{"id":36219,"date":"2024-11-01T09:46:44","date_gmt":"2024-11-01T09:46:44","guid":{"rendered":"http:\/\/atmokpo.com\/w\/?p=36219"},"modified":"2024-11-01T09:46:44","modified_gmt":"2024-11-01T09:46:44","slug":"using-hugging-face-transformers-check-the-image-after-preprocessing","status":"publish","type":"post","link":"https:\/\/atmokpo.com\/w\/36219\/","title":{"rendered":"Using Hugging Face Transformers: Check the Image After Preprocessing"},"content":{"rendered":"<p>Data preprocessing is very important in the field of deep learning. This is especially true when dealing with high-dimensional data such as image processing. In this course, we will explain in detail how to utilize the transformer models provided by Hugging Face and present ways to directly verify the results through the image preprocessing process. This course will address image classification problems, providing explanations along with the necessary Python code for each step.<\/p>\n<h2>1. What is Hugging Face?<\/h2>\n<p>Hugging Face provides libraries for natural language processing (NLP) and other machine learning tasks. In particular, it offers implementations of transformer models and a variety of pretrained models, helping researchers and developers to easily utilize these models.<\/p>\n<h2>2. Importance of Preprocessing<\/h2>\n<p>Data preprocessing has a significant impact on model performance. For image data, the following tasks are included:<\/p>\n<ul>\n<li>Resizing: Consistently resizes images of various dimensions to the same size.<\/li>\n<li>Normalization: Adjusts pixel values to a range of 0 to 1.<\/li>\n<li>Data Augmentation: Allows the model to learn from a more diverse set of data.<\/li>\n<\/ul>\n<h2>3. Environment Setup<\/h2>\n<p>For this course, you need to install the following libraries. Run the code below if early installation is required.<\/p>\n<pre><code>pip install transformers torch torchvision<\/code><\/pre>\n<h2>4. Loading and Preprocessing Images<\/h2>\n<p>Now, let&#8217;s write the code to load and preprocess the images. The code below uses PIL (Python Imaging Library) to process images.<\/p>\n<pre><code>from PIL import Image\nimport torchvision.transforms as transforms\nimport matplotlib.pyplot as plt\n\n# Load image\nimage_path = 'your_image_path.jpg'  # Please specify the image path\nimage = Image.open(image_path)\n\n# Define preprocessing tasks\ntransform = transforms.Compose([\n    transforms.Resize((256, 256)),        # Resize\n    transforms.ToTensor(),                 # Convert to tensor\n    transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))  # Normalize\n])\n\n# Apply preprocessing\nprocessed_image = transform(image)\n\n# Visualize the transformed image\nplt.imshow(processed_image.permute(1, 2, 0) \/ 2 + 0.5)  # Transform back to image for visualization\nplt.axis('off')\nplt.show()<\/code><\/pre>\n<h2>5. Explanation of Preprocessing<\/h2>\n<p>Each preprocessing step used in the code above serves the following roles:<\/p>\n<ul>\n<li><strong>transforms.Resize((256, 256)):<\/strong> Resizes the image to 256&#215;256. This is to match the input size of the model.<\/li>\n<li><strong>transforms.ToTensor():<\/strong> Converts the image to tensor format. This matches the way PyTorch models process data.<\/li>\n<li><strong>transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5)):<\/strong> Normalizes each channel of the image. This speeds up the learning process and aids in model convergence.<\/li>\n<\/ul>\n<h2>6. Using Hugging Face Transformer Models<\/h2>\n<p>You can easily use pretrained transformer models through the Hugging Face library. In the next step, we will look at multimodal models that use both images and text simultaneously.<\/p>\n<pre><code>from transformers import ViTForImageClassification, ViTFeatureExtractor\nimport torch\n\n# Load model and feature extractor\nmodel_name = 'google\/vit-base-patch16-224-in21k'\nmodel = ViTForImageClassification.from_pretrained(model_name)\nextractor = ViTFeatureExtractor.from_pretrained(model_name)\n\n# Extract image features\ninputs = extractor(images=image, return_tensors=\"pt\")\n\n# Inference\nwith torch.no_grad():\n    outputs = model(**inputs)\n    logits = outputs.logits\n    predicted_class_idx = logits.argmax(-1).item()\n\nprint(f'Predicted class index: {predicted_class_idx}<\/code><\/pre>\n<h2>7. Verifying Results<\/h2>\n<p>In the code above, we classified the image using the ViT (Vision Transformer) model. You can verify the predicted class index through the model&#8217;s output. The predicted class index can be interpreted by converting it to a label matching the dataset.<\/p>\n<pre><code>from transformers import AutoTokenizer\n\n# Load classification labels\nlabels = AutoTokenizer.from_pretrained(model_name).tokenizer  # Or define your own list\npredicted_label = labels[predicted_class_idx]\n\nprint(f'Predicted label: {predicted_label}<\/code><\/pre>\n<h2>8. Summary and Conclusion<\/h2>\n<p>In this course, we explored how to perform image preprocessing and classification tasks using Hugging Face transformers. Data preprocessing is an essential process for creating a good model, and you can expand the provided code to suit your dataset. By utilizing the Hugging Face library, you can easily work with various data and models, enabling a lot of research and development possibilities.<\/p>\n<p>I hope the knowledge you gained in this course leads to a deeper understanding! Feel free to adjust the code to your needs and try various experiments.<\/p>\n<h2>9. References<\/h2>\n<ul>\n<li><a href=\"https:\/\/huggingface.co\/transformers\/\">Hugging Face Official Documentation<\/a><\/li>\n<li><a href=\"https:\/\/pytorch.org\/vision\/stable\/index.html\">PyTorch Image Processing<\/a><\/li>\n<\/ul>\n","protected":false},"excerpt":{"rendered":"<p>Data preprocessing is very important in the field of deep learning. This is especially true when dealing with high-dimensional data such as image processing. In this course, we will explain in detail how to utilize the transformer models provided by Hugging Face and present ways to directly verify the results through the image preprocessing process. &hellip; <a href=\"https:\/\/atmokpo.com\/w\/36219\/\" class=\"more-link\">\ub354 \ubcf4\uae30<span class=\"screen-reader-text\"> &#8220;Using Hugging Face Transformers: Check the Image After Preprocessing&#8221;<\/span><\/a><\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_jetpack_memberships_contains_paid_content":false,"footnotes":""},"categories":[108],"tags":[],"class_list":["post-36219","post","type-post","status-publish","format-standard","hentry","category---en"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v26.2 - https:\/\/yoast.com\/wordpress\/plugins\/seo\/ -->\n<title>Using Hugging Face Transformers: Check the Image After Preprocessing - \ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/atmokpo.com\/w\/36219\/\" \/>\n<meta property=\"og:locale\" content=\"ko_KR\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Using Hugging Face Transformers: Check the Image After Preprocessing - \ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8\" \/>\n<meta property=\"og:description\" content=\"Data preprocessing is very important in the field of deep learning. This is especially true when dealing with high-dimensional data such as image processing. In this course, we will explain in detail how to utilize the transformer models provided by Hugging Face and present ways to directly verify the results through the image preprocessing process. &hellip; \ub354 \ubcf4\uae30 &quot;Using Hugging Face Transformers: Check the Image After Preprocessing&quot;\" \/>\n<meta property=\"og:url\" content=\"https:\/\/atmokpo.com\/w\/36219\/\" \/>\n<meta property=\"og:site_name\" content=\"\ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8\" \/>\n<meta property=\"article:published_time\" content=\"2024-11-01T09:46:44+00:00\" \/>\n<meta name=\"author\" content=\"root\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:creator\" content=\"@bebubo4\" \/>\n<meta name=\"twitter:site\" content=\"@bebubo4\" \/>\n<meta name=\"twitter:label1\" content=\"\uae00\uc4f4\uc774\" \/>\n\t<meta name=\"twitter:data1\" content=\"root\" \/>\n\t<meta name=\"twitter:label2\" content=\"\uc608\uc0c1 \ub418\ub294 \ud310\ub3c5 \uc2dc\uac04\" \/>\n\t<meta name=\"twitter:data2\" content=\"3\ubd84\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\/\/atmokpo.com\/w\/36219\/#article\",\"isPartOf\":{\"@id\":\"https:\/\/atmokpo.com\/w\/36219\/\"},\"author\":{\"name\":\"root\",\"@id\":\"https:\/\/atmokpo.com\/w\/#\/schema\/person\/91b6b3b138fbba0efb4ae64b1abd81d7\"},\"headline\":\"Using Hugging Face Transformers: Check the Image After Preprocessing\",\"datePublished\":\"2024-11-01T09:46:44+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\/\/atmokpo.com\/w\/36219\/\"},\"wordCount\":470,\"publisher\":{\"@id\":\"https:\/\/atmokpo.com\/w\/#organization\"},\"articleSection\":[\"Using Hugging Face\"],\"inLanguage\":\"ko-KR\"},{\"@type\":\"WebPage\",\"@id\":\"https:\/\/atmokpo.com\/w\/36219\/\",\"url\":\"https:\/\/atmokpo.com\/w\/36219\/\",\"name\":\"Using Hugging Face Transformers: Check the Image After Preprocessing - \ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8\",\"isPartOf\":{\"@id\":\"https:\/\/atmokpo.com\/w\/#website\"},\"datePublished\":\"2024-11-01T09:46:44+00:00\",\"breadcrumb\":{\"@id\":\"https:\/\/atmokpo.com\/w\/36219\/#breadcrumb\"},\"inLanguage\":\"ko-KR\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/atmokpo.com\/w\/36219\/\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/atmokpo.com\/w\/36219\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"\ud648\",\"item\":\"https:\/\/atmokpo.com\/w\/en\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Using Hugging Face Transformers: Check the Image After Preprocessing\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/atmokpo.com\/w\/#website\",\"url\":\"https:\/\/atmokpo.com\/w\/\",\"name\":\"\ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8\",\"description\":\"\",\"publisher\":{\"@id\":\"https:\/\/atmokpo.com\/w\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/atmokpo.com\/w\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"ko-KR\"},{\"@type\":\"Organization\",\"@id\":\"https:\/\/atmokpo.com\/w\/#organization\",\"name\":\"\ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8\",\"url\":\"https:\/\/atmokpo.com\/w\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"ko-KR\",\"@id\":\"https:\/\/atmokpo.com\/w\/#\/schema\/logo\/image\/\",\"url\":\"https:\/\/atmokpo.com\/w\/wp-content\/uploads\/2024\/11\/logo.png\",\"contentUrl\":\"https:\/\/atmokpo.com\/w\/wp-content\/uploads\/2024\/11\/logo.png\",\"width\":400,\"height\":400,\"caption\":\"\ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8\"},\"image\":{\"@id\":\"https:\/\/atmokpo.com\/w\/#\/schema\/logo\/image\/\"},\"sameAs\":[\"https:\/\/x.com\/bebubo4\"]},{\"@type\":\"Person\",\"@id\":\"https:\/\/atmokpo.com\/w\/#\/schema\/person\/91b6b3b138fbba0efb4ae64b1abd81d7\",\"name\":\"root\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"ko-KR\",\"@id\":\"https:\/\/atmokpo.com\/w\/#\/schema\/person\/image\/\",\"url\":\"https:\/\/secure.gravatar.com\/avatar\/708197b41fc6435a7ce22d951b25d4a47e9e904270cb1f04682d4f025066f80c?s=96&d=mm&r=g\",\"contentUrl\":\"https:\/\/secure.gravatar.com\/avatar\/708197b41fc6435a7ce22d951b25d4a47e9e904270cb1f04682d4f025066f80c?s=96&d=mm&r=g\",\"caption\":\"root\"},\"sameAs\":[\"http:\/\/atmokpo.com\/w\"],\"url\":\"https:\/\/atmokpo.com\/w\/author\/root\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Using Hugging Face Transformers: Check the Image After Preprocessing - \ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/atmokpo.com\/w\/36219\/","og_locale":"ko_KR","og_type":"article","og_title":"Using Hugging Face Transformers: Check the Image After Preprocessing - \ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8","og_description":"Data preprocessing is very important in the field of deep learning. This is especially true when dealing with high-dimensional data such as image processing. In this course, we will explain in detail how to utilize the transformer models provided by Hugging Face and present ways to directly verify the results through the image preprocessing process. &hellip; \ub354 \ubcf4\uae30 \"Using Hugging Face Transformers: Check the Image After Preprocessing\"","og_url":"https:\/\/atmokpo.com\/w\/36219\/","og_site_name":"\ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8","article_published_time":"2024-11-01T09:46:44+00:00","author":"root","twitter_card":"summary_large_image","twitter_creator":"@bebubo4","twitter_site":"@bebubo4","twitter_misc":{"\uae00\uc4f4\uc774":"root","\uc608\uc0c1 \ub418\ub294 \ud310\ub3c5 \uc2dc\uac04":"3\ubd84"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/atmokpo.com\/w\/36219\/#article","isPartOf":{"@id":"https:\/\/atmokpo.com\/w\/36219\/"},"author":{"name":"root","@id":"https:\/\/atmokpo.com\/w\/#\/schema\/person\/91b6b3b138fbba0efb4ae64b1abd81d7"},"headline":"Using Hugging Face Transformers: Check the Image After Preprocessing","datePublished":"2024-11-01T09:46:44+00:00","mainEntityOfPage":{"@id":"https:\/\/atmokpo.com\/w\/36219\/"},"wordCount":470,"publisher":{"@id":"https:\/\/atmokpo.com\/w\/#organization"},"articleSection":["Using Hugging Face"],"inLanguage":"ko-KR"},{"@type":"WebPage","@id":"https:\/\/atmokpo.com\/w\/36219\/","url":"https:\/\/atmokpo.com\/w\/36219\/","name":"Using Hugging Face Transformers: Check the Image After Preprocessing - \ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8","isPartOf":{"@id":"https:\/\/atmokpo.com\/w\/#website"},"datePublished":"2024-11-01T09:46:44+00:00","breadcrumb":{"@id":"https:\/\/atmokpo.com\/w\/36219\/#breadcrumb"},"inLanguage":"ko-KR","potentialAction":[{"@type":"ReadAction","target":["https:\/\/atmokpo.com\/w\/36219\/"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/atmokpo.com\/w\/36219\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"\ud648","item":"https:\/\/atmokpo.com\/w\/en\/"},{"@type":"ListItem","position":2,"name":"Using Hugging Face Transformers: Check the Image After Preprocessing"}]},{"@type":"WebSite","@id":"https:\/\/atmokpo.com\/w\/#website","url":"https:\/\/atmokpo.com\/w\/","name":"\ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8","description":"","publisher":{"@id":"https:\/\/atmokpo.com\/w\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/atmokpo.com\/w\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"ko-KR"},{"@type":"Organization","@id":"https:\/\/atmokpo.com\/w\/#organization","name":"\ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8","url":"https:\/\/atmokpo.com\/w\/","logo":{"@type":"ImageObject","inLanguage":"ko-KR","@id":"https:\/\/atmokpo.com\/w\/#\/schema\/logo\/image\/","url":"https:\/\/atmokpo.com\/w\/wp-content\/uploads\/2024\/11\/logo.png","contentUrl":"https:\/\/atmokpo.com\/w\/wp-content\/uploads\/2024\/11\/logo.png","width":400,"height":400,"caption":"\ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8"},"image":{"@id":"https:\/\/atmokpo.com\/w\/#\/schema\/logo\/image\/"},"sameAs":["https:\/\/x.com\/bebubo4"]},{"@type":"Person","@id":"https:\/\/atmokpo.com\/w\/#\/schema\/person\/91b6b3b138fbba0efb4ae64b1abd81d7","name":"root","image":{"@type":"ImageObject","inLanguage":"ko-KR","@id":"https:\/\/atmokpo.com\/w\/#\/schema\/person\/image\/","url":"https:\/\/secure.gravatar.com\/avatar\/708197b41fc6435a7ce22d951b25d4a47e9e904270cb1f04682d4f025066f80c?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/708197b41fc6435a7ce22d951b25d4a47e9e904270cb1f04682d4f025066f80c?s=96&d=mm&r=g","caption":"root"},"sameAs":["http:\/\/atmokpo.com\/w"],"url":"https:\/\/atmokpo.com\/w\/author\/root\/"}]}},"jetpack_featured_media_url":"","jetpack_sharing_enabled":true,"jetpack-related-posts":[],"_links":{"self":[{"href":"https:\/\/atmokpo.com\/w\/wp-json\/wp\/v2\/posts\/36219","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/atmokpo.com\/w\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/atmokpo.com\/w\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/atmokpo.com\/w\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/atmokpo.com\/w\/wp-json\/wp\/v2\/comments?post=36219"}],"version-history":[{"count":1,"href":"https:\/\/atmokpo.com\/w\/wp-json\/wp\/v2\/posts\/36219\/revisions"}],"predecessor-version":[{"id":36220,"href":"https:\/\/atmokpo.com\/w\/wp-json\/wp\/v2\/posts\/36219\/revisions\/36220"}],"wp:attachment":[{"href":"https:\/\/atmokpo.com\/w\/wp-json\/wp\/v2\/media?parent=36219"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/atmokpo.com\/w\/wp-json\/wp\/v2\/categories?post=36219"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/atmokpo.com\/w\/wp-json\/wp\/v2\/tags?post=36219"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}