Buckets:

hf-doc-build
/

doc

Files
xet
hf-doc-build/doc / diffusers /v0.43.0 /pt /tutorials /basic_training.html
mishig
2 days ago
download
raw
72.7 kB
<meta charset="utf-8" /><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;Treinar um modelo de difusão&quot;,&quot;local&quot;:&quot;train-a-diffusion-model&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;Configuração de treinamento&quot;,&quot;local&quot;:&quot;training-configuration&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Carregue o conjunto de dados&quot;,&quot;local&quot;:&quot;load-the-dataset&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Crie um UNet2DModel&quot;,&quot;local&quot;:&quot;create-a-unet2dmodel&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Criar um agendador&quot;,&quot;local&quot;:&quot;create-a-scheduler&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Treinar o modelo&quot;,&quot;local&quot;:&quot;train-the-model&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Próximas etapas&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><!---->Treinar um modelo de difusão<!----></span></h1><!--]--><!----> <p>A geração de imagens incondicional é uma aplicação popular dos modelos de difusão que gera imagens semelhantes às do conjunto de dados usado para o treinamento. Normalmente, os melhores resultados são obtidos ao fazer o ajuste fino de um modelo pré-treinado em um conjunto de dados específico. Você pode encontrar muitos desses checkpoints no <a href="https://huggingface.co/search/full-text?q=unconditional-image-generation&amp;type=model" rel="nofollow">Hub</a>, mas, se não encontrar nenhum que lhe agrade, você sempre pode treinar o seu próprio!</p> <p>Este tutorial ensinará você a treinar um <a href="/docs/diffusers/v0.43.0/pt/api/models/unet2d#diffusers.UNet2DModel">UNet2DModel</a> do zero em um subconjunto do conjunto de dados <a href="https://huggingface.co/datasets/huggan/smithsonian_butterflies_subset" rel="nofollow">Smithsonian Butterflies</a> para gerar suas próprias borboletas 🦋.</p> <blockquote class="tip"><p>💡 Este tutorial de treinamento é baseado no notebook <a href="https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/training_example.ipynb" rel="nofollow">Training with 🧨 Diffusers</a>. Para mais detalhes e contexto sobre modelos de difusão, como eles funcionam, confira o notebook!</p></blockquote> <p>Antes de começar, verifique se você tem o 🤗 Datasets instalado para carregar e pré-processar conjuntos de dados de imagens, e o 🤗 Accelerate, para simplificar o treinamento em qualquer número de GPUs. O comando a seguir também instalará o <a href="https://www.tensorflow.org/tensorboard" rel="nofollow">TensorBoard</a> para visualizar as métricas de treinamento (você também pode usar o <a href="https://docs.wandb.ai/" rel="nofollow">Weights &amp; Biases</a> para acompanhar seu treinamento).</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> Copiado</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>Incentivamos você a compartilhar seu modelo com a comunidade. Para isso, será necessário fazer login na sua conta do Hugging Face (crie uma <a href="https://hf.co/join" rel="nofollow">aqui</a> caso ainda não tenha!). Você pode fazer login a partir de um notebook e inserir seu token quando solicitado. Certifique-se de que seu token possui a permissão de escrita.</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> Copiado</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>Ou faça login a partir do terminal:</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> Copiado</div><!----></button><!----></div> <pre class="language-bash "><!---->hf auth login<!----></pre></div><!----> <p>Como os checkpoints do modelo são bastante grandes, instale o <a href="https://git-lfs.com/" rel="nofollow">Git-LFS</a> para versionar esses arquivos grandes:</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> Copiado</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><!---->Configuração de treinamento<!----></span></h2><!--]--><!----> <p>Para facilitar, crie uma classe <code>TrainingConfig</code> contendo os hiperparâmetros de treinamento (sinta-se à vontade para ajustá-los):</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> Copiado</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><!---->Carregue o conjunto de dados<!----></span></h2><!--]--><!----> <p>Você pode carregar facilmente o conjunto de dados <a href="https://huggingface.co/datasets/huggan/smithsonian_butterflies_subset" rel="nofollow">Smithsonian Butterflies</a> com a biblioteca 🤗 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> Copiado</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>💡 Você pode encontrar conjuntos de dados adicionais do <a href="https://huggingface.co/huggan" rel="nofollow">HugGan Community Event</a> ou usar seu próprio conjunto de dados criando um <a href="https://huggingface.co/docs/datasets/image_dataset#imagefolder" rel="nofollow"><code>ImageFolder</code></a> local. Defina <code>config.dataset_name</code> como o id do repositório do conjunto de dados, se ele for do HugGan Community Event, ou <code>imagefolder</code> se você estiver usando suas próprias imagens.</p></blockquote> <p>🤗 O Datasets usa o recurso <a href="https://huggingface.co/docs/datasets/v5.2.0/en/package_reference/main_classes#datasets.Image" rel="nofollow">Image</a> para decodificar automaticamente os dados da imagem e carregá-la como <a href="https://pillow.readthedocs.io/en/stable/reference/Image.html" rel="nofollow"><code>PIL.Image</code></a>, que podemos visualizar:</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> Copiado</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>As imagens, no entanto, têm todos os tamanhos diferentes, então você precisará pré-processá-las primeiro:</p> <ul><li><code>Resize</code> altera o tamanho da imagem para o definido em <code>config.image_size</code>.</li> <li><code>RandomHorizontalFlip</code> aumenta o conjunto de dados espelhando as imagens aleatoriamente.</li> <li><code>Normalize</code> é importante para reescalar os valores dos pixels para o intervalo [-1, 1], que é o que o modelo espera.</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> Copiado</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>Use o método <a href="https://huggingface.co/docs/datasets/v5.2.0/en/package_reference/main_classes#datasets.Dataset.set_transform" rel="nofollow">set_transform</a> do 🤗 Datasets para aplicar a função <code>preprocess</code> em tempo real durante o treinamento:</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> Copiado</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>Sinta-se à vontade para visualizar as imagens novamente para confirmar que elas foram redimensionadas. Agora você está pronto para envolver o dataset em um <a href="https://pytorch.org/docs/stable/data#torch.utils.data.DataLoader" rel="nofollow">DataLoader</a> para o treinamento!</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> Copiado</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><!---->Crie um UNet2DModel<!----></span></h2><!--]--><!----> <p>Modelos pré-treinados no 🧨 Diffusers são facilmente criados a partir de sua classe de modelo com os parâmetros desejados. Por exemplo, para criar um <a href="/docs/diffusers/v0.43.0/pt/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> Copiado</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>Muitas vezes, é uma boa ideia verificar rapidamente se a forma da imagem de exemplo corresponde à forma da saída do modelo:</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> Copiado</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>Ótimo! Em seguida, você precisará de um agendador para adicionar algum ruído à imagem.</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><!---->Criar um agendador<!----></span></h2><!--]--><!----> <p>O agendador se comporta de maneira diferente dependendo de você estar usando o modelo para treinamento ou inferência. Durante a inferência, o agendador gera a imagem a partir do ruído. Durante o treinamento, o agendador recebe uma saída do modelo - ou uma amostra - de um ponto específico no processo de difusão e aplica ruído à imagem de acordo com um <em>agendamento de ruído</em> e uma <em>regra de atualização</em>.</p> <p>Vamos dar uma olhada no <a href="/docs/diffusers/v0.43.0/pt/api/schedulers/ddpm#diffusers.DDPMScheduler">DDPMScheduler</a> e usar o método <code>add_noise</code> para adicionar um pouco de ruído aleatório à <code>sample_image</code> de antes:</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> Copiado</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>O objetivo de treinamento do modelo é prever o ruído adicionado à imagem. A perda nesta etapa pode ser calculada por:</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> Copiado</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><!---->Treinar o modelo<!----></span></h2><!--]--><!----> <p>Até aqui, você já tem a maior parte das peças para começar a treinar o modelo e o que falta é juntar tudo.</p> <p>Primeiro, você precisará de um otimizador e de um agendador de taxa de aprendizado:</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> Copiado</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>Em seguida, você precisará de uma maneira de avaliar o modelo. Para a avaliação, você pode usar o <a href="/docs/diffusers/v0.43.0/pt/api/pipelines/ddpm#diffusers.DDPMPipeline">DDPMPipeline</a> para gerar um lote de imagens de exemplo e salvá-lo como uma grade:</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> Copiado</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>Agora você pode agrupar todos esses componentes em um loop de treinamento com 🤗 Accelerate para registro fácil no TensorBoard, acúmulo de gradientes e treinamento com precisão mista. Para enviar o modelo para o Hub, escreva uma função para obter o nome do seu repositório e informações e, em seguida, envie-o para o Hub.</p> <blockquote class="tip"><p>💡 O loop de treinamento abaixo pode parecer intimidador e longo, mas valerá a pena mais tarde, quando você iniciar o treinamento em apenas uma linha de código! Se não consegue esperar e quer começar a gerar imagens, sinta-se à vontade para copiar e executar o código abaixo. Você sempre pode voltar e examinar o loop de treinamento com mais detalhes depois, como quando estiver esperando seu modelo terminar o treinamento. 🤗</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> Copiado</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>Ufa, foi bastante código! Mas você finalmente está pronto para iniciar o treinamento com a função <a href="https://huggingface.co/docs/accelerate/v1.15.0/en/package_reference/launchers#accelerate.notebook_launcher" rel="nofollow">notebook_launcher</a> do 🤗 Accelerate. Passe para a função o loop de treinamento, todos os argumentos de treinamento e o número de processos (você pode alterar esse valor para o número de GPUs disponíveis para você) a serem usados no treinamento:</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> Copiado</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>Quando o treinamento estiver concluído, confira as imagens finais 🦋 geradas pelo seu modelo de difusão! 🦋</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> Copiado</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><!---->Próximas etapas<!----></span></h2><!--]--><!----> <p>A geração de imagens incondicional é um exemplo de tarefa que pode ser treinada. Você pode explorar outras tarefas e técnicas de treinamento visitando a página <a href="../training/overview">🧨 Exemplos de Treinamento do Diffusers</a>. Aqui estão alguns exemplos do que você pode aprender:</p> <ul><li><a href="../training/text_inversion">Textual Inversion</a>, um algoritmo que ensina a um modelo um conceito visual específico e o integra na imagem gerada.</li> <li><a href="../training/dreambooth">DreamBooth</a>, uma técnica para gerar imagens personalizadas de um sujeito a partir de várias imagens de entrada do sujeito.</li> <li><a href="../training/text2image">Guia</a> para o ajuste fino de um modelo Stable Diffusion em seu próprio conjunto de dados.</li> <li><a href="../training/lora">Guia</a> para o uso de LoRA, uma técnica de ajuste fino de modelos muito grandes que é eficiente em memória e mais rápida.</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:: 72.7 kB
Xet hash:: 0fcc744301d0cc5c181b82d1041b7ae24493f1be1df2fdf1cca0b7709b0c0576
Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.