Buckets:
| <meta charset="utf-8" /><meta name="hf:doc:metadata" content="{"title":"Semantic segmentation","local":"semantic-segmentation","sections":[],"depth":1}"> | |
| <link href="/docs/datasets/pr_8113/en/_app/immutable/assets/0.e3b0c442.css" rel="modulepreload"> | |
| <link rel="modulepreload" href="/docs/datasets/pr_8113/en/_app/immutable/entry/start.969da75e.js"> | |
| <link rel="modulepreload" href="/docs/datasets/pr_8113/en/_app/immutable/chunks/scheduler.d75c11ed.js"> | |
| <link rel="modulepreload" href="/docs/datasets/pr_8113/en/_app/immutable/chunks/singletons.61bfd4fd.js"> | |
| <link rel="modulepreload" href="/docs/datasets/pr_8113/en/_app/immutable/chunks/index.d12496d4.js"> | |
| <link rel="modulepreload" href="/docs/datasets/pr_8113/en/_app/immutable/chunks/paths.4c60f2bc.js"> | |
| <link rel="modulepreload" href="/docs/datasets/pr_8113/en/_app/immutable/entry/app.687c6ad1.js"> | |
| <link rel="modulepreload" href="/docs/datasets/pr_8113/en/_app/immutable/chunks/preload-helper.a19054d5.js"> | |
| <link rel="modulepreload" href="/docs/datasets/pr_8113/en/_app/immutable/chunks/index.4ec9dfe9.js"> | |
| <link rel="modulepreload" href="/docs/datasets/pr_8113/en/_app/immutable/nodes/0.4378a702.js"> | |
| <link rel="modulepreload" href="/docs/datasets/pr_8113/en/_app/immutable/chunks/each.e59479a4.js"> | |
| <link rel="modulepreload" href="/docs/datasets/pr_8113/en/_app/immutable/nodes/42.8a892e57.js"> | |
| <link rel="modulepreload" href="/docs/datasets/pr_8113/en/_app/immutable/chunks/MermaidChart.svelte_svelte_type_style_lang.903f9bf7.js"> | |
| <link rel="modulepreload" href="/docs/datasets/pr_8113/en/_app/immutable/chunks/CodeBlock.77fa95e2.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{"title":"Semantic segmentation","local":"semantic-segmentation","sections":[],"depth":1}"><!-- HEAD_svelte-u9bgzb_END --> <p></p> <div class="items-center shrink-0 min-w-[100px] max-sm:min-w-[50px] justify-end ml-auto flex" style="float: right; margin-left: 10px; display: inline-flex; position: relative; z-index: 10;"><div 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>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> </div> <h1 class="relative group"><a id="semantic-segmentation" 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="#semantic-segmentation"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>Semantic segmentation</span></h1> <p data-svelte-h="svelte-fw4ret">Semantic segmentation datasets are used to train a model to classify every pixel in an image. There are | |
| a wide variety of applications enabled by these datasets such as background removal from images, stylizing | |
| images, or scene understanding for autonomous driving. This guide will show you how to apply transformations | |
| to an image segmentation dataset.</p> <p data-svelte-h="svelte-1qtuikq">Before you start, make sure you have up-to-date versions of <code>albumentations</code> and <code>cv2</code> installed:</p> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START -->pip install -U albumentations opencv-python<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-180f5nb"><a href="https://albumentations.ai/" rel="nofollow">Albumentations</a> is a Python library for performing data augmentation | |
| for computer vision. It supports various computer vision tasks such as image classification, object | |
| detection, segmentation, and keypoint estimation.</p> <p data-svelte-h="svelte-1jjf6cy">This guide uses the <a href="https://huggingface.co/datasets/scene_parse_150" rel="nofollow">Scene Parsing</a> dataset for segmenting | |
| and parsing an image into different image regions associated with semantic categories, such as sky, road, person, and bed.</p> <p data-svelte-h="svelte-pju1x0">Load the <code>train</code> split of the dataset and take a look at an example:</p> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START --><span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> datasets <span class="hljs-keyword">import</span> load_dataset | |
| <span class="hljs-meta">>>> </span>dataset = load_dataset(<span class="hljs-string">"scene_parse_150"</span>, split=<span class="hljs-string">"train"</span>) | |
| <span class="hljs-meta">>>> </span>index = <span class="hljs-number">10</span> | |
| <span class="hljs-meta">>>> </span>dataset[index] | |
| {<span class="hljs-string">'image'</span>: <PIL.JpegImagePlugin.JpegImageFile image mode=RGB size=683x512 at <span class="hljs-number">0x7FB37B0EC810</span>>, | |
| <span class="hljs-string">'annotation'</span>: <PIL.PngImagePlugin.PngImageFile image mode=L size=683x512 at <span class="hljs-number">0x7FB37B0EC9D0</span>>, | |
| <span class="hljs-string">'scene_category'</span>: <span class="hljs-number">927</span>}<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-jjwn46">The dataset has three fields:</p> <ul data-svelte-h="svelte-1r68wni"><li><code>image</code>: a PIL image object.</li> <li><code>annotation</code>: segmentation mask of the image.</li> <li><code>scene_category</code>: the label or scene category of the image (like “kitchen” or “office”).</li></ul> <p data-svelte-h="svelte-15dthpv">Next, check out an image with:</p> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START --><span class="hljs-meta">>>> </span>dataset[index][<span class="hljs-string">"image"</span>]<!-- HTML_TAG_END --></pre></div> <div class="flex justify-center" data-svelte-h="svelte-1337354"><img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/datasets/image_seg.png"></div> <p data-svelte-h="svelte-qlholw">Similarly, you can check out the respective segmentation mask:</p> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START --><span class="hljs-meta">>>> </span>dataset[index][<span class="hljs-string">"annotation"</span>]<!-- HTML_TAG_END --></pre></div> <div class="flex justify-center" data-svelte-h="svelte-ru2vd9"><img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/datasets/seg_mask.png"></div> <p data-svelte-h="svelte-vzaie7">We can also add a <a href="https://github.com/tensorflow/models/blob/3f1ca33afe3c1631b733ea7e40c294273b9e406d/research/deeplab/utils/get_dataset_colormap.py#L51" rel="nofollow">color palette</a> on the | |
| segmentation mask and overlay it on top of the original image to visualize the dataset:</p> <p data-svelte-h="svelte-vvbf2j">After defining the color palette, you should be ready to visualize some overlays.</p> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START --><span class="hljs-meta">>>> </span><span class="hljs-keyword">import</span> matplotlib.pyplot <span class="hljs-keyword">as</span> plt | |
| <span class="hljs-meta">>>> </span><span class="hljs-keyword">def</span> <span class="hljs-title function_">visualize_seg_mask</span>(<span class="hljs-params">image: np.ndarray, mask: np.ndarray</span>): | |
| <span class="hljs-meta">... </span> color_seg = np.zeros((mask.shape[<span class="hljs-number">0</span>], mask.shape[<span class="hljs-number">1</span>], <span class="hljs-number">3</span>), dtype=np.uint8) | |
| <span class="hljs-meta">... </span> palette = np.array(create_ade20k_label_colormap()) | |
| <span class="hljs-meta">... </span> <span class="hljs-keyword">for</span> label, color <span class="hljs-keyword">in</span> <span class="hljs-built_in">enumerate</span>(palette): | |
| <span class="hljs-meta">... </span> color_seg[mask == label, :] = color | |
| <span class="hljs-meta">... </span> color_seg = color_seg[..., ::-<span class="hljs-number">1</span>] <span class="hljs-comment"># convert to BGR</span> | |
| <span class="hljs-meta">... </span> img = np.array(image) * <span class="hljs-number">0.5</span> + color_seg * <span class="hljs-number">0.5</span> <span class="hljs-comment"># plot the image with the segmentation map</span> | |
| <span class="hljs-meta">... </span> img = img.astype(np.uint8) | |
| <span class="hljs-meta">... </span> plt.figure(figsize=(<span class="hljs-number">15</span>, <span class="hljs-number">10</span>)) | |
| <span class="hljs-meta">... </span> plt.imshow(img) | |
| <span class="hljs-meta">... </span> plt.axis(<span class="hljs-string">"off"</span>) | |
| <span class="hljs-meta">... </span> plt.show() | |
| <span class="hljs-meta">>>> </span>visualize_seg_mask( | |
| <span class="hljs-meta">... </span> np.array(dataset[index][<span class="hljs-string">"image"</span>]), | |
| <span class="hljs-meta">... </span> np.array(dataset[index][<span class="hljs-string">"annotation"</span>]) | |
| <span class="hljs-meta">... </span>)<!-- HTML_TAG_END --></pre></div> <div class="flex justify-center" data-svelte-h="svelte-1unth95"><img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/datasets/seg_overlay.png"></div> <p data-svelte-h="svelte-c3rxqx">Now apply some augmentations with <code>albumentations</code>. You’ll first resize the image and adjust its brightness.</p> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START --><span class="hljs-meta">>>> </span><span class="hljs-keyword">import</span> albumentations | |
| <span class="hljs-meta">>>> </span>transform = albumentations.Compose( | |
| <span class="hljs-meta">... </span> [ | |
| <span class="hljs-meta">... </span> albumentations.Resize(<span class="hljs-number">256</span>, <span class="hljs-number">256</span>), | |
| <span class="hljs-meta">... </span> albumentations.RandomBrightnessContrast(brightness_limit=<span class="hljs-number">0.3</span>, contrast_limit=<span class="hljs-number">0.3</span>, p=<span class="hljs-number">0.5</span>), | |
| <span class="hljs-meta">... </span> ] | |
| <span class="hljs-meta">... </span>)<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-50733g">Create a function to apply the transformation to the images:</p> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START --><span class="hljs-meta">>>> </span><span class="hljs-keyword">def</span> <span class="hljs-title function_">transforms</span>(<span class="hljs-params">examples</span>): | |
| <span class="hljs-meta">... </span> transformed_images, transformed_masks = [], [] | |
| ... | |
| <span class="hljs-meta">... </span> <span class="hljs-keyword">for</span> image, seg_mask <span class="hljs-keyword">in</span> <span class="hljs-built_in">zip</span>(examples[<span class="hljs-string">"image"</span>], examples[<span class="hljs-string">"annotation"</span>]): | |
| <span class="hljs-meta">... </span> image, seg_mask = np.array(image), np.array(seg_mask) | |
| <span class="hljs-meta">... </span> transformed = transform(image=image, mask=seg_mask) | |
| <span class="hljs-meta">... </span> transformed_images.append(transformed[<span class="hljs-string">"image"</span>]) | |
| <span class="hljs-meta">... </span> transformed_masks.append(transformed[<span class="hljs-string">"mask"</span>]) | |
| ... | |
| <span class="hljs-meta">... </span> examples[<span class="hljs-string">"pixel_values"</span>] = transformed_images | |
| <span class="hljs-meta">... </span> examples[<span class="hljs-string">"label"</span>] = transformed_masks | |
| <span class="hljs-meta">... </span> <span class="hljs-keyword">return</span> examples<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-12nty9f">Use the <a href="/docs/datasets/pr_8113/en/package_reference/main_classes#datasets.Dataset.set_transform">set_transform()</a> function to apply the transformation on-the-fly to batches of the dataset to consume less disk space:</p> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START --><span class="hljs-meta">>>> </span>dataset.set_transform(transforms)<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-11iow8s">You can verify the transformation worked by indexing into the <code>pixel_values</code> and <code>label</code> of an example:</p> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START --><span class="hljs-meta">>>> </span>image = np.array(dataset[index][<span class="hljs-string">"pixel_values"</span>]) | |
| <span class="hljs-meta">>>> </span>mask = np.array(dataset[index][<span class="hljs-string">"label"</span>]) | |
| <span class="hljs-meta">>>> </span>visualize_seg_mask(image, mask)<!-- HTML_TAG_END --></pre></div> <div class="flex justify-center" data-svelte-h="svelte-rz0i83"><img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/datasets/albumentations_seg.png"></div> <p data-svelte-h="svelte-o9kxh2">In this guide, you have used <code>albumentations</code> for augmenting the dataset. It’s also possible to use <code>torchvision</code> to apply some similar transforms.</p> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START --><span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> torchvision.transforms <span class="hljs-keyword">import</span> Resize, ColorJitter, Compose | |
| <span class="hljs-meta">>>> </span>transformation_chain = Compose([ | |
| <span class="hljs-meta">... </span> Resize((<span class="hljs-number">256</span>, <span class="hljs-number">256</span>)), | |
| <span class="hljs-meta">... </span> ColorJitter(brightness=<span class="hljs-number">0.25</span>, contrast=<span class="hljs-number">0.25</span>, saturation=<span class="hljs-number">0.25</span>, hue=<span class="hljs-number">0.1</span>) | |
| <span class="hljs-meta">... </span>]) | |
| <span class="hljs-meta">>>> </span>resize = Resize((<span class="hljs-number">256</span>, <span class="hljs-number">256</span>)) | |
| <span class="hljs-meta">>>> </span><span class="hljs-keyword">def</span> <span class="hljs-title function_">train_transforms</span>(<span class="hljs-params">example_batch</span>): | |
| <span class="hljs-meta">... </span> example_batch[<span class="hljs-string">"pixel_values"</span>] = [transformation_chain(x) <span class="hljs-keyword">for</span> x <span class="hljs-keyword">in</span> example_batch[<span class="hljs-string">"image"</span>]] | |
| <span class="hljs-meta">... </span> example_batch[<span class="hljs-string">"label"</span>] = [resize(x) <span class="hljs-keyword">for</span> x <span class="hljs-keyword">in</span> example_batch[<span class="hljs-string">"annotation"</span>]] | |
| <span class="hljs-meta">... </span> <span class="hljs-keyword">return</span> example_batch | |
| <span class="hljs-meta">>>> </span>dataset.set_transform(train_transforms) | |
| <span class="hljs-meta">>>> </span>image = np.array(dataset[index][<span class="hljs-string">"pixel_values"</span>]) | |
| <span class="hljs-meta">>>> </span>mask = np.array(dataset[index][<span class="hljs-string">"label"</span>]) | |
| <span class="hljs-meta">>>> </span>visualize_seg_mask(image, mask)<!-- HTML_TAG_END --></pre></div> <div class="flex justify-center" data-svelte-h="svelte-jb5bqb"><img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/datasets/torchvision_seg.png"></div> <blockquote class="tip" data-svelte-h="svelte-57s756"><p>Now that you know how to process a dataset for semantic segmentation, learn | |
| <a href="https://huggingface.co/docs/transformers/tasks/semantic_segmentation" rel="nofollow">how to train a semantic segmentation model</a> | |
| and use it for inference.</p></blockquote> <a class="!text-gray-400 !no-underline text-sm flex items-center not-prose mt-4" href="https://github.com/huggingface/datasets/blob/main/docs/source/semantic_segmentation.mdx" 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 data-svelte-h="svelte-zjs2n5"><span class="underline">Update</span> on GitHub</span></a> <p></p> | |
| <script> | |
| { | |
| __sveltekit_1j7f9j2 = { | |
| assets: "/docs/datasets/pr_8113/en", | |
| base: "/docs/datasets/pr_8113/en", | |
| env: {} | |
| }; | |
| const element = document.currentScript.parentElement; | |
| const data = [null,null]; | |
| Promise.all([ | |
| import("/docs/datasets/pr_8113/en/_app/immutable/entry/start.969da75e.js"), | |
| import("/docs/datasets/pr_8113/en/_app/immutable/entry/app.687c6ad1.js") | |
| ]).then(([kit, app]) => { | |
| kit.start(app, element, { | |
| node_ids: [0, 42], | |
| data, | |
| form: null, | |
| error: null | |
| }); | |
| }); | |
| } | |
| </script> | |
Xet Storage Details
- Size:
- 30.8 kB
- Xet hash:
- 1e8fa4645036eb6f55da471aaf7ed9b9bf028a70f6f6e8330e836a5d31a00ee1
·
Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.