Hugging Face's logo

Buckets:
hf-doc-build
/
doc

Files
xet
hf-doc-build/doc / diffusers /v0.43.0 /vi /tutorials /basic_training.html
mishig's picture
mishig
download
raw
74.5 kB
<meta charset="utf-8" /><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;Huấn luyện một mô hình khuếch tán&quot;,&quot;local&quot;:&quot;train-a-diffusion-model&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;Cấu hình huấn luyện&quot;,&quot;local&quot;:&quot;training-configuration&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Tải bộ dữ liệu&quot;,&quot;local&quot;:&quot;load-the-dataset&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Tạo một UNet2DModel&quot;,&quot;local&quot;:&quot;create-a-unet2dmodel&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Tạo một trình lập lịch&quot;,&quot;local&quot;:&quot;create-a-scheduler&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Huấn luyện mô hình&quot;,&quot;local&quot;:&quot;train-the-model&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Các bước tiếp theo&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><!---->Huấn luyện một mô hình khuếch tán<!----></span></h1><!--]--><!----> <p>Tạo ảnh không điều kiện là một ứng dụng phổ biến của mô hình khuếch tán, tạo ra các hình ảnh trông giống với những hình ảnh trong bộ dữ liệu được sử dụng để huấn luyện. Thông thường, kết quả tốt nhất đạt được từ việc tinh chỉnh (finetuning) một mô hình đã được huấn luyện trước trên một bộ dữ liệu cụ thể. Bạn có thể tìm thấy nhiều checkpoint như vậy trên <a href="https://huggingface.co/search/full-text?q=unconditional-image-generation&amp;type=model" rel="nofollow">Hub</a>, nhưng nếu không tìm được checkpoint nào ưng ý, bạn luôn có thể tự huấn luyện một checkpoint của riêng mình!</p> <p>Hướng dẫn này sẽ dạy bạn cách huấn luyện một <a href="/docs/diffusers/v0.43.0/vi/api/models/unet2d#diffusers.UNet2DModel">UNet2DModel</a> từ đầu trên một tập con của bộ dữ liệu <a href="https://huggingface.co/datasets/huggan/smithsonian_butterflies_subset" rel="nofollow">Smithsonian Butterflies</a> để tạo ra những chú bướm 🦋 của riêng bạn 🦋.</p> <blockquote class="tip"><p>💡 Bài hướng dẫn huấn luyện này dựa trên notebook <a href="https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/training_example.ipynb" rel="nofollow">Training with 🧨 Diffusers</a>. Để biết thêm chi tiết và ngữ cảnh về các mô hình khuếch tán, chẳng hạn như cách chúng hoạt động, hãy xem notebook!</p></blockquote> <p>Trước khi bắt đầu, hãy đảm bảo bạn đã cài đặt 🤗 Datasets để tải và tiền xử lý các bộ dữ liệu ảnh, cùng với 🤗 Accelerate để đơn giản hóa việc huấn luyện trên bất kỳ số lượng GPU nào. Lệnh sau đây cũng sẽ cài đặt <a href="https://www.tensorflow.org/tensorboard" rel="nofollow">TensorBoard</a> để trực quan hóa các chỉ số huấn luyện (bạn cũng có thể sử dụng <a href="https://docs.wandb.ai/" rel="nofollow">Weights &amp; Biases</a> để theo dõi quá trình huấn luyện của mình).</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> Đã sao chép</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>Chúng tôi khuyến khích bạn chia sẻ mô hình của mình với cộng đồng, và để làm được điều đó, bạn cần đăng nhập vào tài khoản Hugging Face của mình (tạo một tài khoản <a href="https://hf.co/join" rel="nofollow">tại đây</a> nếu bạn chưa có!). Bạn có thể đăng nhập từ notebook và nhập token khi được yêu cầu. Hãy đảm bảo token của bạn có vai trò ghi (write).</p> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg><!----> <div class=" absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0 "><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent;"></div> Đã sao chép</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>Hoặc đăng nhập từ 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> Đã sao chép</div><!----></button><!----></div> <pre class="language-bash "><!---->hf auth login<!----></pre></div><!----> <p>Vì các checkpoint của mô hình khá lớn, hãy cài đặt <a href="https://git-lfs.com/" rel="nofollow">Git-LFS</a> để quản lý phiên bản cho các tệp lớn này:</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> Đã sao chép</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><!---->Cấu hình huấn luyện<!----></span></h2><!--]--><!----> <p>Để tiện lợi, hãy tạo một lớp <code>TrainingConfig</code> chứa các siêu tham số huấn luyện (bạn có thể tự do điều chỉnh chúng):</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> Đã sao chép</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><!---->Tải bộ dữ liệu<!----></span></h2><!--]--><!----> <p>Bạn có thể dễ dàng tải bộ dữ liệu <a href="https://huggingface.co/datasets/huggan/smithsonian_butterflies_subset" rel="nofollow">Smithsonian Butterflies</a> bằng thư viện 🤗 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> Đã sao chép</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>💡 Bạn có thể tìm thêm các bộ dữ liệu từ <a href="https://huggingface.co/huggan" rel="nofollow">Sự kiện Cộng đồng HugGan</a> hoặc sử dụng bộ dữ liệu của riêng bạn bằng cách tạo một <a href="https://huggingface.co/docs/datasets/image_dataset#imagefolder" rel="nofollow"><code>ImageFolder</code></a> cục bộ. Đặt <code>config.dataset_name</code> thành id của kho dữ liệu nếu nó đến từ Sự kiện Cộng đồng HugGan, hoặc <code>imagefolder</code> nếu bạn đang sử dụng hình ảnh của riêng mình.</p></blockquote> <p>🤗 Datasets sử dụng tính năng <a href="https://huggingface.co/docs/datasets/v5.2.0/en/package_reference/main_classes#datasets.Image" rel="nofollow">Image</a> để tự động giải mã dữ liệu ảnh và nạp nó dưới dạng <a href="https://pillow.readthedocs.io/en/stable/reference/Image.html" rel="nofollow"><code>PIL.Image</code></a>, cho phép chúng ta trực quan hóa:</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> Đã sao chép</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>Tuy nhiên, tất cả các hình ảnh đều có kích thước khác nhau, vì vậy bạn sẽ cần tiền xử lý chúng trước:</p> <ul><li><code>Resize</code> thay đổi kích thước ảnh thành kích thước được định nghĩa trong <code>config.image_size</code>.</li> <li><code>RandomHorizontalFlip</code> tăng cường bộ dữ liệu bằng cách lật ngẫu nhiên các hình ảnh theo chiều ngang.</li> <li><code>Normalize</code> rất quan trọng để chuẩn hóa lại giá trị pixel vào khoảng [-1, 1], đây là điều mà mô hình mong đợi.</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> Đã sao chép</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>Sử dụng phương thức <a href="https://huggingface.co/docs/datasets/v5.2.0/en/package_reference/main_classes#datasets.Dataset.set_transform" rel="nofollow">set_transform</a> của 🤗 Datasets để áp dụng hàm <code>preprocess</code> trực tiếp trong quá trình huấn luyện:</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> Đã sao chép</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>Hãy tự do trực quan hóa lại các hình ảnh để xác nhận rằng chúng đã được thay đổi kích thước. Bây giờ bạn đã sẵn sàng bọc dataset trong một <a href="https://pytorch.org/docs/stable/data#torch.utils.data.DataLoader" rel="nofollow">DataLoader</a> để huấn luyện!</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> Đã sao chép</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><!---->Tạo một UNet2DModel<!----></span></h2><!--]--><!----> <p>Các mô hình được huấn luyện trước trong 🧨 Diffusers có thể dễ dàng được tạo ra từ lớp mô hình của chúng với các tham số bạn mong muốn. Ví dụ, để tạo một <a href="/docs/diffusers/v0.43.0/vi/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> Đã sao chép</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>Thường là một ý tưởng hay để nhanh chóng kiểm tra xem hình dạng của hình ảnh mẫu có khớp với hình dạng đầu ra của mô hình không:</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> Đã sao chép</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>Tuyệt! Tiếp theo, bạn sẽ cần một trình lập lịch (scheduler) để thêm nhiễu vào hình ảnh.</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><!---->Tạo một trình lập lịch<!----></span></h2><!--]--><!----> <p>Trình điều phối hoạt động khác nhau tùy thuộc vào việc bạn sử dụng mô hình cho huấn luyện hay suy luận. Trong quá trình suy luận, trình điều phối tạo ra hình ảnh từ nhiễu. Trong quá trình huấn luyện, trình điều phối nhận một đầu ra của mô hình - hoặc một mẫu - từ một điểm cụ thể trong quá trình khuếch tán và áp dụng nhiễu vào hình ảnh theo một <em>lịch trình nhiễu</em> và một <em>quy tắc cập nhật</em>.</p> <p>Hãy cùng xem xét <a href="/docs/diffusers/v0.43.0/vi/api/schedulers/ddpm#diffusers.DDPMScheduler">DDPMScheduler</a> và sử dụng phương thức <code>add_noise</code> để thêm một chút nhiễu ngẫu nhiên vào <code>sample_image</code> từ trước đó:</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> Đã sao chép</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>Mục tiêu huấn luyện của mô hình là dự đoán nhiễu được thêm vào ảnh. Tổn thất ở bước này có thể được tính bằng:</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> Đã sao chép</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><!---->Huấn luyện mô hình<!----></span></h2><!--]--><!----> <p>Đến đây, bạn đã có hầu hết các thành phần cần thiết để bắt đầu huấn luyện mô hình và điều còn lại chỉ là ghép tất cả lại với nhau.</p> <p>Đầu tiên, bạn sẽ cần một optimizer và một learning rate scheduler:</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> Đã sao chép</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>Sau đó, bạn sẽ cần một cách để đánh giá mô hình. Để đánh giá, bạn có thể sử dụng <a href="/docs/diffusers/v0.43.0/vi/api/pipelines/ddpm#diffusers.DDPMPipeline">DDPMPipeline</a> để tạo một lô ảnh mẫu và lưu chúng dưới dạng lưới:</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> Đã sao chép</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>Bây giờ bạn có thể kết hợp tất cả các thành phần này trong một vòng lặp huấn luyện với 🤗 Accelerate để dễ dàng ghi log TensorBoard, tích lũy gradient và huấn luyện độ chính xác hỗn hợp. Để tải mô hình lên Hub, hãy viết một hàm để lấy tên và thông tin kho lưu trữ của bạn, sau đó đẩy nó lên Hub.</p> <blockquote class="tip"><p>💡 Vòng lặp huấn luyện bên dưới có thể trông đáng sợ và dài dòng, nhưng nó sẽ xứng đáng khi bạn khởi chạy huấn luyện chỉ bằng một dòng mã sau này! Nếu bạn không thể chờ đợi và muốn bắt đầu tạo hình ảnh, hãy thoải mái sao chép và chạy mã bên dưới. Bạn luôn có thể quay lại và xem xét kỹ hơn vòng lặp huấn luyện sau, chẳng hạn như khi bạn đang chờ mô hình của mình hoàn tất huấn luyện. 🤗</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> Đã sao chép</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>Phew, khá nhiều mã! Nhưng cuối cùng bạn đã sẵn sàng để khởi động quá trình huấn luyện bằng hàm <a href="https://huggingface.co/docs/accelerate/v1.15.0/en/package_reference/launchers#accelerate.notebook_launcher" rel="nofollow">notebook_launcher</a> của 🤗 Accelerate. Truyền cho hàm này vòng lặp huấn luyện, tất cả các đối số huấn luyện và số lượng tiến trình (bạn có thể thay đổi giá trị này thành số lượng GPU khả dụng của bạn) sẽ được sử dụng cho huấn luyện:</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> Đã sao chép</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>Khi quá trình huấn luyện hoàn tất, hãy xem các hình ảnh 🦋 cuối cùng 🦋 do mô hình khuếch tán của bạn tạo ra!</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> Đã sao chép</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><!---->Các bước tiếp theo<!----></span></h2><!--]--><!----> <p>Tạo ảnh không điều kiện là một ví dụ về tác vụ có thể được huấn luyện. Bạn có thể khám phá các tác vụ và kỹ thuật huấn luyện khác bằng cách truy cập trang <a href="../training/overview">🧨 Diffusers Training Examples</a>. Dưới đây là một số ví dụ về những gì bạn có thể học:</p> <ul><li><a href="../training/text_inversion">Textual Inversion</a>, một thuật toán dạy cho mô hình một khái niệm thị giác cụ thể và tích hợp nó vào hình ảnh được tạo ra.</li> <li><a href="../training/dreambooth">DreamBooth</a>, một kỹ thuật để tạo ra các hình ảnh cá nhân hóa của một chủ thể dựa trên một vài hình ảnh đầu vào của chủ thể đó.</li> <li><a href="../training/text2image">Hướng dẫn</a> tinh chỉnh mô hình Stable Diffusion trên bộ dữ liệu của bạn.</li> <li><a href="../training/lora">Hướng dẫn</a> sử dụng LoRA, một kỹ thuật tiết kiệm bộ nhớ để tinh chỉnh các mô hình rất lớn nhanh hơn.</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:
74.5 kB
·
Xet hash:
94c56441ed725aa7d90eae8dadafd34fe5322a9e7cd677900df6d468789ef7dd

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