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 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> Скопировано</div><!----></button><!----></div> <pre class="language-py "><!----><span class="hljs-meta">&gt;&gt;&gt; </span><span class="hljs-keyword">import</span> matplotlib.pyplot <span class="hljs-keyword">as</span> plt
<span class="hljs-meta">&gt;&gt;&gt; </span>fig, axs = plt.subplots(<span class="hljs-number">1</span>, <span class="hljs-number">4</span>, figsize=(<span class="hljs-number">16</span>, <span class="hljs-number">4</span>))
<span class="hljs-meta">&gt;&gt;&gt; </span><span class="hljs-keyword">for</span> i, image <span class="hljs-keyword">in</span> <span class="hljs-built_in">enumerate</span>(dataset[:<span class="hljs-number">4</span>][<span class="hljs-string">&quot;image&quot;</span>]):
<span class="hljs-meta">... </span> axs[i].imshow(image)
<span class="hljs-meta">... </span> axs[i].set_axis_off()
<span class="hljs-meta">&gt;&gt;&gt; </span>fig.show()<!----></pre></div><!----> <div class="flex justify-center"><img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/butterflies_ds.png"/></div> <p>Однако все изображения имеют разные размеры, поэтому сначала необходимо выполнить их предобработку:</p> <ul><li><code>Resize</code> изменяет размер изображения до значения, заданного в <code>config.image_size</code>.</li> <li><code>RandomHorizontalFlip</code> дополняет набор данных, случайно отражая изображения по горизонтали.</li> <li><code>Normalize</code> важно для масштабирования значений пикселей в диапазон [-1, 1], который ожидает модель.</li></ul> <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 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> Скопировано</div><!----></button><!----></div> <pre class="language-py "><!----><span class="hljs-meta">&gt;&gt;&gt; </span><span class="hljs-keyword">from</span> torchvision <span class="hljs-keyword">import</span> transforms
<span class="hljs-meta">&gt;&gt;&gt; </span>preprocess = transforms.Compose(
<span class="hljs-meta">... </span> [
<span class="hljs-meta">... </span> transforms.Resize((config.image_size, config.image_size)),
<span class="hljs-meta">... </span> transforms.RandomHorizontalFlip(),
<span class="hljs-meta">... </span> transforms.ToTensor(),
<span class="hljs-meta">... </span> transforms.Normalize([<span class="hljs-number">0.5</span>], [<span class="hljs-number">0.5</span>]),
<span class="hljs-meta">... </span> ]
<span class="hljs-meta">... </span>)<!----></pre></div><!----> <p>Используйте метод <a href="https://huggingface.co/docs/datasets/v5.2.0/en/package_reference/main_classes#datasets.Dataset.set_transform" rel="nofollow">set_transform</a> библиотеки 🤗 Datasets, чтобы применять функцию <code>preprocess</code> на лету во время обучения:</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 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> Скопировано</div><!----></button><!----></div> <pre class="language-py "><!----><span class="hljs-meta">&gt;&gt;&gt; </span><span class="hljs-keyword">def</span> <span class="hljs-title function_">transform</span>(<span class="hljs-params">examples</span>):
<span class="hljs-meta">... </span> images = [preprocess(image.convert(<span class="hljs-string">&quot;RGB&quot;</span>)) <span class="hljs-keyword">for</span> image <span class="hljs-keyword">in</span> examples[<span class="hljs-string">&quot;image&quot;</span>]]
<span class="hljs-meta">... </span> <span class="hljs-keyword">return</span> {<span class="hljs-string">&quot;images&quot;</span>: images}
<span class="hljs-meta">&gt;&gt;&gt; </span>dataset.set_transform(transform)<!----></pre></div><!----> <p>Вы можете снова визуализировать изображения, чтобы убедиться, что они были изменены в размере. Теперь вы готовы обернуть набор данных в <a href="https://pytorch.org/docs/stable/data#torch.utils.data.DataLoader" rel="nofollow">DataLoader</a> для обучения!</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 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> Скопировано</div><!----></button><!----></div> <pre class="language-py "><!----><span class="hljs-meta">&gt;&gt;&gt; </span><span class="hljs-keyword">import</span> torch
<span class="hljs-meta">&gt;&gt;&gt; </span>train_dataloader = torch.utils.data.DataLoader(dataset, batch_size=config.train_batch_size, shuffle=<span class="hljs-literal">True</span>)<!----></pre></div><!----> <!--[1--><h2 class="relative group"><a id="create-a-unet2dmodel" 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="#create-a-unet2dmodel"><span><svg 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><!---->Создание UNet2DModel<!----></span></h2><!--]--><!----> <p>Предобученные модели в 🧨 Diffusers легко создаются из их класса модели с нужными вам параметрами. Например, чтобы создать <a href="/docs/diffusers/v0.43.0/ru/api/models/unet2d#diffusers.UNet2DModel">UNet2DModel</a>:</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 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> Скопировано</div><!----></button><!----></div> <pre class="language-py "><!----><span class="hljs-meta">&gt;&gt;&gt; </span><span class="hljs-keyword">from</span> diffusers <span class="hljs-keyword">import</span> UNet2DModel
<span class="hljs-meta">&gt;&gt;&gt; </span>model = UNet2DModel(
<span class="hljs-meta">... </span> sample_size=config.image_size, <span class="hljs-comment"># the target image resolution</span>
<span class="hljs-meta">... </span> in_channels=<span class="hljs-number">3</span>, <span class="hljs-comment"># the number of input channels, 3 for RGB images</span>
<span class="hljs-meta">... </span> out_channels=<span class="hljs-number">3</span>, <span class="hljs-comment"># the number of output channels</span>
<span class="hljs-meta">... </span> layers_per_block=<span class="hljs-number">2</span>, <span class="hljs-comment"># how many ResNet layers to use per UNet block</span>
<span class="hljs-meta">... </span> block_out_channels=(<span class="hljs-number">128</span>, <span class="hljs-number">128</span>, <span class="hljs-number">256</span>, <span class="hljs-number">256</span>, <span class="hljs-number">512</span>, <span class="hljs-number">512</span>), <span class="hljs-comment"># the number of output channels for each UNet block</span>
<span class="hljs-meta">... </span> down_block_types=(
<span class="hljs-meta">... </span> <span class="hljs-string">&quot;DownBlock2D&quot;</span>, <span class="hljs-comment"># a regular ResNet downsampling block</span>
<span class="hljs-meta">... </span> <span class="hljs-string">&quot;DownBlock2D&quot;</span>,
<span class="hljs-meta">... </span> <span class="hljs-string">&quot;DownBlock2D&quot;</span>,
<span class="hljs-meta">... </span> <span class="hljs-string">&quot;DownBlock2D&quot;</span>,
<span class="hljs-meta">... </span> <span class="hljs-string">&quot;AttnDownBlock2D&quot;</span>, <span class="hljs-comment"># a ResNet downsampling block with spatial self-attention</span>
<span class="hljs-meta">... </span> <span class="hljs-string">&quot;DownBlock2D&quot;</span>,
<span class="hljs-meta">... </span> ),
<span class="hljs-meta">... </span> up_block_types=(
<span class="hljs-meta">... </span> <span class="hljs-string">&quot;UpBlock2D&quot;</span>, <span class="hljs-comment"># a regular ResNet upsampling block</span>
<span class="hljs-meta">... </span> <span class="hljs-string">&quot;AttnUpBlock2D&quot;</span>, <span class="hljs-comment"># a ResNet upsampling block with spatial self-attention</span>
<span class="hljs-meta">... </span> <span class="hljs-string">&quot;UpBlock2D&quot;</span>,
<span class="hljs-meta">... </span> <span class="hljs-string">&quot;UpBlock2D&quot;</span>,
<span class="hljs-meta">... </span> <span class="hljs-string">&quot;UpBlock2D&quot;</span>,
<span class="hljs-meta">... </span> <span class="hljs-string">&quot;UpBlock2D&quot;</span>,
<span class="hljs-meta">... </span> ),
<span class="hljs-meta">... </span>)<!----></pre></div><!----> <p>Часто бывает хорошей идеей быстро проверить, что форма образцов совпадает с формой вывода модели:</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 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> Скопировано</div><!----></button><!----></div> <pre class="language-py "><!----><span class="hljs-meta">&gt;&gt;&gt; </span>sample_image = dataset[<span class="hljs-number">0</span>][<span class="hljs-string">&quot;images&quot;</span>].unsqueeze(<span class="hljs-number">0</span>)
<span class="hljs-meta">&gt;&gt;&gt; </span><span class="hljs-built_in">print</span>(<span class="hljs-string">&quot;Input shape:&quot;</span>, sample_image.shape)
Input shape: torch.Size([<span class="hljs-number">1</span>, <span class="hljs-number">3</span>, <span class="hljs-number">128</span>, <span class="hljs-number">128</span>])
<span class="hljs-meta">&gt;&gt;&gt; </span><span class="hljs-built_in">print</span>(<span class="hljs-string">&quot;Output shape:&quot;</span>, model(sample_image, timestep=<span class="hljs-number">0</span>).sample.shape)
Output shape: torch.Size([<span class="hljs-number">1</span>, <span class="hljs-number">3</span>, <span class="hljs-number">128</span>, <span class="hljs-number">128</span>])<!----></pre></div><!----> <p>Отлично! Далее вам понадобится планировщик, чтобы добавить шум к изображению.</p> <!--[1--><h2 class="relative group"><a id="create-a-scheduler" 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="#create-a-scheduler"><span><svg 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><!---->Создание планировщика<!----></span></h2><!--]--><!----> <p>Поведение планировщика зависит от того, используется ли модель для обучения или инференса. Во время инференса планировщик генерирует изображение из шума. Во время обучения планировщик принимает выход модели — или образец — из конкретной точки процесса диффузии и добавляет шум к изображению в соответствии с <em>расписанием шума</em> и <em>правилом обновления</em>.</p> <p>Рассмотрим <a href="/docs/diffusers/v0.43.0/ru/api/schedulers/ddpm#diffusers.DDPMScheduler">DDPMScheduler</a> и воспользуемся методом <code>add_noise</code>, чтобы добавить случайный шум к изображению <code>sample_image</code>, полученному ранее:</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 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> Скопировано</div><!----></button><!----></div> <pre class="language-py "><!----><span class="hljs-meta">&gt;&gt;&gt; </span><span class="hljs-keyword">import</span> torch
<span class="hljs-meta">&gt;&gt;&gt; </span><span class="hljs-keyword">from</span> PIL <span class="hljs-keyword">import</span> Image
<span class="hljs-meta">&gt;&gt;&gt; </span><span class="hljs-keyword">from</span> diffusers <span class="hljs-keyword">import</span> DDPMScheduler
<span class="hljs-meta">&gt;&gt;&gt; </span>noise_scheduler = DDPMScheduler(num_train_timesteps=<span class="hljs-number">1000</span>)
<span class="hljs-meta">&gt;&gt;&gt; </span>noise = torch.randn(sample_image.shape)
<span class="hljs-meta">&gt;&gt;&gt; </span>timesteps = torch.LongTensor([<span class="hljs-number">50</span>])
<span class="hljs-meta">&gt;&gt;&gt; </span>noisy_image = noise_scheduler.add_noise(sample_image, noise, timesteps)
<span class="hljs-meta">&gt;&gt;&gt; </span>Image.fromarray(((noisy_image.permute(<span class="hljs-number">0</span>, <span class="hljs-number">2</span>, <span class="hljs-number">3</span>, <span class="hljs-number">1</span>) + <span class="hljs-number">1.0</span>) * <span class="hljs-number">127.5</span>).<span class="hljs-built_in">type</span>(torch.uint8).numpy()[<span class="hljs-number">0</span>])<!----></pre></div><!----> <div class="flex justify-center"><img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/noisy_butterfly.png"/></div> <p>Целью обучения модели является предсказание шума, добавленного к изображению. Потери на этом шаге можно вычислить по формуле:</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 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> Скопировано</div><!----></button><!----></div> <pre class="language-py "><!----><span class="hljs-meta">&gt;&gt;&gt; </span><span class="hljs-keyword">import</span> torch.nn.functional <span class="hljs-keyword">as</span> F
<span class="hljs-meta">&gt;&gt;&gt; </span>noise_pred = model(noisy_image, timesteps).sample
<span class="hljs-meta">&gt;&gt;&gt; </span>loss = F.mse_loss(noise_pred, noise)<!----></pre></div><!----> <!--[1--><h2 class="relative group"><a id="train-the-model" 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-the-model"><span><svg 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><!---->Обучение модели<!----></span></h2><!--]--><!----> <p>К этому моменту у вас есть все необходимые компоненты для начала обучения модели, и осталось лишь собрать всё воедино.</p> <p>Сначала вам понадобится оптимизатор и планировщик скорости обучения:</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 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> Скопировано</div><!----></button><!----></div> <pre class="language-py "><!----><span class="hljs-meta">&gt;&gt;&gt; </span><span class="hljs-keyword">from</span> diffusers.optimization <span class="hljs-keyword">import</span> get_cosine_schedule_with_warmup
<span class="hljs-meta">&gt;&gt;&gt; </span>optimizer = torch.optim.AdamW(model.parameters(), lr=config.learning_rate)
<span class="hljs-meta">&gt;&gt;&gt; </span>lr_scheduler = get_cosine_schedule_with_warmup(
<span class="hljs-meta">... </span> optimizer=optimizer,
<span class="hljs-meta">... </span> num_warmup_steps=config.lr_warmup_steps,
<span class="hljs-meta">... </span> num_training_steps=(<span class="hljs-built_in">len</span>(train_dataloader) * config.num_epochs),
<span class="hljs-meta">... </span>)<!----></pre></div><!----> <p>Затем вам понадобится способ оценить модель. Для оценки можно использовать <a href="/docs/diffusers/v0.43.0/ru/api/pipelines/ddpm#diffusers.DDPMPipeline">DDPMPipeline</a>, чтобы сгенерировать пакет примеров изображений и сохранить его в виде сетки:</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 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> Скопировано</div><!----></button><!----></div> <pre class="language-py "><!----><span class="hljs-meta">&gt;&gt;&gt; </span><span class="hljs-keyword">from</span> diffusers <span class="hljs-keyword">import</span> DDPMPipeline
<span class="hljs-meta">&gt;&gt;&gt; </span><span class="hljs-keyword">from</span> diffusers.utils <span class="hljs-keyword">import</span> make_image_grid
<span class="hljs-meta">&gt;&gt;&gt; </span><span class="hljs-keyword">import</span> os
<span class="hljs-meta">&gt;&gt;&gt; </span><span class="hljs-keyword">def</span> <span class="hljs-title function_">evaluate</span>(<span class="hljs-params">config, epoch, pipeline</span>):
<span class="hljs-meta">... </span> <span class="hljs-comment"># Sample some images from random noise (this is the backward diffusion process).</span>
<span class="hljs-meta">... </span> <span class="hljs-comment"># The default pipeline output type is `List[PIL.Image]`</span>
<span class="hljs-meta">... </span> images = pipeline(
<span class="hljs-meta">... </span> batch_size=config.eval_batch_size,
<span class="hljs-meta">... </span> generator=torch.Generator(device=<span class="hljs-string">&#x27;cpu&#x27;</span>).manual_seed(config.seed), <span class="hljs-comment"># Use a separate torch generator to avoid rewinding the random state of the main training loop</span>
<span class="hljs-meta">... </span> ).images
<span class="hljs-meta">... </span> <span class="hljs-comment"># Make a grid out of the images</span>
<span class="hljs-meta">... </span> image_grid = make_image_grid(images, rows=<span class="hljs-number">4</span>, cols=<span class="hljs-number">4</span>)
<span class="hljs-meta">... </span> <span class="hljs-comment"># Save the images</span>
<span class="hljs-meta">... </span> test_dir = os.path.join(config.output_dir, <span class="hljs-string">&quot;samples&quot;</span>)
<span class="hljs-meta">... </span> os.makedirs(test_dir, exist_ok=<span class="hljs-literal">True</span>)
<span class="hljs-meta">... </span> image_grid.save(<span class="hljs-string">f&quot;<span class="hljs-subst">{test_dir}</span>/<span class="hljs-subst">{epoch:04d}</span>.png&quot;</span>)<!----></pre></div><!----> <p>Теперь вы можете объединить все эти компоненты в цикл обучения с помощью 🤗 Accelerate для простого логирования в TensorBoard, накопления градиентов и обучения с смешанной точностью. Чтобы загрузить модель в Hub, напишите функцию для получения имени вашего репозитория и информации о нём, а затем отправьте её в Hub.</p> <blockquote class="tip"><p>💡 Цикл обучения ниже может показаться пугающим и длинным, но позже это окупится, когда вы запустите обучение всего одной строкой кода! Если вы не можете дождаться и хотите начать генерировать изображения, смело копируйте и запускайте код ниже. Вы всегда можете вернуться и более внимательно изучить цикл обучения позже, например, пока ждёте завершения обучения вашей модели. 🤗</p></blockquote> <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 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> Скопировано</div><!----></button><!----></div> <pre class="language-py "><!----><span class="hljs-meta">&gt;&gt;&gt; </span><span class="hljs-keyword">from</span> accelerate <span class="hljs-keyword">import</span> Accelerator
<span class="hljs-meta">&gt;&gt;&gt; </span><span class="hljs-keyword">from</span> huggingface_hub <span class="hljs-keyword">import</span> create_repo, upload_folder
<span class="hljs-meta">&gt;&gt;&gt; </span><span class="hljs-keyword">from</span> tqdm.auto <span class="hljs-keyword">import</span> tqdm
<span class="hljs-meta">&gt;&gt;&gt; </span><span class="hljs-keyword">from</span> pathlib <span class="hljs-keyword">import</span> Path
<span class="hljs-meta">&gt;&gt;&gt; </span><span class="hljs-keyword">import</span> os
<span class="hljs-meta">&gt;&gt;&gt; </span><span class="hljs-keyword">def</span> <span class="hljs-title function_">train_loop</span>(<span class="hljs-params">config, model, noise_scheduler, optimizer, train_dataloader, lr_scheduler</span>):
<span class="hljs-meta">... </span> <span class="hljs-comment"># Initialize accelerator and tensorboard logging</span>
<span class="hljs-meta">... </span> accelerator = Accelerator(
<span class="hljs-meta">... </span> mixed_precision=config.mixed_precision,
<span class="hljs-meta">... </span> gradient_accumulation_steps=config.gradient_accumulation_steps,
<span class="hljs-meta">... </span> log_with=<span class="hljs-string">&quot;tensorboard&quot;</span>,
<span class="hljs-meta">... </span> project_dir=os.path.join(config.output_dir, <span class="hljs-string">&quot;logs&quot;</span>),
<span class="hljs-meta">... </span> )
<span class="hljs-meta">... </span> <span class="hljs-keyword">if</span> accelerator.is_main_process:
<span class="hljs-meta">... </span> <span class="hljs-keyword">if</span> config.output_dir <span class="hljs-keyword">is</span> <span class="hljs-keyword">not</span> <span class="hljs-literal">None</span>:
<span class="hljs-meta">... </span> os.makedirs(config.output_dir, exist_ok=<span class="hljs-literal">True</span>)
<span class="hljs-meta">... </span> <span class="hljs-keyword">if</span> config.push_to_hub:
<span class="hljs-meta">... </span> repo_id = create_repo(
<span class="hljs-meta">... </span> repo_id=config.hub_model_id <span class="hljs-keyword">or</span> Path(config.output_dir).name, exist_ok=<span class="hljs-literal">True</span>
<span class="hljs-meta">... </span> ).repo_id
<span class="hljs-meta">... </span> accelerator.init_trackers(<span class="hljs-string">&quot;train_example&quot;</span>)
<span class="hljs-meta">... </span> <span class="hljs-comment"># Prepare everything</span>
<span class="hljs-meta">... </span> <span class="hljs-comment"># There is no specific order to remember, you just need to unpack the</span>
<span class="hljs-meta">... </span> <span class="hljs-comment"># objects in the same order you gave them to the prepare method.</span>
<span class="hljs-meta">... </span> model, optimizer, train_dataloader, lr_scheduler = accelerator.prepare(
<span class="hljs-meta">... </span> model, optimizer, train_dataloader, lr_scheduler
<span class="hljs-meta">... </span> )
<span class="hljs-meta">... </span> global_step = <span class="hljs-number">0</span>
<span class="hljs-meta">... </span> <span class="hljs-comment"># Now you train the model</span>
<span class="hljs-meta">... </span> <span class="hljs-keyword">for</span> epoch <span class="hljs-keyword">in</span> <span class="hljs-built_in">range</span>(config.num_epochs):
<span class="hljs-meta">... </span> progress_bar = tqdm(total=<span class="hljs-built_in">len</span>(train_dataloader), disable=<span class="hljs-keyword">not</span> accelerator.is_local_main_process)
<span class="hljs-meta">... </span> progress_bar.set_description(<span class="hljs-string">f&quot;Epoch <span class="hljs-subst">{epoch}</span>&quot;</span>)
<span class="hljs-meta">... </span> <span class="hljs-keyword">for</span> step, batch <span class="hljs-keyword">in</span> <span class="hljs-built_in">enumerate</span>(train_dataloader):
<span class="hljs-meta">... </span> clean_images = batch[<span class="hljs-string">&quot;images&quot;</span>]
<span class="hljs-meta">... </span> <span class="hljs-comment"># Sample noise to add to the images</span>
<span class="hljs-meta">... </span> noise = torch.randn(clean_images.shape, device=clean_images.device)
<span class="hljs-meta">... </span> bs = clean_images.shape[<span class="hljs-number">0</span>]
<span class="hljs-meta">... </span> <span class="hljs-comment"># Sample a random timestep for each image</span>
<span class="hljs-meta">... </span> timesteps = torch.randint(
<span class="hljs-meta">... </span> <span class="hljs-number">0</span>, noise_scheduler.config.num_train_timesteps, (bs,), device=clean_images.device,
<span class="hljs-meta">... </span> dtype=torch.int64
<span class="hljs-meta">... </span> )
<span class="hljs-meta">... </span> <span class="hljs-comment"># Add noise to the clean images according to the noise magnitude at each timestep</span>
<span class="hljs-meta">... </span> <span class="hljs-comment"># (this is the forward diffusion process)</span>
<span class="hljs-meta">... </span> noisy_images = noise_scheduler.add_noise(clean_images, noise, timesteps)
<span class="hljs-meta">... </span> <span class="hljs-keyword">with</span> accelerator.accumulate(model):
<span class="hljs-meta">... </span> <span class="hljs-comment"># Predict the noise residual</span>
<span class="hljs-meta">... </span> noise_pred = model(noisy_images, timesteps, return_dict=<span class="hljs-literal">False</span>)[<span class="hljs-number">0</span>]
<span class="hljs-meta">... </span> loss = F.mse_loss(noise_pred, noise)
<span class="hljs-meta">... </span> accelerator.backward(loss)
<span class="hljs-meta">... </span> <span class="hljs-keyword">if</span> accelerator.sync_gradients:
<span class="hljs-meta">... </span> accelerator.clip_grad_norm_(model.parameters(), <span class="hljs-number">1.0</span>)
<span class="hljs-meta">... </span> optimizer.step()
<span class="hljs-meta">... </span> lr_scheduler.step()
<span class="hljs-meta">... </span> optimizer.zero_grad()
<span class="hljs-meta">... </span> progress_bar.update(<span class="hljs-number">1</span>)
<span class="hljs-meta">... </span> logs = {<span class="hljs-string">&quot;loss&quot;</span>: loss.detach().item(), <span class="hljs-string">&quot;lr&quot;</span>: lr_scheduler.get_last_lr()[<span class="hljs-number">0</span>], <span class="hljs-string">&quot;step&quot;</span>: global_step}
<span class="hljs-meta">... </span> progress_bar.set_postfix(**logs)
<span class="hljs-meta">... </span> accelerator.log(logs, step=global_step)
<span class="hljs-meta">... </span> global_step += <span class="hljs-number">1</span>
<span class="hljs-meta">... </span> <span class="hljs-comment"># After each epoch you optionally sample some demo images with evaluate() and save the model</span>
<span class="hljs-meta">... </span> <span class="hljs-keyword">if</span> accelerator.is_main_process:
<span class="hljs-meta">... </span> pipeline = DDPMPipeline(unet=accelerator.unwrap_model(model), scheduler=noise_scheduler)
<span class="hljs-meta">... </span> <span class="hljs-keyword">if</span> (epoch + <span class="hljs-number">1</span>) % config.save_image_epochs == <span class="hljs-number">0</span> <span class="hljs-keyword">or</span> epoch == config.num_epochs - <span class="hljs-number">1</span>:
<span class="hljs-meta">... </span> evaluate(config, epoch, pipeline)
<span class="hljs-meta">... </span> <span class="hljs-keyword">if</span> (epoch + <span class="hljs-number">1</span>) % config.save_model_epochs == <span class="hljs-number">0</span> <span class="hljs-keyword">or</span> epoch == config.num_epochs - <span class="hljs-number">1</span>:
<span class="hljs-meta">... </span> <span class="hljs-keyword">if</span> config.push_to_hub:
<span class="hljs-meta">... </span> upload_folder(
<span class="hljs-meta">... </span> repo_id=repo_id,
<span class="hljs-meta">... </span> folder_path=config.output_dir,
<span class="hljs-meta">... </span> commit_message=<span class="hljs-string">f&quot;Epoch <span class="hljs-subst">{epoch}</span>&quot;</span>,
<span class="hljs-meta">... </span> ignore_patterns=[<span class="hljs-string">&quot;step_*&quot;</span>, <span class="hljs-string">&quot;epoch_*&quot;</span>],
<span class="hljs-meta">... </span> )
<span class="hljs-meta">... </span> <span class="hljs-keyword">else</span>:
<span class="hljs-meta">... </span> pipeline.save_pretrained(config.output_dir)<!----></pre></div><!----> <p>Фух, это было немало кода! Но теперь вы наконец готовы запустить обучение с помощью функции <a href="https://huggingface.co/docs/accelerate/v1.15.0/en/package_reference/launchers#accelerate.notebook_launcher" rel="nofollow">notebook_launcher</a> из 🤗 Accelerate. Передайте в функцию цикл обучения, все аргументы обучения и количество процессов (это значение можно изменить на количество доступных вам GPU), которые будут использоваться для обучения:</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 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> Скопировано</div><!----></button><!----></div> <pre class="language-py "><!----><span class="hljs-meta">&gt;&gt;&gt; </span><span class="hljs-keyword">from</span> accelerate <span class="hljs-keyword">import</span> notebook_launcher
<span class="hljs-meta">&gt;&gt;&gt; </span>args = (config, model, noise_scheduler, optimizer, train_dataloader, lr_scheduler)
<span class="hljs-meta">&gt;&gt;&gt; </span>notebook_launcher(train_loop, args, num_processes=<span class="hljs-number">1</span>)<!----></pre></div><!----> <p>Когда обучение завершено, посмотрите на финальные изображения 🦋, сгенерированные вашей диффузионной моделью! 🦋</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 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> Скопировано</div><!----></button><!----></div> <pre class="language-py "><!----><span class="hljs-meta">&gt;&gt;&gt; </span><span class="hljs-keyword">import</span> glob
<span class="hljs-meta">&gt;&gt;&gt; </span>sample_images = <span class="hljs-built_in">sorted</span>(glob.glob(<span class="hljs-string">f&quot;<span class="hljs-subst">{config.output_dir}</span>/samples/*.png&quot;</span>))
<span class="hljs-meta">&gt;&gt;&gt; </span>Image.<span class="hljs-built_in">open</span>(sample_images[-<span class="hljs-number">1</span>])<!----></pre></div><!----> <div class="flex justify-center"><img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/butterflies_final.png"/></div> <!--[1--><h2 class="relative group"><a id="next-steps" 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="#next-steps"><span><svg 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><!---->Дальнейшие шаги<!----></span></h2><!--]--><!----> <p>Безусловная генерация изображений — один из примеров задач, для которых можно обучать модель. Вы можете ознакомиться с другими задачами и методами обучения на странице <a href="../training/overview">🧨 Diffusers Training Examples</a>. Вот несколько примеров того, что вы можете узнать:</p> <ul><li><a href="../training/text_inversion">Textual Inversion</a> — алгоритм, который обучает модель конкретному визуальному концепту и интегрирует его в генерируемое изображение.</li> <li><a href="../training/dreambooth">DreamBooth</a> — техника генерации персонализированных изображений объекта на основе нескольких входных изображений этого объекта.</li> <li><a href="../training/text2image">Руководство</a> по дообучению модели Stable Diffusion на собственном наборе данных.</li> <li><a href="../training/lora">Руководство</a> по использованию LoRA — эффективного с точки зрения памяти метода для более быстрого дообучения очень больших моделей.</li></ul> <a class="!text-gray-400 !no-underline text-sm flex items-center not-prose mt-4" href="https://github.com/huggingface/diffusers/blob/main/docs/source/en/tutorials/basic_training.md" 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><span class="underline">Update</span> on GitHub</span></a><!----> <p></p><!--]--><!----><!--]--><!--]--><!--]--> <!--[-1--><!--]--><!--]-->
<script>
{
__sveltekit_ywq9g6 = {
base: "/docs/diffusers/v0.43.0/en",
assets: "/docs/diffusers/v0.43.0/en"
};
const element = document.currentScript.parentElement;
Promise.all([
import("/docs/diffusers/v0.43.0/en/_app/immutable/entry/start.1gaXe03k.js"),
import("/docs/diffusers/v0.43.0/en/_app/immutable/entry/app.BwdYRbCn.js")
]).then(([kit, app]) => {
kit.start(app, element, {
node_ids: [0, 318],
data: [null,null],
form: null,
error: null
});
});
}
</script>

Xet Storage Details

Size:
77.3 kB
·
Xet hash:
f31e3d280cb793ff69e81fcac4faa69cd4afd50f1fcf4b1baa3fb23dac1c0f12

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