Hugging Face's logo

Buckets:
hf-doc-build
/
doc

Files
xet
hf-doc-build/doc / diffusers /main /fr /tutorials /basic_training.html
mishig's picture
mishig
download
raw
73.4 kB
<meta charset="utf-8" /><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;Entraîner un modèle de diffusion&quot;,&quot;local&quot;:&quot;train-a-diffusion-model&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;Configuration de l'entraînement&quot;,&quot;local&quot;:&quot;training-configuration&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Charger le jeu de données&quot;,&quot;local&quot;:&quot;load-the-dataset&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Créer un UNet2DModel&quot;,&quot;local&quot;:&quot;create-a-unet2dmodel&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Créer un planificateur&quot;,&quot;local&quot;:&quot;create-a-scheduler&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Entraîner le modèle&quot;,&quot;local&quot;:&quot;train-the-model&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Étapes suivantes&quot;,&quot;local&quot;:&quot;next-steps&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2}],&quot;depth&quot;:1}"/>
<link href="/docs/diffusers/main/en/_app/immutable/entry/start.D3LnKZ4R.js" rel="modulepreload">
<link href="/docs/diffusers/main/en/_app/immutable/chunks/BF9UNEM9.js" rel="modulepreload">
<link href="/docs/diffusers/main/en/_app/immutable/chunks/DPnyVmXs.js" rel="modulepreload">
<link href="/docs/diffusers/main/en/_app/immutable/entry/app.C0rBoMxR.js" rel="modulepreload">
<link href="/docs/diffusers/main/en/_app/immutable/chunks/DSGUT_OW.js" rel="modulepreload">
<link href="/docs/diffusers/main/en/_app/immutable/chunks/C045MWWx.js" rel="modulepreload">
<link href="/docs/diffusers/main/en/_app/immutable/chunks/DnVIJfC5.js" rel="modulepreload">
<link href="/docs/diffusers/main/en/_app/immutable/chunks/DsnmJJEf.js" rel="modulepreload">
<link href="/docs/diffusers/main/en/_app/immutable/nodes/0.DTZsP_3B.js" rel="modulepreload">
<link href="/docs/diffusers/main/en/_app/immutable/chunks/IaDvMxLQ.js" rel="modulepreload">
<link href="/docs/diffusers/main/en/_app/immutable/nodes/319.OvCVDJ2Q.js" rel="modulepreload">
<link href="/docs/diffusers/main/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/main/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><!---->Entraîner un modèle de diffusion<!----></span></h1><!--]--><!----> <p>La génération d’images non conditionnée est une application populaire des modèles de diffusion qui produit des images ressemblant à celles du jeu de données utilisé pour l’entraînement. En général, les meilleurs résultats sont obtenus en affinant un modèle préentraîné sur un jeu de données spécifique. Vous pouvez trouver de nombreux de ces points de contrôle sur le <a href="https://huggingface.co/search/full-text?q=unconditional-image-generation&amp;type=model" rel="nofollow">Hub</a>, mais si vous n’en trouvez pas qui vous convient, vous pouvez toujours entraîner le vôtre !</p> <p>Ce tutoriel vous apprendra à entraîner un <a href="/docs/diffusers/main/fr/api/models/unet2d#diffusers.UNet2DModel">UNet2DModel</a> à partir de zéro sur un sous-ensemble du jeu de données <a href="https://huggingface.co/datasets/huggan/smithsonian_butterflies_subset" rel="nofollow">Smithsonian Butterflies</a> afin de générer vos propres papillons 🦋.</p> <blockquote class="tip"><p>💡 Ce tutoriel d'entraînement est basé sur le notebook <a href="https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/training_example.ipynb" rel="nofollow">Training with 🧨 Diffusers</a>. Pour plus de détails et de contexte sur les modèles de diffusion, comme leur fonctionnement, consultez le notebook !</p></blockquote> <p>Avant de commencer, assurez-vous d'avoir installé 🤗 Datasets pour charger et prétraiter les jeux de données d'images, ainsi que 🤗 Accelerate, afin de simplifier l'entraînement sur n'importe quel nombre de GPU. La commande suivante installera également <a href="https://www.tensorflow.org/tensorboard" rel="nofollow">TensorBoard</a> pour visualiser les métriques d'entraînement (vous pouvez également utiliser <a href="https://docs.wandb.ai/" rel="nofollow">Weights &amp; Biases</a> pour suivre votre entraînement).</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> Copié</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>Nous vous encourageons à partager votre modèle avec la communauté. Pour ce faire, vous devrez vous connecter à votre compte Hugging Face (en créer un <a href="https://hf.co/join" rel="nofollow">ici</a> si vous n’en avez pas encore !). Vous pouvez vous connecter depuis un notebook et saisir votre jeton lorsque cela vous est demandé. Assurez-vous que votre jeton dispose du rôle d’écriture.</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> Copié</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 connectez-vous depuis le 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> Copié</div><!----></button><!----></div> <pre class="language-bash "><!---->hf auth login<!----></pre></div><!----> <p>Les points de contrôle du modèle étant assez volumineux, installez <a href="https://git-lfs.com/" rel="nofollow">Git-LFS</a> pour versionner ces fichiers de grande taille :</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> Copié</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><!---->Configuration de l'entraînement<!----></span></h2><!--]--><!----> <p>Pour plus de commodité, créez une classe <code>TrainingConfig</code> contenant les hyperparamètres d'entraînement (n'hésitez pas à les ajuster) :</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> Copié</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><!---->Charger le jeu de données<!----></span></h2><!--]--><!----> <p>Vous pouvez facilement charger le jeu de données <a href="https://huggingface.co/datasets/huggan/smithsonian_butterflies_subset" rel="nofollow">Smithsonian Butterflies</a> avec la bibliothèque 🤗 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> Copié</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>💡 Vous pouvez trouver des jeux de données supplémentaires dans le <a href="https://huggingface.co/huggan" rel="nofollow">HugGan Community Event</a> ou utiliser votre propre jeu de données en créant un <a href="https://huggingface.co/docs/datasets/image_dataset#imagefolder" rel="nofollow"><code>ImageFolder</code></a> local. Définissez <code>config.dataset_name</code> sur l'identifiant du dépôt du jeu de données s'il provient du HugGan Community Event, ou sur <code>imagefolder</code> si vous utilisez vos propres images.</p></blockquote> <p>🤗 Datasets utilise la fonctionnalité <a href="https://huggingface.co/docs/datasets/main/en/package_reference/main_classes#datasets.Image" rel="nofollow">Image</a> pour décoder automatiquement les données d'image et les charger en tant que <a href="https://pillow.readthedocs.io/en/stable/reference/Image.html" rel="nofollow"><code>PIL.Image</code></a>, ce qui nous permet de les visualiser :</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> Copié</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>Les images ont toutes des tailles différentes, il faut donc les prétraiter d'abord :</p> <ul><li><code>Resize</code> modifie la taille de l'image pour qu'elle corresponde à celle définie dans <code>config.image_size</code>.</li> <li><code>RandomHorizontalFlip</code> augmente le jeu de données en inversant aléatoirement les images.</li> <li><code>Normalize</code> est important pour remettre à l'échelle les valeurs des pixels dans l'intervalle [-1, 1], ce que le modèle attend.</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> Copié</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>Utilisez la méthode <a href="https://huggingface.co/docs/datasets/main/en/package_reference/main_classes#datasets.Dataset.set_transform" rel="nofollow">set_transform</a> de 🤗 Datasets pour appliquer la fonction <code>preprocess</code> à la volée pendant l’entraînement :</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> Copié</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>N’hésitez pas à visualiser à nouveau les images pour confirmer qu’elles ont été redimensionnées. Vous êtes maintenant prêt à encapsuler le jeu de données dans un <a href="https://pytorch.org/docs/stable/data#torch.utils.data.DataLoader" rel="nofollow">DataLoader</a> pour l’entraînement !</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> Copié</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><!---->Créer un UNet2DModel<!----></span></h2><!--]--><!----> <p>Les modèles préentraînés dans 🧨 Diffusers sont facilement créés à partir de leur classe de modèle avec les paramètres souhaités. Par exemple, pour créer un <a href="/docs/diffusers/main/fr/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> Copié</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>Il est souvent judicieux de vérifier rapidement que la forme de l'image d'exemple correspond à la forme de la sortie du modèle :</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> Copié</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>Parfait ! Ensuite, vous aurez besoin d'un planificateur pour ajouter du bruit à l'image.</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><!---->Créer un planificateur<!----></span></h2><!--]--><!----> <p>Le comportement du planificateur varie selon que vous utilisez le modèle pour l’entraînement ou pour l’inférence. Lors de l’inférence, le planificateur génère l’image à partir du bruit. Lors de l’entraînement, le planificateur prend une sortie du modèle – ou un échantillon – à un point précis du processus de diffusion et applique du bruit à l’image selon un <em>plan de bruit</em> et une <em>règle de mise à jour</em>.</p> <p>Regardons le <a href="/docs/diffusers/main/fr/api/schedulers/ddpm#diffusers.DDPMScheduler">DDPMScheduler</a> et utilisons la méthode <code>add_noise</code> pour ajouter du bruit aléatoire à l’image <code>sample_image</code> de tout à l’heure :</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> Copié</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>L'objectif d'entraînement du modèle est de prédire le bruit ajouté à l'image. La perte à cette étape peut être calculée par :</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> Copié</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><!---->Entraîner le modèle<!----></span></h2><!--]--><!----> <p>À ce stade, vous disposez de la plupart des éléments nécessaires pour commencer l’entraînement du modèle, et il ne reste plus qu’à assembler le tout.</p> <p>Tout d'abord, vous aurez besoin d'un optimiseur et d'un planificateur de taux d'apprentissage :</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> Copié</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>Ensuite, vous aurez besoin d'une méthode pour évaluer le modèle. Pour l'évaluation, vous pouvez utiliser le <a href="/docs/diffusers/main/fr/api/pipelines/ddpm#diffusers.DDPMPipeline">DDPMPipeline</a> pour générer un lot d'images d'exemple et l'enregistrer sous forme de grille :</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> Copié</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>Vous pouvez maintenant assembler tous ces composants dans une boucle d’entraînement avec 🤗 Accelerate pour bénéficier d’un journalisation TensorBoard simplifiée, d’une accumulation de gradients et d’une formation en précision mixte. Pour téléverser le modèle sur le Hub, écrivez une fonction pour récupérer le nom de votre dépôt et ses informations, puis poussez-le sur le Hub.</p> <blockquote class="tip"><p>💡 La boucle d’entraînement ci-dessous peut sembler intimidante et longue, mais cela en vaudra la peine plus tard lorsque vous lancerez votre entraînement en une seule ligne de code ! Si vous ne pouvez pas attendre et souhaitez commencer à générer des images, n’hésitez pas à copier et exécuter le code ci-dessous. Vous pourrez toujours revenir plus tard pour examiner la boucle d’entraînement plus en détail, par exemple pendant que vous attendez que votre modèle termine son entraînement. 🤗</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> Copié</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>Ouf, c’était pas mal de code ! Mais vous êtes enfin prêt à lancer l’entraînement avec la fonction <a href="https://huggingface.co/docs/accelerate/main/en/package_reference/launchers#accelerate.notebook_launcher" rel="nofollow">notebook_launcher</a> de 🤗 Accelerate. Transmettez à la fonction la boucle d’entraînement, tous les arguments d’entraînement et le nombre de processus (vous pouvez modifier cette valeur pour correspondre au nombre de GPU disponibles) à utiliser pour l’entraînement :</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> Copié</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>Une fois l'entraînement terminé, jetez un œil aux images 🦋 finales 🦋 générées par votre modèle de diffusion !</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> Copié</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><!---->Étapes suivantes<!----></span></h2><!--]--><!----> <p>La génération d’images non conditionnelle est un exemple de tâche qui peut être entraînée. Vous pouvez explorer d’autres tâches et techniques d’entraînement en consultant la page <a href="../training/overview">🧨 Diffusers Training Examples</a>. Voici quelques exemples de ce que vous pouvez apprendre :</p> <ul><li><a href="../training/text_inversion">Textual Inversion</a>, un algorithme qui apprend à un modèle un concept visuel spécifique et l’intègre dans l’image générée.</li> <li><a href="../training/dreambooth">DreamBooth</a>, une technique permettant de générer des images personnalisées d’un sujet à partir de plusieurs images d’entrée de ce sujet.</li> <li><a href="../training/text2image">Guide</a> pour l’ajustement fin d’un modèle Stable Diffusion sur votre propre jeu de données.</li> <li><a href="../training/lora">Guide</a> pour utiliser LoRA, une technique de fine-tuning économe en mémoire permettant d'entraîner plus rapidement des modèles très volumineux.</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_g37pnb = {
base: "/docs/diffusers/main/en",
assets: "/docs/diffusers/main/en"
};
const element = document.currentScript.parentElement;
Promise.all([
import("/docs/diffusers/main/en/_app/immutable/entry/start.D3LnKZ4R.js"),
import("/docs/diffusers/main/en/_app/immutable/entry/app.C0rBoMxR.js")
]).then(([kit, app]) => {
kit.start(app, element, {
node_ids: [0, 319],
data: [null,null],
form: null,
error: null
});
});
}
</script>

Xet Storage Details

Size:
73.4 kB
·
Xet hash:
087dab33a46cf3079f50bd85567b9b7a2b05ee32e873e710c959ffada8abf780

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