{"id":226903,"date":"2019-09-24T18:44:47","date_gmt":"2019-09-24T10:44:47","guid":{"rendered":"http:\/\/magicalbits.net\/?p=226903"},"modified":"2019-09-24T18:44:47","modified_gmt":"2019-09-24T10:44:47","slug":"facebook-model-pretrained-on-billions-of-instagram-hashtags-achieves-sota-results-on-top-1-imagenet","status":"publish","type":"post","link":"https:\/\/magicalbits.net\/?p=226903","title":{"rendered":"Facebook Model Pretrained on Billions of Instagram Hashtags Achieves SOTA Results on Top-1 ImageNet"},"content":{"rendered":"<blockquote><p>Pretraining models on the ImageNet dataset has been a mainstream research approach for years, but in today\u2019s digital world where data is growing by orders of magnitude the 10 year-old ImageNet dataset is now considered relatively small in size. That motivated Facebook to explore how pretraining a machine learning model on a large-scale, weakly-supervised dataset could impact model performance.<\/p><\/blockquote>\n<p>Source: <em><a href=\"https:\/\/medium.com\/syncedreview\/facebook-model-pretrained-on-billions-of-instagram-hashtags-achieves-sota-results-on-top-1-imagenet-ae8113bb3145\">Facebook Model Pretrained on Billions of Instagram Hashtags Achieves SOTA Results on Top-1 ImageNet<\/a><\/em><\/p>\n<p>Model available in PyTorch, link at the bottom.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Pretraining models on the ImageNet dataset has been a mainstream research approach for years, but in today\u2019s digital world where data is growing by orders of magnitude the 10 year-old ImageNet dataset is now considered relatively small in size. That motivated Facebook to explore how pretraining a machine learning model on a large-scale, weakly-supervised dataset [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"ep_exclude_from_search":false,"_jetpack_memberships_contains_paid_content":false,"footnotes":""},"categories":[1],"tags":[],"class_list":["post-226903","post","type-post","status-publish","format-standard","hentry","category-uncategorised"],"jetpack_featured_media_url":"","jetpack-related-posts":[],"jetpack_sharing_enabled":true,"_links":{"self":[{"href":"https:\/\/magicalbits.net\/index.php?rest_route=\/wp\/v2\/posts\/226903","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/magicalbits.net\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/magicalbits.net\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/magicalbits.net\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/magicalbits.net\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=226903"}],"version-history":[{"count":1,"href":"https:\/\/magicalbits.net\/index.php?rest_route=\/wp\/v2\/posts\/226903\/revisions"}],"predecessor-version":[{"id":226904,"href":"https:\/\/magicalbits.net\/index.php?rest_route=\/wp\/v2\/posts\/226903\/revisions\/226904"}],"wp:attachment":[{"href":"https:\/\/magicalbits.net\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=226903"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/magicalbits.net\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=226903"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/magicalbits.net\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=226903"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}