{"id":36431,"date":"2024-11-01T09:48:26","date_gmt":"2024-11-01T09:48:26","guid":{"rendered":"http:\/\/atmokpo.com\/w\/?p=36431"},"modified":"2024-11-01T11:53:12","modified_gmt":"2024-11-01T11:53:12","slug":"deep-learning-pytorch-course-faster-r-cnn","status":"publish","type":"post","link":"https:\/\/atmokpo.com\/w\/36431\/","title":{"rendered":"Deep Learning PyTorch Course, Faster R-CNN"},"content":{"rendered":"<article>\n<p>This course covers Faster R-CNN (Region-based Convolutional Neural Network), one of the object detection techniques utilizing deep learning. Additionally, we will implement Faster R-CNN using the PyTorch framework and explain the process of training it with real data.<\/p>\n<h2>1. Overview of Faster R-CNN<\/h2>\n<p>Faster R-CNN is a deep learning model that boasts high accuracy in detecting objects within images. It consists of two main components based on CNN (Convolutional Neural Network):<\/p>\n<ul>\n<li><strong>Region Proposal Network (RPN)<\/strong>: This is responsible for proposing potential object regions.<\/li>\n<li><strong>Fast R-CNN<\/strong>: It refines the regions produced by the RPN to predict the final object classes and bounding boxes.<\/li>\n<\/ul>\n<p>The main strength of Faster R-CNN is that RPN directly shares gradients with the CNN, allowing it to make object proposals much faster and more efficiently than previous methods.<\/p>\n<h2>2. How Faster R-CNN Works<\/h2>\n<p>Faster R-CNN operates through the following steps:<\/p>\n<ol>\n<li>The input image is passed through a CNN to generate feature maps.<\/li>\n<li>Based on the feature maps, the RPN generates proposed object regions.<\/li>\n<li>Fast R-CNN predicts the class of each proposed region and adjusts the bounding boxes based on these proposals.<\/li>\n<\/ol>\n<p>All these components adjust parameters during the training process, so if the data is well-prepared, high performance can be achieved.<\/p>\n<h2>3. Environment Setup<\/h2>\n<p>The libraries needed to implement Faster R-CNN are as follows:<\/p>\n<ul>\n<li><strong>torch<\/strong>: The PyTorch library<\/li>\n<li><strong>torchvision<\/strong>: Provides image processing and pre-processing functionalities<\/li>\n<li><strong>numpy<\/strong>: A library needed for array and numerical calculations<\/li>\n<li><strong>matplotlib<\/strong>: Used for visualizing results<\/li>\n<\/ul>\n<p>Additionally, you can use datasets provided by <strong>torchvision.datasets<\/strong> to handle datasets.<\/p>\n<h3>3.1. Library Installation<\/h3>\n<p>You can install the necessary libraries using the code below:<\/p>\n<pre><code>pip install torch torchvision numpy matplotlib<\/code><\/pre>\n<h2>4. Dataset Preparation<\/h2>\n<p>The datasets that can be used for training Faster R-CNN include PASCAL VOC, COCO, or a dataset created by you. Here, we will use the COCO dataset.<\/p>\n<h3>4.1. Downloading the COCO Dataset<\/h3>\n<p>The COCO dataset can be downloaded from various public sources, and it can be easily loaded through PyTorch&#8217;s Dataloader. The necessary dataset can be downloaded from the [official COCO dataset website](https:\/\/cocodataset.org\/#download).<\/p>\n<h2>5. Implementing the Faster R-CNN Model<\/h2>\n<p>Now let&#8217;s build the Faster R-CNN model using PyTorch. With the torchvision package in PyTorch, you can easily utilize the base framework.<\/p>\n<h3>5.1. Loading the Model<\/h3>\n<p>You can load a pre-trained model to perform Transfer Learning. This can improve training speed and performance.<\/p>\n<pre><code>\nimport torch\nimport torchvision\nfrom torchvision.models.detection import FasterRCNN\nfrom torchvision.models.detection.rpn import AnchorGenerator\n\n# Load pre-trained Faster R-CNN model\nmodel = torchvision.models.detection.fasterrcnn_resnet50_fpn(pretrained=True)\n\n# Adjust the model's classifier\nnum_classes = 91  # Number of classes in the COCO dataset\nin_features = model.roi_heads.box_predictor.cls_score.in_features\nmodel.roi_heads.box_predictor = torchvision.models.detection.faster_rcnn.FastRCNNPredictor(in_features, num_classes)\n    <\/code><\/pre>\n<h3>5.2. Data Preprocessing<\/h3>\n<p>A preprocessing step is necessary to adapt the data to the model. You need to convert the images to tensors and perform normalization.<\/p>\n<pre><code>\nfrom torchvision import transforms\n\ntransform = transforms.Compose([\n    transforms.ToTensor(),\n    transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),\n])\n    <\/code><\/pre>\n<h3>5.3. Setting Up the Data Loader<\/h3>\n<p>Use PyTorch&#8217;s DataLoader to efficiently load the data in batches.<\/p>\n<pre><code>\nfrom torch.utils.data import DataLoader\nfrom torchvision.datasets import CocoDetection\n\ndataset = CocoDetection(root='path\/to\/coco\/train2017',\n                         annFile='path\/to\/coco\/annotations\/instances_train2017.json',\n                         transform=transform)\n\ndata_loader = DataLoader(dataset, batch_size=4, shuffle=True, collate_fn=lambda x: tuple(zip(*x)))\n    <\/code><\/pre>\n<h2>6. Training the Model<\/h2>\n<p>Now we are ready to train the model. Define the optimizer and loss function, and set the epochs to train the model.<\/p>\n<h3>6.1. Defining Loss and Optimizer<\/h3>\n<pre><code>\ndevice = torch.device('cuda') if torch.cuda.is_available() else torch.device('cpu')\nmodel.to(device)\n\nparams = [p for p in model.parameters() if p.requires_grad]\noptimizer = torch.optim.SGD(params, lr=0.005, momentum=0.9, weight_decay=0.0005)\n    <\/code><\/pre>\n<h3>6.2. Training Loop<\/h3>\n<pre><code>\nnum_epochs = 10\n\nfor epoch in range(num_epochs):\n    model.train()\n    for images, targets in data_loader:\n        images = list(image.to(device) for image in images)\n        targets = [{k: v.to(device) for k, v in t.items()} for t in targets]\n    \n        # Initialize gradients\n        optimizer.zero_grad()\n    \n        # Model predictions\n        loss_dict = model(images, targets)\n    \n        # Calculate loss\n        losses = sum(loss for loss in loss_dict.values())\n    \n        # Backpropagation\n        losses.backward()\n        optimizer.step()\n    \n    print(f\"Epoch {epoch+1}\/{num_epochs}, Loss: {losses.item()}\")\n    <\/code><\/pre>\n<h2>7. Validation and Evaluation<\/h2>\n<p>To evaluate the model&#8217;s performance, we will test the trained model using a validation dataset.<\/p>\n<h3>7.1. Defining Evaluation Function<\/h3>\n<pre><code>\ndef evaluate(model, data_loader):\n    model.eval()\n    list_of_boxes = []\n    list_of_scores = []\n    list_of_labels = []\n\n    with torch.no_grad():\n        for images, targets in data_loader:\n            images = list(image.to(device) for image in images)\n            outputs = model(images)\n     \n            # Save results\n            for output in outputs:\n                list_of_boxes.append(output['boxes'].cpu().numpy())\n                list_of_scores.append(output['scores'].cpu().numpy())\n                list_of_labels.append(output['labels'].cpu().numpy())\n\n    return list_of_boxes, list_of_scores, list_of_labels\n    <\/code><\/pre>\n<h2>8. Result Visualization<\/h2>\n<p>Visualize the model&#8217;s object detection results to see how well it works in practice.<\/p>\n<pre><code>\nimport matplotlib.pyplot as plt\nimport torchvision.transforms.functional as F\n\ndef visualize_results(images, boxes, labels):\n    for img, box, label in zip(images, boxes, labels):\n        img = F.to_pil_image(img)\n        plt.imshow(img)\n\n        for b, l in zip(box, label):\n            xmin, ymin, xmax, ymax = b\n            plt.gca().add_patch(plt.Rectangle((xmin, ymin), xmax - xmin, ymax - ymin,\n                                    fill=False, edgecolor='red', linewidth=3))\n            plt.text(xmin, ymin, f'Class: {l}', bbox=dict(facecolor='yellow', alpha=0.5))\n\n        plt.axis('off')\n        plt.show()\n\n# Load images and targets, then visualize\nimages, targets = next(iter(data_loader))\nboxes, scores, labels = evaluate(model, [images])\nvisualize_results(images, boxes, labels)\n    <\/code><\/pre>\n<h2>9. Conclusion<\/h2>\n<p>In this lecture, we learned how to implement Faster R-CNN using PyTorch. We understood the basic principles of object detection and how RPN and Fast R-CNN work, and we could verify the model&#8217;s performance through the training, validation, and visualization processes. I hope you can apply this to real projects and build an object detection model tailored to your data.<\/p>\n<\/article>\n","protected":false},"excerpt":{"rendered":"<p>This course covers Faster R-CNN (Region-based Convolutional Neural Network), one of the object detection techniques utilizing deep learning. Additionally, we will implement Faster R-CNN using the PyTorch framework and explain the process of training it with real data. 1. Overview of Faster R-CNN Faster R-CNN is a deep learning model that boasts high accuracy in &hellip; <a href=\"https:\/\/atmokpo.com\/w\/36431\/\" class=\"more-link\">\ub354 \ubcf4\uae30<span class=\"screen-reader-text\"> &#8220;Deep Learning PyTorch Course, Faster R-CNN&#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":[149],"tags":[],"class_list":["post-36431","post","type-post","status-publish","format-standard","hentry","category-pytorch-study"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v26.2 - https:\/\/yoast.com\/wordpress\/plugins\/seo\/ -->\n<title>Deep Learning PyTorch Course, Faster R-CNN - \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\/36431\/\" \/>\n<meta property=\"og:locale\" content=\"ko_KR\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Deep Learning PyTorch Course, Faster R-CNN - \ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8\" \/>\n<meta property=\"og:description\" content=\"This course covers Faster R-CNN (Region-based Convolutional Neural Network), one of the object detection techniques utilizing deep learning. Additionally, we will implement Faster R-CNN using the PyTorch framework and explain the process of training it with real data. 1. Overview of Faster R-CNN Faster R-CNN is a deep learning model that boasts high accuracy in &hellip; \ub354 \ubcf4\uae30 &quot;Deep Learning PyTorch Course, Faster R-CNN&quot;\" \/>\n<meta property=\"og:url\" content=\"https:\/\/atmokpo.com\/w\/36431\/\" \/>\n<meta property=\"og:site_name\" content=\"\ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8\" \/>\n<meta property=\"article:published_time\" content=\"2024-11-01T09:48:26+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2024-11-01T11:53:12+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=\"5\ubd84\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\/\/atmokpo.com\/w\/36431\/#article\",\"isPartOf\":{\"@id\":\"https:\/\/atmokpo.com\/w\/36431\/\"},\"author\":{\"name\":\"root\",\"@id\":\"https:\/\/atmokpo.com\/w\/#\/schema\/person\/91b6b3b138fbba0efb4ae64b1abd81d7\"},\"headline\":\"Deep Learning PyTorch Course, Faster R-CNN\",\"datePublished\":\"2024-11-01T09:48:26+00:00\",\"dateModified\":\"2024-11-01T11:53:12+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\/\/atmokpo.com\/w\/36431\/\"},\"wordCount\":559,\"publisher\":{\"@id\":\"https:\/\/atmokpo.com\/w\/#organization\"},\"articleSection\":[\"PyTorch Study\"],\"inLanguage\":\"ko-KR\"},{\"@type\":\"WebPage\",\"@id\":\"https:\/\/atmokpo.com\/w\/36431\/\",\"url\":\"https:\/\/atmokpo.com\/w\/36431\/\",\"name\":\"Deep Learning PyTorch Course, Faster R-CNN - \ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8\",\"isPartOf\":{\"@id\":\"https:\/\/atmokpo.com\/w\/#website\"},\"datePublished\":\"2024-11-01T09:48:26+00:00\",\"dateModified\":\"2024-11-01T11:53:12+00:00\",\"breadcrumb\":{\"@id\":\"https:\/\/atmokpo.com\/w\/36431\/#breadcrumb\"},\"inLanguage\":\"ko-KR\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/atmokpo.com\/w\/36431\/\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/atmokpo.com\/w\/36431\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"\ud648\",\"item\":\"https:\/\/atmokpo.com\/w\/en\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Deep Learning PyTorch Course, Faster R-CNN\"}]},{\"@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":"Deep Learning PyTorch Course, Faster R-CNN - \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\/36431\/","og_locale":"ko_KR","og_type":"article","og_title":"Deep Learning PyTorch Course, Faster R-CNN - \ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8","og_description":"This course covers Faster R-CNN (Region-based Convolutional Neural Network), one of the object detection techniques utilizing deep learning. Additionally, we will implement Faster R-CNN using the PyTorch framework and explain the process of training it with real data. 1. Overview of Faster R-CNN Faster R-CNN is a deep learning model that boasts high accuracy in &hellip; \ub354 \ubcf4\uae30 \"Deep Learning PyTorch Course, Faster R-CNN\"","og_url":"https:\/\/atmokpo.com\/w\/36431\/","og_site_name":"\ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8","article_published_time":"2024-11-01T09:48:26+00:00","article_modified_time":"2024-11-01T11:53:12+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":"5\ubd84"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/atmokpo.com\/w\/36431\/#article","isPartOf":{"@id":"https:\/\/atmokpo.com\/w\/36431\/"},"author":{"name":"root","@id":"https:\/\/atmokpo.com\/w\/#\/schema\/person\/91b6b3b138fbba0efb4ae64b1abd81d7"},"headline":"Deep Learning PyTorch Course, Faster R-CNN","datePublished":"2024-11-01T09:48:26+00:00","dateModified":"2024-11-01T11:53:12+00:00","mainEntityOfPage":{"@id":"https:\/\/atmokpo.com\/w\/36431\/"},"wordCount":559,"publisher":{"@id":"https:\/\/atmokpo.com\/w\/#organization"},"articleSection":["PyTorch Study"],"inLanguage":"ko-KR"},{"@type":"WebPage","@id":"https:\/\/atmokpo.com\/w\/36431\/","url":"https:\/\/atmokpo.com\/w\/36431\/","name":"Deep Learning PyTorch Course, Faster R-CNN - \ub77c\uc774\ube0c\uc2a4\ub9c8\ud2b8","isPartOf":{"@id":"https:\/\/atmokpo.com\/w\/#website"},"datePublished":"2024-11-01T09:48:26+00:00","dateModified":"2024-11-01T11:53:12+00:00","breadcrumb":{"@id":"https:\/\/atmokpo.com\/w\/36431\/#breadcrumb"},"inLanguage":"ko-KR","potentialAction":[{"@type":"ReadAction","target":["https:\/\/atmokpo.com\/w\/36431\/"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/atmokpo.com\/w\/36431\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"\ud648","item":"https:\/\/atmokpo.com\/w\/en\/"},{"@type":"ListItem","position":2,"name":"Deep Learning PyTorch Course, Faster R-CNN"}]},{"@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\/36431","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=36431"}],"version-history":[{"count":1,"href":"https:\/\/atmokpo.com\/w\/wp-json\/wp\/v2\/posts\/36431\/revisions"}],"predecessor-version":[{"id":36432,"href":"https:\/\/atmokpo.com\/w\/wp-json\/wp\/v2\/posts\/36431\/revisions\/36432"}],"wp:attachment":[{"href":"https:\/\/atmokpo.com\/w\/wp-json\/wp\/v2\/media?parent=36431"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/atmokpo.com\/w\/wp-json\/wp\/v2\/categories?post=36431"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/atmokpo.com\/w\/wp-json\/wp\/v2\/tags?post=36431"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}