{"id":1794,"date":"2019-04-04T20:04:38","date_gmt":"2019-04-04T20:04:38","guid":{"rendered":"https:\/\/blogs.mathworks.com\/deep-learning\/?p=1794"},"modified":"2021-04-06T15:51:01","modified_gmt":"2021-04-06T19:51:01","slug":"whats-new-in-r2019a-features","status":"publish","type":"post","link":"https:\/\/blogs.mathworks.com\/deep-learning\/2019\/04\/04\/whats-new-in-r2019a-features\/","title":{"rendered":"What&#8217;s new in R2019a: Features"},"content":{"rendered":"<span style=\"font-size: 14px;\">Welcome again to R2019a! There\u2019s a new release of MATLAB out right now. Last post, we covered a bunch of <a href=\"https:\/\/blogs.mathworks.com\/deep-learning\/2019\/03\/27\/whats-new-r2019a-examples\/\">new 19a examples<\/a>, and today's post will dive into the specifics of new deep learning features. <\/span>\r\n<h6><\/h6>\r\n<span style=\"font-size: 14px;\">Please note: this is primarily for deep learning features, and\u00a0<\/span><span style=\"font-size: 14px;\">this list isn\u2019t comprehensive. (Think of this as \u201cJohanna\u2019s list of favorite new features.\u201d). If you think I forgot something important, please leave a comment below!<\/span><!--more-->\r\n<h6><\/h6>\r\n<span style=\"font-size: 16px; color: #2f5ba3;\"><strong>New Deep Learning Features:<\/strong><\/span>\r\n<h6><\/h6>\r\n<span style=\"font-size: 16px; color: #0a295b;\"><strong>#1. <\/strong><\/span><span style=\"font-size: 15px; color: #0a295b;\">Signal Labeling App<\/span>\r\n<h6><\/h6>\r\n<span style=\"font-size: 14px;\">Signal Labeler is the latest app to join our collection of labeling apps, including ground truth labeler, video labeler, image labeler, and audio labeler.<\/span>\r\n<h6><\/h6>\r\n<ul>\r\n \t<li><a href=\"https:\/\/www.mathworks.com\/help\/signal\/ref\/signallabeler.html\">More on Signal Labeler<\/a><\/li>\r\n<\/ul>\r\n<img decoding=\"async\" loading=\"lazy\" class=\"aligncenter wp-image-1888 size-medium\" src=\"https:\/\/blogs.mathworks.com\/deep-learning\/files\/2019\/04\/WhaleSongLabelingExample_04-300x206.png\" alt=\"\" width=\"300\" height=\"206\" \/>\r\n\r\n<span style=\"font-size: 16px; color: #0a295b;\"><strong>#2. <\/strong><\/span> <span style=\"font-size: 15px; color: #0a295b;\">YOLO v2<\/span>\r\n<h6><\/h6>\r\n<span style=\"font-size: 14px;\">Hurray! Yolo v2 is here! Train a \u201cyou-only-look-once\u201d object detector AND generate CUDA code from the MATLAB code.*<\/span>\r\n<h6><\/h6>\r\n<ul>\r\n \t<li><a href=\"https:\/\/www.mathworks.com\/help\/vision\/ug\/yolo-v2-basics.html\">More on Yolo v2 concepts<\/a><\/li>\r\n<\/ul>\r\n<div id=\"attachment_1894\" style=\"width: 643px\" class=\"wp-caption alignnone\"><img aria-describedby=\"caption-attachment-1894\" decoding=\"async\" loading=\"lazy\" class=\"wp-image-1894 size-full\" src=\"https:\/\/blogs.mathworks.com\/deep-learning\/files\/2019\/04\/yolo_model.png\" alt=\"\" width=\"633\" height=\"159\" \/><p id=\"caption-attachment-1894\" class=\"wp-caption-text\">I pulled this image directly from the documentation link above. It's a great page introducing the basics of this algorithm.<\/p><\/div>\r\n<h6><\/h6>\r\n<span style=\"font-size: 16px; color: #0a295b;\"><strong>#3. <\/strong><\/span> <span style=\"font-size: 15px; color: #0a295b;\">Deep learning for videos<\/span>\r\n<h6><\/h6>\r\n<span style=\"font-size: 14px;\">Combine LSTM and convolutional layers for video classification and gesture recognition.<\/span>\r\n<h6><\/h6>\r\n<ul>\r\n \t<li><a href=\"https:\/\/www.mathworks.com\/help\/deeplearning\/examples\/classify-videos-using-deep-learning.html\">More on deep learning video classification<\/a><\/li>\r\n<\/ul>\r\n<span style=\"font-size: 16px; color: #0a295b;\"><strong>#4. <\/strong><\/span> <span style=\"font-size: 15px; color: #0a295b;\">Deep Learning on NVIDIA GPU Cloud and DGX<\/span>\r\n<h6><\/h6>\r\n<span style=\"font-size: 14px;\">Bring MATLAB with you to the cloud or GPU clusters using NVIDIA\u2019s docker container. A video on how to get this set up can be found here, and documentation is below.<\/span>\r\n<h6><\/h6>\r\n<ul>\r\n \t<li style=\"list-style-type: none;\">\r\n<ul>\r\n \t<li><a href=\"https:\/\/www.mathworks.com\/videos\/setting-up-the-matlab-deep-learning-container-on-ngc-1537515024196.html\">Video on setting up MATLAB Container<\/a><\/li>\r\n \t<li><a href=\"https:\/\/www.mathworks.com\/help\/cloudcenter\/ug\/matlab-deep-learning-container-on-dgx.html\">MATLAB Documentation on NGC<\/a><\/li>\r\n<\/ul>\r\n<\/li>\r\n<\/ul>\r\n<span style=\"font-size: 16px; color: #0a295b;\"><strong>#5. <\/strong><\/span> <span style=\"font-size: 15px; color: #0a295b;\">New pretrained models<\/span>\r\n<h6><\/h6>\r\n<span style=\"font-size: 14px;\"> You can now use MobileNet-v2, Inception-ResNet-v2, Xception, and SqueezeNet, to name a few.\r\n<\/span>\r\n<h6><\/h6>\r\n<ul>\r\n \t<li><a href=\"https:\/\/www.mathworks.com\/solutions\/deep-learning\/models.html\">See a full list of pretrained models<\/a><\/li>\r\n<\/ul>\r\n<div id=\"attachment_1900\" style=\"width: 1034px\" class=\"wp-caption alignnone\"><img aria-describedby=\"caption-attachment-1900\" decoding=\"async\" loading=\"lazy\" class=\"wp-image-1900 size-large\" src=\"https:\/\/blogs.mathworks.com\/deep-learning\/files\/2019\/04\/pretrained_networks_comb_gpu64-1024x576.png\" alt=\"\" width=\"1024\" height=\"576\" \/><p id=\"caption-attachment-1900\" class=\"wp-caption-text\">\u00a0A new documentation page visualizes pretrained networks' speed, size and accuracy<\/p><\/div>\r\n\r\n<span style=\"font-size: 16px; color: #0a295b;\"><strong>#6. <\/strong><\/span> <span style=\"font-size: 15px; color: #0a295b;\">Deep learning for 3-D image data<\/span>\r\n<h6><\/h6>\r\n<span style=\"font-size: 14px;\">Over 20 deep learning layers support 3D data, semantic segmentation workflows work in 3D, and a new example walking through segmenting a brain in 3D is below.<\/span>\r\n<h6><\/h6>\r\n<ul>\r\n \t<li><a href=\"https:\/\/www.mathworks.com\/help\/deeplearning\/examples\/segment-3d-brain-tumor-using-deep-learning.html\">More on 3D Deep Learning<\/a><\/li>\r\n<\/ul>\r\n<span style=\"font-size: 16px; color: #0a295b;\"><strong>#7. <\/strong><\/span> <span style=\"font-size: 15px; color: #0a295b;\">(advanced) Custom layers with multiple inputs and outputs<\/span>\r\n<h6><\/h6>\r\n<span style=\"font-size: 14px;\">We\u2019ve been investing in more advanced features for deep learning for the last few releases, so it feels right to add one new advanced feature. While defining your own custom layer is an advanced maneuver, it may be important to implement networks from research papers, since a lot of networks in literature become quite complex.<\/span>\r\n\r\n&nbsp;\r\n\r\n<div id=\"attachment_1912\" style=\"width: 610px\" class=\"wp-caption alignnone\"><img aria-describedby=\"caption-attachment-1912\" decoding=\"async\" loading=\"lazy\" class=\"wp-image-1912 size-full\" src=\"https:\/\/blogs.mathworks.com\/deep-learning\/files\/2019\/04\/custom_layer_flow2.png\" alt=\"\" width=\"600\" height=\"137\" \/><p id=\"caption-attachment-1912\" class=\"wp-caption-text\">Showing intermediate custom layer architecture<\/p><\/div>\r\n<h6><\/h6>\r\n<ul>\r\n \t<li>You can find more information on custom layers <a href=\"https:\/\/www.mathworks.com\/help\/deeplearning\/ug\/define-custom-deep-learning-layers.html\">here<\/a><\/li>\r\n \t<li>And custom layers with multiple inputs <a href=\"https:\/\/www.mathworks.com\/help\/deeplearning\/ug\/define-custom-layer-with-multiple-inputs.html\">here<\/a><\/li>\r\n<\/ul>\r\n<h6><\/h6>\r\n\r\n<hr \/>\r\n\r\n<span style=\"font-size: 14px;\">I'm always curious how you learn about new features and functionality. Do you watch <\/span><a href=\"https:\/\/www.mathworks.com\/products\/new_products\/latest_features.html\">Gabriel's video<\/a>? <span style=\"font-size: 14px;\">Read the documentation? Let me know in the comments below.<\/span>\r\n<h6><\/h6>\r\n*YOLO v2 CUDA Code generation is available with GPU Coder\r\n<h6><\/h6>\r\n<p><a href=\"https:\/\/twitter.com\/jo_pings?ref_src=twsrc%5Etfw\" class=\"twitter-follow-button\" data-size=\"large\" data-show-count=\"false\">Follow @jo_pings<\/a><script async src=\"https:\/\/platform.twitter.com\/widgets.js\" charset=\"utf-8\"><\/script><\/p>","protected":false},"excerpt":{"rendered":"<div class=\"overview-image\"><img decoding=\"async\"  class=\"img-responsive\" src=\"https:\/\/blogs.mathworks.com\/deep-learning\/files\/2019\/04\/WhaleSongLabelingExample_04-300x206.png\" onError=\"this.style.display ='none';\" \/><\/div><p>Welcome again to R2019a! There\u2019s a new release of MATLAB out right now. Last post, we covered a bunch of new 19a examples, and today's post will dive into the specifics of new deep learning features.... <a class=\"read-more\" href=\"https:\/\/blogs.mathworks.com\/deep-learning\/2019\/04\/04\/whats-new-in-r2019a-features\/\">read more >><\/a><\/p>","protected":false},"author":156,"featured_media":0,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":[],"categories":[9],"tags":[],"_links":{"self":[{"href":"https:\/\/blogs.mathworks.com\/deep-learning\/wp-json\/wp\/v2\/posts\/1794"}],"collection":[{"href":"https:\/\/blogs.mathworks.com\/deep-learning\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/blogs.mathworks.com\/deep-learning\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/blogs.mathworks.com\/deep-learning\/wp-json\/wp\/v2\/users\/156"}],"replies":[{"embeddable":true,"href":"https:\/\/blogs.mathworks.com\/deep-learning\/wp-json\/wp\/v2\/comments?post=1794"}],"version-history":[{"count":66,"href":"https:\/\/blogs.mathworks.com\/deep-learning\/wp-json\/wp\/v2\/posts\/1794\/revisions"}],"predecessor-version":[{"id":1936,"href":"https:\/\/blogs.mathworks.com\/deep-learning\/wp-json\/wp\/v2\/posts\/1794\/revisions\/1936"}],"wp:attachment":[{"href":"https:\/\/blogs.mathworks.com\/deep-learning\/wp-json\/wp\/v2\/media?parent=1794"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/blogs.mathworks.com\/deep-learning\/wp-json\/wp\/v2\/categories?post=1794"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/blogs.mathworks.com\/deep-learning\/wp-json\/wp\/v2\/tags?post=1794"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}