{"id":8,"date":"2023-06-12T17:07:57","date_gmt":"2023-06-12T17:07:57","guid":{"rendered":"https:\/\/farrukhnaveed.co\/blog\/?p=8"},"modified":"2023-09-13T23:00:08","modified_gmt":"2023-09-13T17:30:08","slug":"train-yolov8-on-custom-data","status":"publish","type":"post","link":"https:\/\/farrukhnaveed.co\/blogs\/train-yolov8-on-custom-data\/","title":{"rendered":"Train YOLOv8 on Custom Data?"},"content":{"rendered":"\n<p><a href=\"https:\/\/medium.com\/@chr043416?source=post_page-----6d28cd348262--------------------------------\"><\/a><\/p>\n\n\n\n<p id=\"51df\">YOLOv8\ud83d\udd25has been released by Ultralytics on (10th, Jan 2023).<\/p>\n\n\n\n<p id=\"9b66\">It has provided advancements in computer vision that have brought about a massive novelty in the way we perceive, analyze, and understand the visual world. It will allow for unprecedented possibilities in various fields.<\/p>\n\n\n\n<p id=\"eb0e\">Considerable improvements have been made in terms of speed, accuracy, and architecture. Its implementation is done from scratch, and no major modules (i.e model architecture) have been used from YOLOv5. It is faster in speed and more accurate than its previous version (YOLOv7), and it has achieved a new high in terms of Mean Average Precision (MAP) with a score of 53.7.<\/p>\n\n\n\n<p id=\"034a\">In this article, we will focus on steps that are required to do training of YOLOv8 on custom data. You can follow mentioned steps below to train YOLOv8 on your own data. All mentioned steps have been tested properly and working fine on Windows and Linux operating systems.<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li>Installation of Modules<\/li>\n\n\n\n<li>Pretrained Object Detection<\/li>\n\n\n\n<li>Train YOLOv8 on Custom Data<\/li>\n\n\n\n<li>Inference with Custom Weights<\/li>\n<\/ul>\n\n\n\n<p id=\"7ef8\"><strong>Installation of Modules<\/strong><\/p>\n\n\n\n<p id=\"bc7d\">YOLOv8 released a package named \u201cultralytics\u201d, that you can install with the mentioned command below.<\/p>\n\n\n\n<div class=\"wp-block-kevinbatdorf-code-block-pro\" data-code-block-pro-font-family=\"Code-Pro-JetBrains-Mono\" style=\"font-size:.875rem;font-family:Code-Pro-JetBrains-Mono,ui-monospace,SFMono-Regular,Menlo,Monaco,Consolas,monospace;line-height:1.25rem;--cbp-tab-width:2;tab-size:var(--cbp-tab-width, 2)\"><span style=\"display:block;padding:16px 0 0 16px;margin-bottom:-1px;width:100%;text-align:left;background-color:#2e3440ff\"><svg xmlns=\"http:\/\/www.w3.org\/2000\/svg\" width=\"54\" height=\"14\" viewBox=\"0 0 54 14\"><g fill=\"none\" fill-rule=\"evenodd\" transform=\"translate(1 1)\"><circle cx=\"6\" cy=\"6\" r=\"6\" fill=\"#FF5F56\" stroke=\"#E0443E\" stroke-width=\".5\"><\/circle><circle cx=\"26\" cy=\"6\" r=\"6\" fill=\"#FFBD2E\" stroke=\"#DEA123\" stroke-width=\".5\"><\/circle><circle cx=\"46\" cy=\"6\" r=\"6\" fill=\"#27C93F\" stroke=\"#1AAB29\" stroke-width=\".5\"><\/circle><\/g><\/svg><\/span><span role=\"button\" tabindex=\"0\" data-code=\"pip install ultralytics==8.0.0\n\" style=\"color:#d8dee9ff;display:none\" aria-label=\"Copy\" class=\"code-block-pro-copy-button\"><svg xmlns=\"http:\/\/www.w3.org\/2000\/svg\" style=\"width:24px;height:24px\" fill=\"none\" viewBox=\"0 0 24 24\" stroke=\"currentColor\" stroke-width=\"2\"><path class=\"with-check\" stroke-linecap=\"round\" stroke-linejoin=\"round\" d=\"M9 5H7a2 2 0 00-2 2v12a2 2 0 002 2h10a2 2 0 002-2V7a2 2 0 00-2-2h-2M9 5a2 2 0 002 2h2a2 2 0 002-2M9 5a2 2 0 012-2h2a2 2 0 012 2m-6 9l2 2 4-4\"><\/path><path class=\"without-check\" stroke-linecap=\"round\" stroke-linejoin=\"round\" d=\"M9 5H7a2 2 0 00-2 2v12a2 2 0 002 2h10a2 2 0 002-2V7a2 2 0 00-2-2h-2M9 5a2 2 0 002 2h2a2 2 0 002-2M9 5a2 2 0 012-2h2a2 2 0 012 2\"><\/path><\/svg><\/span><pre class=\"shiki nord\" style=\"background-color: #2e3440ff\" tabindex=\"0\"><code><span class=\"line\"><span style=\"color: #88C0D0\">pip<\/span><span style=\"color: #D8DEE9FF\"> <\/span><span style=\"color: #A3BE8C\">install<\/span><span style=\"color: #D8DEE9FF\"> <\/span><span style=\"color: #A3BE8C\">ultralytics==<\/span><span style=\"color: #B48EAD\">8.0<\/span><span style=\"color: #A3BE8C\">.0<\/span><\/span>\n<span class=\"line\"><\/span><\/code><\/pre><\/div>\n\n\n\n<p id=\"bc7d\">or<\/p>\n\n\n\n<div class=\"wp-block-kevinbatdorf-code-block-pro\" data-code-block-pro-font-family=\"Code-Pro-JetBrains-Mono\" style=\"font-size:.875rem;font-family:Code-Pro-JetBrains-Mono,ui-monospace,SFMono-Regular,Menlo,Monaco,Consolas,monospace;line-height:1.25rem;--cbp-tab-width:2;tab-size:var(--cbp-tab-width, 2)\"><span style=\"display:block;padding:16px 0 0 16px;margin-bottom:-1px;width:100%;text-align:left;background-color:#2e3440ff\"><svg xmlns=\"http:\/\/www.w3.org\/2000\/svg\" width=\"54\" height=\"14\" viewBox=\"0 0 54 14\"><g fill=\"none\" fill-rule=\"evenodd\" transform=\"translate(1 1)\"><circle cx=\"6\" cy=\"6\" r=\"6\" fill=\"#FF5F56\" stroke=\"#E0443E\" stroke-width=\".5\"><\/circle><circle cx=\"26\" cy=\"6\" r=\"6\" fill=\"#FFBD2E\" stroke=\"#DEA123\" stroke-width=\".5\"><\/circle><circle cx=\"46\" cy=\"6\" r=\"6\" fill=\"#27C93F\" stroke=\"#1AAB29\" stroke-width=\".5\"><\/circle><\/g><\/svg><\/span><span role=\"button\" tabindex=\"0\" data-code=\"# latestversion\npip install ultralytics \" style=\"color:#d8dee9ff;display:none\" aria-label=\"Copy\" class=\"code-block-pro-copy-button\"><svg xmlns=\"http:\/\/www.w3.org\/2000\/svg\" style=\"width:24px;height:24px\" fill=\"none\" viewBox=\"0 0 24 24\" stroke=\"currentColor\" stroke-width=\"2\"><path class=\"with-check\" stroke-linecap=\"round\" stroke-linejoin=\"round\" d=\"M9 5H7a2 2 0 00-2 2v12a2 2 0 002 2h10a2 2 0 002-2V7a2 2 0 00-2-2h-2M9 5a2 2 0 002 2h2a2 2 0 002-2M9 5a2 2 0 012-2h2a2 2 0 012 2m-6 9l2 2 4-4\"><\/path><path class=\"without-check\" stroke-linecap=\"round\" stroke-linejoin=\"round\" d=\"M9 5H7a2 2 0 00-2 2v12a2 2 0 002 2h10a2 2 0 002-2V7a2 2 0 00-2-2h-2M9 5a2 2 0 002 2h2a2 2 0 002-2M9 5a2 2 0 012-2h2a2 2 0 012 2\"><\/path><\/svg><\/span><pre class=\"shiki nord\" style=\"background-color: #2e3440ff\" tabindex=\"0\"><code><span class=\"line\"><span style=\"color: #616E88\"># latestversion<\/span><\/span>\n<span class=\"line\"><span style=\"color: #88C0D0\">pip<\/span><span style=\"color: #D8DEE9FF\"> <\/span><span style=\"color: #A3BE8C\">install<\/span><span style=\"color: #D8DEE9FF\"> <\/span><span style=\"color: #A3BE8C\">ultralytics<\/span><span style=\"color: #D8DEE9FF\"> <\/span><\/span><\/code><\/pre><\/div>\n\n\n\n<p id=\"c01c\">The above command will install all the packages that are required to use YOLOv8 for detection and training on your own data.<\/p>\n\n\n\n<p id=\"be1a\"><strong>Note:&nbsp;<\/strong>Make sure, that you have python 3.7.0 or newer installed on your system.<\/p>\n\n\n\n<p id=\"1795\"><strong>Pretrained Object Detection<\/strong><\/p>\n\n\n\n<p id=\"f29d\">What will be your feeling? if you will need to run a single command that can do object detection in an efficient way and provide you results with better accuracy and fast speed.<\/p>\n\n\n\n<p id=\"84fb\">You can run the mentioned command below in terminal\/(command prompt) to do detection with pre-trained weights on your selected video\/image using YOLOv8.<\/p>\n\n\n\n<p><strong>For Image<\/strong><\/p>\n\n\n\n<div class=\"wp-block-kevinbatdorf-code-block-pro\" data-code-block-pro-font-family=\"Code-Pro-JetBrains-Mono\" style=\"font-size:.875rem;font-family:Code-Pro-JetBrains-Mono,ui-monospace,SFMono-Regular,Menlo,Monaco,Consolas,monospace;line-height:1.25rem;--cbp-tab-width:2;tab-size:var(--cbp-tab-width, 2)\"><span style=\"display:block;padding:16px 0 0 16px;margin-bottom:-1px;width:100%;text-align:left;background-color:#2e3440ff\"><svg xmlns=\"http:\/\/www.w3.org\/2000\/svg\" width=\"54\" height=\"14\" viewBox=\"0 0 54 14\"><g fill=\"none\" fill-rule=\"evenodd\" transform=\"translate(1 1)\"><circle cx=\"6\" cy=\"6\" r=\"6\" fill=\"#FF5F56\" stroke=\"#E0443E\" stroke-width=\".5\"><\/circle><circle cx=\"26\" cy=\"6\" r=\"6\" fill=\"#FFBD2E\" stroke=\"#DEA123\" stroke-width=\".5\"><\/circle><circle cx=\"46\" cy=\"6\" r=\"6\" fill=\"#27C93F\" stroke=\"#1AAB29\" stroke-width=\".5\"><\/circle><\/g><\/svg><\/span><span role=\"button\" tabindex=\"0\" data-code=\"yolo task=detect mode=predict model=yolov8n.pt source=&quot;test.png&quot;\" style=\"color:#d8dee9ff;display:none\" aria-label=\"Copy\" class=\"code-block-pro-copy-button\"><svg xmlns=\"http:\/\/www.w3.org\/2000\/svg\" style=\"width:24px;height:24px\" fill=\"none\" viewBox=\"0 0 24 24\" stroke=\"currentColor\" stroke-width=\"2\"><path class=\"with-check\" stroke-linecap=\"round\" stroke-linejoin=\"round\" d=\"M9 5H7a2 2 0 00-2 2v12a2 2 0 002 2h10a2 2 0 002-2V7a2 2 0 00-2-2h-2M9 5a2 2 0 002 2h2a2 2 0 002-2M9 5a2 2 0 012-2h2a2 2 0 012 2m-6 9l2 2 4-4\"><\/path><path class=\"without-check\" stroke-linecap=\"round\" stroke-linejoin=\"round\" d=\"M9 5H7a2 2 0 00-2 2v12a2 2 0 002 2h10a2 2 0 002-2V7a2 2 0 00-2-2h-2M9 5a2 2 0 002 2h2a2 2 0 002-2M9 5a2 2 0 012-2h2a2 2 0 012 2\"><\/path><\/svg><\/span><pre class=\"shiki nord\" style=\"background-color: #2e3440ff\" tabindex=\"0\"><code><span class=\"line\"><span style=\"color: #88C0D0\">yolo<\/span><span style=\"color: #D8DEE9FF\"> <\/span><span style=\"color: #A3BE8C\">task=detect<\/span><span style=\"color: #D8DEE9FF\"> <\/span><span style=\"color: #A3BE8C\">mode=predict<\/span><span style=\"color: #D8DEE9FF\"> <\/span><span style=\"color: #A3BE8C\">model=yolov8n.pt<\/span><span style=\"color: #D8DEE9FF\"> <\/span><span style=\"color: #A3BE8C\">source=<\/span><span style=\"color: #ECEFF4\">&quot;<\/span><span style=\"color: #A3BE8C\">test.png<\/span><span style=\"color: #ECEFF4\">&quot;<\/span><\/span><\/code><\/pre><\/div>\n\n\n\n<p id=\"84fb\"><strong>For Video<\/strong><\/p>\n\n\n\n<div class=\"wp-block-kevinbatdorf-code-block-pro\" data-code-block-pro-font-family=\"Code-Pro-JetBrains-Mono\" style=\"font-size:.875rem;font-family:Code-Pro-JetBrains-Mono,ui-monospace,SFMono-Regular,Menlo,Monaco,Consolas,monospace;line-height:1.25rem;--cbp-tab-width:2;tab-size:var(--cbp-tab-width, 2)\"><span style=\"display:block;padding:16px 0 0 16px;margin-bottom:-1px;width:100%;text-align:left;background-color:#2e3440ff\"><svg xmlns=\"http:\/\/www.w3.org\/2000\/svg\" width=\"54\" height=\"14\" viewBox=\"0 0 54 14\"><g fill=\"none\" fill-rule=\"evenodd\" transform=\"translate(1 1)\"><circle cx=\"6\" cy=\"6\" r=\"6\" fill=\"#FF5F56\" stroke=\"#E0443E\" stroke-width=\".5\"><\/circle><circle cx=\"26\" cy=\"6\" r=\"6\" fill=\"#FFBD2E\" stroke=\"#DEA123\" stroke-width=\".5\"><\/circle><circle cx=\"46\" cy=\"6\" r=\"6\" fill=\"#27C93F\" stroke=\"#1AAB29\" stroke-width=\".5\"><\/circle><\/g><\/svg><\/span><span role=\"button\" tabindex=\"0\" data-code=\"yolo task=detect mode=predict model=yolov8n.pt source=&quot;test.mp4&quot;\" style=\"color:#d8dee9ff;display:none\" aria-label=\"Copy\" class=\"code-block-pro-copy-button\"><svg xmlns=\"http:\/\/www.w3.org\/2000\/svg\" style=\"width:24px;height:24px\" fill=\"none\" viewBox=\"0 0 24 24\" stroke=\"currentColor\" stroke-width=\"2\"><path class=\"with-check\" stroke-linecap=\"round\" stroke-linejoin=\"round\" d=\"M9 5H7a2 2 0 00-2 2v12a2 2 0 002 2h10a2 2 0 002-2V7a2 2 0 00-2-2h-2M9 5a2 2 0 002 2h2a2 2 0 002-2M9 5a2 2 0 012-2h2a2 2 0 012 2m-6 9l2 2 4-4\"><\/path><path class=\"without-check\" stroke-linecap=\"round\" stroke-linejoin=\"round\" d=\"M9 5H7a2 2 0 00-2 2v12a2 2 0 002 2h10a2 2 0 002-2V7a2 2 0 00-2-2h-2M9 5a2 2 0 002 2h2a2 2 0 002-2M9 5a2 2 0 012-2h2a2 2 0 012 2\"><\/path><\/svg><\/span><pre class=\"shiki nord\" style=\"background-color: #2e3440ff\" tabindex=\"0\"><code><span class=\"line\"><span style=\"color: #88C0D0\">yolo<\/span><span style=\"color: #D8DEE9FF\"> <\/span><span style=\"color: #A3BE8C\">task=detect<\/span><span style=\"color: #D8DEE9FF\"> <\/span><span style=\"color: #A3BE8C\">mode=predict<\/span><span style=\"color: #D8DEE9FF\"> <\/span><span style=\"color: #A3BE8C\">model=yolov8n.pt<\/span><span style=\"color: #D8DEE9FF\"> <\/span><span style=\"color: #A3BE8C\">source=<\/span><span style=\"color: #ECEFF4\">&quot;<\/span><span style=\"color: #A3BE8C\">test.mp4<\/span><span style=\"color: #ECEFF4\">&quot;<\/span><\/span><\/code><\/pre><\/div>\n\n\n\n<p id=\"84fb\">You will get the results in the current directory inside the \u201cruns\/detect\/exp\u201d folder if everything works well.<\/p>\n\n\n\n<figure class=\"wp-block-image\"><img decoding=\"async\" src=\"https:\/\/miro.medium.com\/v2\/resize:fit:875\/1*FDV3ZV8BvPxD0QezoV_DwA.png\" alt=\"\"\/><figcaption class=\"wp-element-caption\"><strong>Fig-1.3: Pretrained Object Detection (Image from Author)<\/strong><\/figcaption><\/figure>\n\n\n\n<p id=\"ce0c\"><strong>Train YOLOv8 on Custom Data<\/strong><\/p>\n\n\n\n<p id=\"ec2d\">The steps for training a YOLOv8 object detection model on custom data can be summarized as follows,<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li><em>Collect data<\/em><\/li>\n\n\n\n<li><em>Label data<\/em><\/li>\n\n\n\n<li><em>Split data (train, test, and val)<\/em><\/li>\n\n\n\n<li><em>Creation of config files<\/em><\/li>\n\n\n\n<li><em>Start training<\/em><\/li>\n<\/ul>\n\n\n\n<p id=\"07a8\"><strong>Step-1: Collect Data<\/strong><\/p>\n\n\n\n<p id=\"16ca\">Create a dataset for&nbsp;<strong>YOLOv8 custom training.&nbsp;<\/strong>if you have no data<strong>,&nbsp;<\/strong>You can use the dataset from the&nbsp;<a href=\"https:\/\/storage.googleapis.com\/openimages\/web\/index.html\" rel=\"noreferrer noopener\" target=\"_blank\"><strong><em>openimages<\/em><\/strong><\/a>&nbsp;database or \ud83d\udc47<\/p>\n\n\n\n<p id=\"1603\">\u2b50 Create your own Data by reading the article&nbsp;<a href=\"https:\/\/medium.com\/nerd-for-tech\/extraction-of-frames-from-multiple-videos-3ddbced6f3c2\"><em>\u201cExtraction of a frame from videos\u201d<\/em><\/a><\/p>\n\n\n\n<blockquote class=\"wp-block-quote is-layout-flow wp-block-quote-is-layout-flow\">\n<p id=\"404c\">YOLOv8 takes label data in the text (.txt) file and has the following format:<\/p>\n<\/blockquote>\n\n\n\n<pre class=\"wp-block-preformatted\">&lt;object-class-id&gt; &lt;x&gt; &lt;y&gt; &lt;width&gt; &lt;height&gt;<\/pre>\n\n\n\n<p id=\"9bc4\"><strong>Step 2: Label Data<\/strong><\/p>\n\n\n\n<p id=\"08c4\">You can use the labelImg tool or&nbsp;<a href=\"http:\/\/roboflow.com\/as\" rel=\"noreferrer noopener\" target=\"_blank\">Roboflow platform<\/a>&nbsp;for data labeling, whatever suit your needs. If you want to understand the workflow of the labelImg tool, then\ud83d\udc47<\/p>\n\n\n\n<p id=\"bb7c\">\ud83d\udc49Don\u2019t forget to check out an article&nbsp;<a href=\"https:\/\/medium.com\/nerd-for-tech\/labeling-data-for-object-detection-yolo-5a4fa4f05844\"><strong><em>Labelling data for object detection (Yolo)<\/em><\/strong><\/a><strong><em>.<\/em><\/strong><\/p>\n\n\n\n<p id=\"ec63\"><strong>Step-3: Split Data (Train, Test, and Val)<\/strong><\/p>\n\n\n\n<p id=\"0fb4\">When you want to train a computer vision model on custom data, it\u2019s important to split your data into a training set and a test set. The training set is used to teach the model how to make predictions, while the test set is used to evaluate the accuracy of the model. The (80\u201320%) split ratio is a common one, but the exact ratio can depend on the size of your dataset and the specific task you\u2019re working on. For example, if you have a small dataset, you may want to use a higher percentage of it for training, while if you have a large dataset, you can afford to use a smaller percentage of it for training.<\/p>\n\n\n\n<p id=\"52e2\">\ud83d\udc49 For data splitting, you can take a look at&nbsp;<a href=\"https:\/\/pypi.org\/project\/split-folders\/\" rel=\"noreferrer noopener\" target=\"_blank\">split-folders<\/a>&nbsp;that will split your data randomly into the train, test, and validation.<\/p>\n\n\n\n<blockquote class=\"wp-block-quote is-layout-flow wp-block-quote-is-layout-flow\">\n<p id=\"7621\"><strong><em>Folder structure:<\/em><\/strong><\/p>\n<\/blockquote>\n\n\n\n<pre class=\"wp-block-preformatted\">\u251c\u2500\u2500 yolov8<br> ## \u2514\u2500\u2500 train<br> ####\u2514\u2500\u2500 images (folder including all training images)<br> ####\u2514\u2500\u2500 labels (folder including all training labels)<br> ## \u2514\u2500\u2500 test<br> ####\u2514\u2500\u2500 images (folder including all testing images)<br> ####\u2514\u2500\u2500 labels (folder including all testing labels)<br> ## \u2514\u2500\u2500 valid<br> ####\u2514\u2500\u2500 images (folder including all testing images)<br> ####\u2514\u2500\u2500 labels (folder including all testing labels)<\/pre>\n\n\n\n<p><\/p>\n\n\n\n<p><strong>Fig-1.4: So far, you have done good work learner. Just a few steps away from YOLOv8 Magic (Author Appreciation)<\/strong><\/p>\n\n\n\n<p id=\"f19c\"><strong>Step-4: Creation of Config Files<\/strong><\/p>\n\n\n\n<p id=\"7a00\">Creating a custom configuration file can be a helpful way to organize and store all of the important parameters for your computer vision model.<\/p>\n\n\n\n<p id=\"e4d0\">Create a file having the filename \u201ccustom. yaml\u201d, inside the current directory where you have opened a terminal\/(command prompt). Paste the below code in that file. set the correct path of the dataset folder, change the classes and their names, then save it.<\/p>\n\n\n\n<pre class=\"wp-block-preformatted\">path:  (dataset directory path)<br>train: (Complete path to dataset train folder)<br>test: (Complete path to dataset test folder) <br>valid: (Complete path to dataset valid folder)<br><br>#Classes<br>nc: 5# replace according to your number of classes<br><br>#classes names<br>#replace all class names list with your classes names<br>names: ['person', 'bicycle', 'car', 'motorcycle', 'airplane']<\/pre>\n\n\n\n<p id=\"e444\"><strong>Note:&nbsp;<\/strong>Make sure to set the correct path of training and testing directories, because the training process will totally dependent on that file.<\/p>\n\n\n\n<p id=\"52f1\"><strong>Step-5: Start Training<\/strong><\/p>\n\n\n\n<p id=\"a1a7\">Once you\u2019ve completed the preprocessing steps, such as data collection, data labeling, data splitting, and creating a custom configuration file, you can start training YOLOv8 on custom data by using mentioned command below in the terminal\/(command prompt).<\/p>\n\n\n\n<div class=\"wp-block-kevinbatdorf-code-block-pro\" data-code-block-pro-font-family=\"Code-Pro-JetBrains-Mono\" style=\"font-size:.875rem;font-family:Code-Pro-JetBrains-Mono,ui-monospace,SFMono-Regular,Menlo,Monaco,Consolas,monospace;line-height:1.25rem;--cbp-tab-width:2;tab-size:var(--cbp-tab-width, 2)\"><span style=\"display:block;padding:16px 0 0 16px;margin-bottom:-1px;width:100%;text-align:left;background-color:#2e3440ff\"><svg xmlns=\"http:\/\/www.w3.org\/2000\/svg\" width=\"54\" height=\"14\" viewBox=\"0 0 54 14\"><g fill=\"none\" fill-rule=\"evenodd\" transform=\"translate(1 1)\"><circle cx=\"6\" cy=\"6\" r=\"6\" fill=\"#FF5F56\" stroke=\"#E0443E\" stroke-width=\".5\"><\/circle><circle cx=\"26\" cy=\"6\" r=\"6\" fill=\"#FFBD2E\" stroke=\"#DEA123\" stroke-width=\".5\"><\/circle><circle cx=\"46\" cy=\"6\" r=\"6\" fill=\"#27C93F\" stroke=\"#1AAB29\" stroke-width=\".5\"><\/circle><\/g><\/svg><\/span><span role=\"button\" tabindex=\"0\" data-code=\"yolo task=detect mode=train model=yolov8n.pt data=custom.yaml epochs=3 imgsz=640\" style=\"color:#d8dee9ff;display:none\" aria-label=\"Copy\" class=\"code-block-pro-copy-button\"><svg xmlns=\"http:\/\/www.w3.org\/2000\/svg\" style=\"width:24px;height:24px\" fill=\"none\" viewBox=\"0 0 24 24\" stroke=\"currentColor\" stroke-width=\"2\"><path class=\"with-check\" stroke-linecap=\"round\" stroke-linejoin=\"round\" d=\"M9 5H7a2 2 0 00-2 2v12a2 2 0 002 2h10a2 2 0 002-2V7a2 2 0 00-2-2h-2M9 5a2 2 0 002 2h2a2 2 0 002-2M9 5a2 2 0 012-2h2a2 2 0 012 2m-6 9l2 2 4-4\"><\/path><path class=\"without-check\" stroke-linecap=\"round\" stroke-linejoin=\"round\" d=\"M9 5H7a2 2 0 00-2 2v12a2 2 0 002 2h10a2 2 0 002-2V7a2 2 0 00-2-2h-2M9 5a2 2 0 002 2h2a2 2 0 002-2M9 5a2 2 0 012-2h2a2 2 0 012 2\"><\/path><\/svg><\/span><pre class=\"shiki nord\" style=\"background-color: #2e3440ff\" tabindex=\"0\"><code><span class=\"line\"><span style=\"color: #88C0D0\">yolo<\/span><span style=\"color: #D8DEE9FF\"> <\/span><span style=\"color: #A3BE8C\">task=detect<\/span><span style=\"color: #D8DEE9FF\"> <\/span><span style=\"color: #A3BE8C\">mode=train<\/span><span style=\"color: #D8DEE9FF\"> <\/span><span style=\"color: #A3BE8C\">model=yolov8n.pt<\/span><span style=\"color: #D8DEE9FF\"> <\/span><span style=\"color: #A3BE8C\">data=custom.yaml<\/span><span style=\"color: #D8DEE9FF\"> <\/span><span style=\"color: #A3BE8C\">epochs=<\/span><span style=\"color: #B48EAD\">3<\/span><span style=\"color: #D8DEE9FF\"> <\/span><span style=\"color: #A3BE8C\">imgsz=<\/span><span style=\"color: #B48EAD\">640<\/span><\/span><\/code><\/pre><\/div>\n\n\n\n<p id=\"5cbb\"><strong>task<\/strong>&nbsp;= detect (It can be segment or classify)<\/p>\n\n\n\n<p id=\"1b88\"><strong>mode&nbsp;<\/strong>= train (It can be predict or val)<\/p>\n\n\n\n<p id=\"4ee7\"><strong>model<\/strong>&nbsp;= yolov8n.pt (It can yolov8s\/yolov8l\/yolov8x)<\/p>\n\n\n\n<p id=\"ae4d\"><strong>epochs<\/strong>&nbsp;= 3 (It can be any number)<\/p>\n\n\n\n<p id=\"886a\"><strong>imgsz<\/strong>&nbsp;= 640 (It can be 320, 416, etc, but make sure it needs to be a multiple of 32)<\/p>\n\n\n\n<figure class=\"wp-block-image\"><img decoding=\"async\" src=\"https:\/\/miro.medium.com\/v2\/resize:fit:875\/1*IVy0dYjC3UgplhIeq94zEg.jpeg\" alt=\"\"\/><figcaption class=\"wp-element-caption\"><strong>Fig-1.5: YOLOv8 Training on Custom Data<\/strong><\/figcaption><\/figure>\n\n\n\n<blockquote class=\"wp-block-quote is-layout-flow wp-block-quote-is-layout-flow\">\n<p id=\"572d\">YOLOv8 will not start training on custom data if any image is corrupt, If some label file will be corrupted so there will be no issue in training because YOLOv8 will ignore that (image and label) files.<\/p>\n<\/blockquote>\n\n\n\n<p id=\"0735\">\ud83d\udc49Wait for training to complete, and then do inference with newly created weights. Custom-trained weights will be saved in the folder path mentioned below.<\/p>\n\n\n\n<p id=\"a49b\"><strong><em>[runs\/train\/exp\/weights\/best.pt]<\/em><\/strong><\/p>\n\n\n\n<p id=\"0282\"><strong>Inference with Custom Weights<\/strong><\/p>\n\n\n\n<p id=\"1a45\">Once your model is trained, you can use it to make predictions on new data. Use the mentioned command below for detection with custom weights.<\/p>\n\n\n\n<div class=\"wp-block-kevinbatdorf-code-block-pro\" data-code-block-pro-font-family=\"Code-Pro-JetBrains-Mono\" style=\"font-size:.875rem;font-family:Code-Pro-JetBrains-Mono,ui-monospace,SFMono-Regular,Menlo,Monaco,Consolas,monospace;line-height:1.25rem;--cbp-tab-width:2;tab-size:var(--cbp-tab-width, 2)\"><span style=\"display:block;padding:16px 0 0 16px;margin-bottom:-1px;width:100%;text-align:left;background-color:#2e3440ff\"><svg xmlns=\"http:\/\/www.w3.org\/2000\/svg\" width=\"54\" height=\"14\" viewBox=\"0 0 54 14\"><g fill=\"none\" fill-rule=\"evenodd\" transform=\"translate(1 1)\"><circle cx=\"6\" cy=\"6\" r=\"6\" fill=\"#FF5F56\" stroke=\"#E0443E\" stroke-width=\".5\"><\/circle><circle cx=\"26\" cy=\"6\" r=\"6\" fill=\"#FFBD2E\" stroke=\"#DEA123\" stroke-width=\".5\"><\/circle><circle cx=\"46\" cy=\"6\" r=\"6\" fill=\"#27C93F\" stroke=\"#1AAB29\" stroke-width=\".5\"><\/circle><\/g><\/svg><\/span><span role=\"button\" tabindex=\"0\" data-code=\"yolo task=detect mode=predict model=&quot;runs\/train\/exp\/weights\/best.pt&quot; source=&quot;test.png&quot;\" style=\"color:#d8dee9ff;display:none\" aria-label=\"Copy\" class=\"code-block-pro-copy-button\"><svg xmlns=\"http:\/\/www.w3.org\/2000\/svg\" style=\"width:24px;height:24px\" fill=\"none\" viewBox=\"0 0 24 24\" stroke=\"currentColor\" stroke-width=\"2\"><path class=\"with-check\" stroke-linecap=\"round\" stroke-linejoin=\"round\" d=\"M9 5H7a2 2 0 00-2 2v12a2 2 0 002 2h10a2 2 0 002-2V7a2 2 0 00-2-2h-2M9 5a2 2 0 002 2h2a2 2 0 002-2M9 5a2 2 0 012-2h2a2 2 0 012 2m-6 9l2 2 4-4\"><\/path><path class=\"without-check\" stroke-linecap=\"round\" stroke-linejoin=\"round\" d=\"M9 5H7a2 2 0 00-2 2v12a2 2 0 002 2h10a2 2 0 002-2V7a2 2 0 00-2-2h-2M9 5a2 2 0 002 2h2a2 2 0 002-2M9 5a2 2 0 012-2h2a2 2 0 012 2\"><\/path><\/svg><\/span><pre class=\"shiki nord\" style=\"background-color: #2e3440ff\" tabindex=\"0\"><code><span class=\"line\"><span style=\"color: #88C0D0\">yolo<\/span><span style=\"color: #D8DEE9FF\"> <\/span><span style=\"color: #A3BE8C\">task=detect<\/span><span style=\"color: #D8DEE9FF\"> <\/span><span style=\"color: #A3BE8C\">mode=predict<\/span><span style=\"color: #D8DEE9FF\"> <\/span><span style=\"color: #A3BE8C\">model=<\/span><span style=\"color: #ECEFF4\">&quot;<\/span><span style=\"color: #A3BE8C\">runs\/train\/exp\/weights\/best.pt<\/span><span style=\"color: #ECEFF4\">&quot;<\/span><span style=\"color: #D8DEE9FF\"> <\/span><span style=\"color: #A3BE8C\">source=<\/span><span style=\"color: #ECEFF4\">&quot;<\/span><span style=\"color: #A3BE8C\">test.png<\/span><span style=\"color: #ECEFF4\">&quot;<\/span><\/span><\/code><\/pre><\/div>\n\n\n\n<p id=\"1a45\">or<\/p>\n\n\n\n<div class=\"wp-block-kevinbatdorf-code-block-pro\" data-code-block-pro-font-family=\"Code-Pro-JetBrains-Mono\" style=\"font-size:.875rem;font-family:Code-Pro-JetBrains-Mono,ui-monospace,SFMono-Regular,Menlo,Monaco,Consolas,monospace;line-height:1.25rem;--cbp-tab-width:2;tab-size:var(--cbp-tab-width, 2)\"><span style=\"display:block;padding:16px 0 0 16px;margin-bottom:-1px;width:100%;text-align:left;background-color:#2e3440ff\"><svg xmlns=\"http:\/\/www.w3.org\/2000\/svg\" width=\"54\" height=\"14\" viewBox=\"0 0 54 14\"><g fill=\"none\" fill-rule=\"evenodd\" transform=\"translate(1 1)\"><circle cx=\"6\" cy=\"6\" r=\"6\" fill=\"#FF5F56\" stroke=\"#E0443E\" stroke-width=\".5\"><\/circle><circle cx=\"26\" cy=\"6\" r=\"6\" fill=\"#FFBD2E\" stroke=\"#DEA123\" stroke-width=\".5\"><\/circle><circle cx=\"46\" cy=\"6\" r=\"6\" fill=\"#27C93F\" stroke=\"#1AAB29\" stroke-width=\".5\"><\/circle><\/g><\/svg><\/span><span role=\"button\" tabindex=\"0\" data-code=\"yolo task=detect mode=predict model=&quot;runs\/train\/exp\/weights\/best.pt&quot; source=&quot;test.mp4&quot; \" style=\"color:#d8dee9ff;display:none\" aria-label=\"Copy\" class=\"code-block-pro-copy-button\"><svg xmlns=\"http:\/\/www.w3.org\/2000\/svg\" style=\"width:24px;height:24px\" fill=\"none\" viewBox=\"0 0 24 24\" stroke=\"currentColor\" stroke-width=\"2\"><path class=\"with-check\" stroke-linecap=\"round\" stroke-linejoin=\"round\" d=\"M9 5H7a2 2 0 00-2 2v12a2 2 0 002 2h10a2 2 0 002-2V7a2 2 0 00-2-2h-2M9 5a2 2 0 002 2h2a2 2 0 002-2M9 5a2 2 0 012-2h2a2 2 0 012 2m-6 9l2 2 4-4\"><\/path><path class=\"without-check\" stroke-linecap=\"round\" stroke-linejoin=\"round\" d=\"M9 5H7a2 2 0 00-2 2v12a2 2 0 002 2h10a2 2 0 002-2V7a2 2 0 00-2-2h-2M9 5a2 2 0 002 2h2a2 2 0 002-2M9 5a2 2 0 012-2h2a2 2 0 012 2\"><\/path><\/svg><\/span><pre class=\"shiki nord\" style=\"background-color: #2e3440ff\" tabindex=\"0\"><code><span class=\"line\"><span style=\"color: #88C0D0\">yolo<\/span><span style=\"color: #D8DEE9FF\"> <\/span><span style=\"color: #A3BE8C\">task=detect<\/span><span style=\"color: #D8DEE9FF\"> <\/span><span style=\"color: #A3BE8C\">mode=predict<\/span><span style=\"color: #D8DEE9FF\"> <\/span><span style=\"color: #A3BE8C\">model=<\/span><span style=\"color: #ECEFF4\">&quot;<\/span><span style=\"color: #A3BE8C\">runs\/train\/exp\/weights\/best.pt<\/span><span style=\"color: #ECEFF4\">&quot;<\/span><span style=\"color: #D8DEE9FF\"> <\/span><span style=\"color: #A3BE8C\">source=<\/span><span style=\"color: #ECEFF4\">&quot;<\/span><span style=\"color: #A3BE8C\">test.mp4<\/span><span style=\"color: #ECEFF4\">&quot;<\/span><span style=\"color: #D8DEE9FF\"> <\/span><\/span><\/code><\/pre><\/div>\n\n\n\n<p id=\"f1e2\">I have used Person data for training, the results with custom weights are shown below.<\/p>\n\n\n\n<p><\/p>\n\n\n\n<p><\/p>\n\n\n\n<p><strong>Fig-1.6: YOLOv8 Trained on Custom Data (Live Dem<\/strong><\/p>\n\n\n\n<p id=\"daa3\"><em>That is all regarding&nbsp;<\/em><strong><em>\u201cTrain YOLOv8 on Custom Data\u201d<\/em><\/strong><em>. you can try this on your own data.<\/em><\/p>\n","protected":false},"excerpt":{"rendered":"<p>YOLOv8\ud83d\udd25has been released by Ultralytics on (10th, Jan 2023). It has provided advancements in computer vision that have brought about a massive novelty in the [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":11,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[3],"tags":[8,7],"class_list":["post-8","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-ai","tag-custom-model","tag-yolo"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v21.7 - https:\/\/yoast.com\/wordpress\/plugins\/seo\/ -->\n<title>Train YOLOv8 on Custom Data? - Farrukh&#039;s Tech Space<\/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:\/\/farrukhnaveed.co\/blogs\/train-yolov8-on-custom-data\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Train YOLOv8 on Custom Data? - Farrukh&#039;s Tech Space\" \/>\n<meta property=\"og:description\" content=\"YOLOv8\ud83d\udd25has been released by Ultralytics on (10th, Jan 2023). It has provided advancements in computer vision that have brought about a massive novelty in the [&hellip;]\" \/>\n<meta property=\"og:url\" content=\"https:\/\/farrukhnaveed.co\/blogs\/train-yolov8-on-custom-data\/\" \/>\n<meta property=\"og:site_name\" content=\"Farrukh&#039;s Tech Space\" \/>\n<meta property=\"article:published_time\" content=\"2023-06-12T17:07:57+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2023-09-13T17:30:08+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/farrukhnaveed.co\/blogs\/wp-content\/uploads\/2023\/06\/1_KihOlL8geuYB0XJ7uhMSew.gif\" \/>\n\t<meta property=\"og:image:width\" content=\"790\" \/>\n\t<meta property=\"og:image:height\" content=\"414\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/gif\" \/>\n<meta name=\"author\" content=\"Farrukh Naveed Anjum\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"Farrukh Naveed Anjum\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"6 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\/\/farrukhnaveed.co\/blogs\/train-yolov8-on-custom-data\/#article\",\"isPartOf\":{\"@id\":\"https:\/\/farrukhnaveed.co\/blogs\/train-yolov8-on-custom-data\/\"},\"author\":{\"name\":\"Farrukh Naveed Anjum\",\"@id\":\"https:\/\/farrukhnaveed.co\/blogs\/#\/schema\/person\/ce7d07e6a917b9b73aa79007a2357d29\"},\"headline\":\"Train YOLOv8 on Custom Data?\",\"datePublished\":\"2023-06-12T17:07:57+00:00\",\"dateModified\":\"2023-09-13T17:30:08+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\/\/farrukhnaveed.co\/blogs\/train-yolov8-on-custom-data\/\"},\"wordCount\":971,\"commentCount\":0,\"publisher\":{\"@id\":\"https:\/\/farrukhnaveed.co\/blogs\/#organization\"},\"keywords\":[\"Custom Model\",\"Yolo\"],\"articleSection\":[\"AI\"],\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"CommentAction\",\"name\":\"Comment\",\"target\":[\"https:\/\/farrukhnaveed.co\/blogs\/train-yolov8-on-custom-data\/#respond\"]}]},{\"@type\":\"WebPage\",\"@id\":\"https:\/\/farrukhnaveed.co\/blogs\/train-yolov8-on-custom-data\/\",\"url\":\"https:\/\/farrukhnaveed.co\/blogs\/train-yolov8-on-custom-data\/\",\"name\":\"Train YOLOv8 on Custom Data? - Farrukh&#039;s Tech Space\",\"isPartOf\":{\"@id\":\"https:\/\/farrukhnaveed.co\/blogs\/#website\"},\"datePublished\":\"2023-06-12T17:07:57+00:00\",\"dateModified\":\"2023-09-13T17:30:08+00:00\",\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/farrukhnaveed.co\/blogs\/train-yolov8-on-custom-data\/\"]}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/farrukhnaveed.co\/blogs\/#website\",\"url\":\"https:\/\/farrukhnaveed.co\/blogs\/\",\"name\":\"Farrukh Naveed Anjum Blogs\",\"description\":\"Empowering Software Architects with Knowledge on Big Data and AI\",\"publisher\":{\"@id\":\"https:\/\/farrukhnaveed.co\/blogs\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/farrukhnaveed.co\/blogs\/?s={search_term_string}\"},\"query-input\":\"required name=search_term_string\"}],\"inLanguage\":\"en-US\"},{\"@type\":\"Organization\",\"@id\":\"https:\/\/farrukhnaveed.co\/blogs\/#organization\",\"name\":\"Farrukh Naveed Anjum Blogs\",\"url\":\"https:\/\/farrukhnaveed.co\/blogs\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/farrukhnaveed.co\/blogs\/#\/schema\/logo\/image\/\",\"url\":\"https:\/\/farrukhnaveed.co\/blogs\/wp-content\/uploads\/2023\/06\/IMG_5018-scaled.jpg\",\"contentUrl\":\"https:\/\/farrukhnaveed.co\/blogs\/wp-content\/uploads\/2023\/06\/IMG_5018-scaled.jpg\",\"width\":1707,\"height\":2560,\"caption\":\"Farrukh Naveed Anjum Blogs\"},\"image\":{\"@id\":\"https:\/\/farrukhnaveed.co\/blogs\/#\/schema\/logo\/image\/\"}},{\"@type\":\"Person\",\"@id\":\"https:\/\/farrukhnaveed.co\/blogs\/#\/schema\/person\/ce7d07e6a917b9b73aa79007a2357d29\",\"name\":\"Farrukh Naveed Anjum\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/farrukhnaveed.co\/blogs\/#\/schema\/person\/image\/\",\"url\":\"https:\/\/secure.gravatar.com\/avatar\/bdf1af0d569259df562434e6dc99415a377c6fc053f9e1507aa34a6522561bb8?s=96&d=mm&r=g\",\"contentUrl\":\"https:\/\/secure.gravatar.com\/avatar\/bdf1af0d569259df562434e6dc99415a377c6fc053f9e1507aa34a6522561bb8?s=96&d=mm&r=g\",\"caption\":\"Farrukh Naveed Anjum\"},\"description\":\"Full Stack Developer and Software Architect with 14 years of experience in various domains, including Enterprise Resource Planning, Data Retrieval, Web Scraping, Real-Time Analytics, Cybersecurity, NLP, ED-Tech, and B2B Price Comparison\",\"sameAs\":[\"https:\/\/farrukhnaveed.co\/blog\"],\"url\":\"https:\/\/farrukhnaveed.co\/blogs\/author\/admin\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Train YOLOv8 on Custom Data? - Farrukh&#039;s Tech Space","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:\/\/farrukhnaveed.co\/blogs\/train-yolov8-on-custom-data\/","og_locale":"en_US","og_type":"article","og_title":"Train YOLOv8 on Custom Data? - Farrukh&#039;s Tech Space","og_description":"YOLOv8\ud83d\udd25has been released by Ultralytics on (10th, Jan 2023). It has provided advancements in computer vision that have brought about a massive novelty in the [&hellip;]","og_url":"https:\/\/farrukhnaveed.co\/blogs\/train-yolov8-on-custom-data\/","og_site_name":"Farrukh&#039;s Tech Space","article_published_time":"2023-06-12T17:07:57+00:00","article_modified_time":"2023-09-13T17:30:08+00:00","og_image":[{"url":"https:\/\/farrukhnaveed.co\/blogs\/wp-content\/uploads\/2023\/06\/1_KihOlL8geuYB0XJ7uhMSew.gif","width":790,"height":414,"type":"image\/gif"}],"author":"Farrukh Naveed Anjum","twitter_card":"summary_large_image","twitter_misc":{"Written by":"Farrukh Naveed Anjum","Est. reading time":"6 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/farrukhnaveed.co\/blogs\/train-yolov8-on-custom-data\/#article","isPartOf":{"@id":"https:\/\/farrukhnaveed.co\/blogs\/train-yolov8-on-custom-data\/"},"author":{"name":"Farrukh Naveed Anjum","@id":"https:\/\/farrukhnaveed.co\/blogs\/#\/schema\/person\/ce7d07e6a917b9b73aa79007a2357d29"},"headline":"Train YOLOv8 on Custom Data?","datePublished":"2023-06-12T17:07:57+00:00","dateModified":"2023-09-13T17:30:08+00:00","mainEntityOfPage":{"@id":"https:\/\/farrukhnaveed.co\/blogs\/train-yolov8-on-custom-data\/"},"wordCount":971,"commentCount":0,"publisher":{"@id":"https:\/\/farrukhnaveed.co\/blogs\/#organization"},"keywords":["Custom Model","Yolo"],"articleSection":["AI"],"inLanguage":"en-US","potentialAction":[{"@type":"CommentAction","name":"Comment","target":["https:\/\/farrukhnaveed.co\/blogs\/train-yolov8-on-custom-data\/#respond"]}]},{"@type":"WebPage","@id":"https:\/\/farrukhnaveed.co\/blogs\/train-yolov8-on-custom-data\/","url":"https:\/\/farrukhnaveed.co\/blogs\/train-yolov8-on-custom-data\/","name":"Train YOLOv8 on Custom Data? - Farrukh&#039;s Tech Space","isPartOf":{"@id":"https:\/\/farrukhnaveed.co\/blogs\/#website"},"datePublished":"2023-06-12T17:07:57+00:00","dateModified":"2023-09-13T17:30:08+00:00","inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/farrukhnaveed.co\/blogs\/train-yolov8-on-custom-data\/"]}]},{"@type":"WebSite","@id":"https:\/\/farrukhnaveed.co\/blogs\/#website","url":"https:\/\/farrukhnaveed.co\/blogs\/","name":"Farrukh Naveed Anjum Blogs","description":"Empowering Software Architects with Knowledge on Big Data and AI","publisher":{"@id":"https:\/\/farrukhnaveed.co\/blogs\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/farrukhnaveed.co\/blogs\/?s={search_term_string}"},"query-input":"required name=search_term_string"}],"inLanguage":"en-US"},{"@type":"Organization","@id":"https:\/\/farrukhnaveed.co\/blogs\/#organization","name":"Farrukh Naveed Anjum Blogs","url":"https:\/\/farrukhnaveed.co\/blogs\/","logo":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/farrukhnaveed.co\/blogs\/#\/schema\/logo\/image\/","url":"https:\/\/farrukhnaveed.co\/blogs\/wp-content\/uploads\/2023\/06\/IMG_5018-scaled.jpg","contentUrl":"https:\/\/farrukhnaveed.co\/blogs\/wp-content\/uploads\/2023\/06\/IMG_5018-scaled.jpg","width":1707,"height":2560,"caption":"Farrukh Naveed Anjum Blogs"},"image":{"@id":"https:\/\/farrukhnaveed.co\/blogs\/#\/schema\/logo\/image\/"}},{"@type":"Person","@id":"https:\/\/farrukhnaveed.co\/blogs\/#\/schema\/person\/ce7d07e6a917b9b73aa79007a2357d29","name":"Farrukh Naveed Anjum","image":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/farrukhnaveed.co\/blogs\/#\/schema\/person\/image\/","url":"https:\/\/secure.gravatar.com\/avatar\/bdf1af0d569259df562434e6dc99415a377c6fc053f9e1507aa34a6522561bb8?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/bdf1af0d569259df562434e6dc99415a377c6fc053f9e1507aa34a6522561bb8?s=96&d=mm&r=g","caption":"Farrukh Naveed Anjum"},"description":"Full Stack Developer and Software Architect with 14 years of experience in various domains, including Enterprise Resource Planning, Data Retrieval, Web Scraping, Real-Time Analytics, Cybersecurity, NLP, ED-Tech, and B2B Price Comparison","sameAs":["https:\/\/farrukhnaveed.co\/blog"],"url":"https:\/\/farrukhnaveed.co\/blogs\/author\/admin\/"}]}},"_links":{"self":[{"href":"https:\/\/farrukhnaveed.co\/blogs\/wp-json\/wp\/v2\/posts\/8","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/farrukhnaveed.co\/blogs\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/farrukhnaveed.co\/blogs\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/farrukhnaveed.co\/blogs\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/farrukhnaveed.co\/blogs\/wp-json\/wp\/v2\/comments?post=8"}],"version-history":[{"count":6,"href":"https:\/\/farrukhnaveed.co\/blogs\/wp-json\/wp\/v2\/posts\/8\/revisions"}],"predecessor-version":[{"id":91,"href":"https:\/\/farrukhnaveed.co\/blogs\/wp-json\/wp\/v2\/posts\/8\/revisions\/91"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/farrukhnaveed.co\/blogs\/wp-json\/wp\/v2\/media\/11"}],"wp:attachment":[{"href":"https:\/\/farrukhnaveed.co\/blogs\/wp-json\/wp\/v2\/media?parent=8"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/farrukhnaveed.co\/blogs\/wp-json\/wp\/v2\/categories?post=8"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/farrukhnaveed.co\/blogs\/wp-json\/wp\/v2\/tags?post=8"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}