{"id":91993,"date":"2025-01-09T03:54:35","date_gmt":"2025-01-09T00:24:35","guid":{"rendered":"https:\/\/nabfollower.com\/blog\/cococaptions-in-pytorch-2-4fb3\/"},"modified":"2025-01-09T03:54:35","modified_gmt":"2025-01-09T00:24:35","slug":"cococaptions-in-pytorch-2-4fb3","status":"publish","type":"post","link":"https:\/\/nabfollower.com\/blog\/cococaptions-in-pytorch-2-4fb3\/","title":{"rendered":"CocoCaptions \u062f\u0631 PyTorch (2) &#8211; \u0627\u0646\u062c\u0645\u0646 DEV"},"content":{"rendered":"<div data-article-id=\"2196379\" id=\"article-body\">\n<p>\u0628\u0631\u0627\u06cc \u0645\u0646 \u06cc\u06a9 \u0642\u0647\u0648\u0647 \u0628\u062e\u0631\u2615<\/p>\n<p>*\u06cc\u0627\u062f\u062f\u0627\u0634\u062a \u0647\u0627:<\/p>\n<ul>\n<li>\n<p>\u067e\u0633\u062a \u0645\u0646 \u0628\u0627 \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u0627\u0632 CocoCaptions () \u062a\u0648\u0636\u06cc\u062d \u0645\u06cc \u062f\u0647\u062f <code>train2014<\/code> \u0628\u0627 <code>captions_train2014.json<\/code>\u060c <code>instances_train2014.json<\/code> \u0648 <code>person_keypoints_train2014.json<\/code>\u060c <code>val2014<\/code> \u0628\u0627 <code>captions_val2014.json<\/code>\u060c <code>instances_val2014.json<\/code> \u0648 <code>person_keypoints_val2014.json<\/code> \u0648 <code>test2017<\/code> \u0628\u0627 <code>image_info_test2014.json<\/code>\u060c <code>image_info_test2015.json<\/code> \u0648 <code>image_info_test-dev2015.json<\/code>.<\/li>\n<li>\n<p>\u067e\u0633\u062a \u0645\u0646 \u0628\u0627 \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u0627\u0632 CocoCaptions () \u062a\u0648\u0636\u06cc\u062d \u0645\u06cc \u062f\u0647\u062f <code>train2017<\/code> \u0628\u0627 <code>stuff_train2017.json<\/code>\u060c <code>val2017<\/code> \u0628\u0627 <code>stuff_val2017.json<\/code>\u060c <code>stuff_train2017_pixelmaps<\/code> \u0628\u0627 <code>stuff_train2017.json<\/code>\u060c <code>stuff_val2017_pixelmaps<\/code> \u0628\u0627 <code>stuff_val2017.json<\/code>\u060c <code>panoptic_train2017<\/code> \u0628\u0627 <code>panoptic_train2017.json<\/code>\u060c <code>panoptic_val2017<\/code> \u0628\u0627 <code>panoptic_val2017.json<\/code> \u0648 <code>unlabeled2017<\/code> \u0628\u0627 <code>image_info_unlabeled2017.json<\/code>.<\/li>\n<li>\n<p>\u067e\u0633\u062a \u0645\u0646 \u0628\u0627 \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u0627\u0632 CocoDetection() \u062a\u0648\u0636\u06cc\u062d \u0645\u06cc \u062f\u0647\u062f <code>train2014<\/code> \u0628\u0627 <code>captions_train2014.json<\/code>\u060c <code>instances_train2014.json<\/code> \u0648 <code>person_keypoints_train2014.json<\/code>\u060c <code>val2014<\/code> \u0628\u0627 <code>captions_val2014.json<\/code>\u060c <code>instances_val2014.json<\/code> \u0648 <code>person_keypoints_val2014.json<\/code> \u0648 <code>test2017<\/code> \u0628\u0627 <code>image_info_test2014.json<\/code>\u060c <code>image_info_test2015.json<\/code> \u0648 <code>image_info_test-dev2015.json<\/code>.<\/li>\n<li>\n<p>\u067e\u0633\u062a \u0645\u0646 \u0628\u0627 \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u0627\u0632 CocoDetection() \u062a\u0648\u0636\u06cc\u062d \u0645\u06cc \u062f\u0647\u062f <code>train2017<\/code> \u0628\u0627 <code>captions_train2017.json<\/code>\u060c <code>instances_train2017.json<\/code> \u0648 <code>person_keypoints_train2017.json<\/code>\u060c <code>val2017<\/code> \u0628\u0627 <code>captions_val2017.json<\/code>\u060c <code>instances_val2017.json<\/code> \u0648 <code>person_keypoints_val2017.json<\/code> \u0648 <code>test2017<\/code> \u0628\u0627 <code>image_info_test2017.json<\/code> \u0648 <code>image_info_test-dev2017.json<\/code>.<\/li>\n<li>\n<p>\u067e\u0633\u062a \u0645\u0646 \u0628\u0627 \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u0627\u0632 CocoDetection() \u062a\u0648\u0636\u06cc\u062d \u0645\u06cc \u062f\u0647\u062f <code>train2017<\/code> \u0628\u0627 <code>stuff_train2017.json<\/code>\u060c <code>val2017<\/code> \u0628\u0627 <code>stuff_val2017.json<\/code>\u060c <code>stuff_train2017_pixelmaps<\/code> \u0628\u0627 <code>stuff_train2017.json<\/code>\u060c <code>stuff_val2017_pixelmaps<\/code> \u0628\u0627 <code>stuff_val2017.json<\/code>\u060c <code>panoptic_train2017<\/code> \u0628\u0627 <code>panoptic_train2017.json<\/code>\u060c <code>panoptic_val2017<\/code> \u0628\u0627 <code>panoptic_val2017.json<\/code> \u0648 <code>unlabeled2017<\/code> \u0628\u0627 <code>image_info_unlabeled2017.json<\/code>.<\/li>\n<li>\n<p>\u067e\u0633\u062a \u0645\u0646 MS COCO \u0631\u0627 \u062a\u0648\u0636\u06cc\u062d \u0645\u06cc \u062f\u0647\u062f.<\/li>\n<\/ul>\n<p>CocoCaptions() \u0645\u06cc \u062a\u0648\u0627\u0646\u062f \u0627\u0632 \u0645\u062c\u0645\u0648\u0639\u0647 \u062f\u0627\u062f\u0647 MS COCO \u0647\u0645\u0627\u0646\u0637\u0648\u0631 \u06a9\u0647 \u062f\u0631 \u0632\u06cc\u0631 \u0646\u0634\u0627\u0646 \u062f\u0627\u062f\u0647 \u0634\u062f\u0647 \u0627\u0633\u062a \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u06a9\u0646\u062f. *\u0627\u06cc\u0646 \u0628\u0631\u0627\u06cc <code>train2017<\/code> \u0628\u0627 <code>captions_train2017.json<\/code>\u060c <code>instances_train2017.json<\/code> \u0648 <code>person_keypoints_train2017.json<\/code>\u060c <code>val2017<\/code> \u0628\u0627 <code>captions_val2017.json<\/code>\u060c <code>instances_val2017.json<\/code> \u0648 <code>person_keypoints_val2017.json<\/code> \u0648 <code>test2017<\/code> \u0628\u0627 <code>image_info_test2017.json<\/code> \u0648 <code>image_info_test-dev2017.json<\/code>:<\/p>\n<div class=\"highlight js-code-highlight\">\n<pre class=\"highlight python\"><code><span class=\"kn\">from<\/span> <span class=\"n\">torchvision.datasets<\/span> <span class=\"kn\">import<\/span> <span class=\"n\">CocoCaptions<\/span>\n\n<span class=\"n\">cap_train2017_data<\/span> <span class=\"o\">=<\/span> <span class=\"nc\">CocoCaptions<\/span><span class=\"p\">(<\/span>\n    <span class=\"n\">root<\/span><span class=\"o\">=<\/span><span class=\"sh\">\"<\/span><span class=\"s\">data\/coco\/imgs\/train2017<\/span><span class=\"sh\">\"<\/span><span class=\"p\">,<\/span>\n    <span class=\"n\">annFile<\/span><span class=\"o\">=<\/span><span class=\"sh\">\"<\/span><span class=\"s\">data\/coco\/anns\/trainval2017\/captions_train2017.json<\/span><span class=\"sh\">\"<\/span>\n<span class=\"p\">)<\/span>\n\n<span class=\"n\">ins_train2017_data<\/span> <span class=\"o\">=<\/span> <span class=\"nc\">CocoCaptions<\/span><span class=\"p\">(<\/span>\n    <span class=\"n\">root<\/span><span class=\"o\">=<\/span><span class=\"sh\">\"<\/span><span class=\"s\">data\/coco\/imgs\/train2017<\/span><span class=\"sh\">\"<\/span><span class=\"p\">,<\/span>\n    <span class=\"n\">annFile<\/span><span class=\"o\">=<\/span><span class=\"sh\">\"<\/span><span class=\"s\">data\/coco\/anns\/trainval2017\/instances_train2017.json<\/span><span class=\"sh\">\"<\/span>\n<span class=\"p\">)<\/span>\n\n<span class=\"n\">pk_train2017_data<\/span> <span class=\"o\">=<\/span> <span class=\"nc\">CocoCaptions<\/span><span class=\"p\">(<\/span>\n    <span class=\"n\">root<\/span><span class=\"o\">=<\/span><span class=\"sh\">\"<\/span><span class=\"s\">data\/coco\/imgs\/train2017<\/span><span class=\"sh\">\"<\/span><span class=\"p\">,<\/span>\n    <span class=\"n\">annFile<\/span><span class=\"o\">=<\/span><span class=\"sh\">\"<\/span><span class=\"s\">data\/coco\/anns\/trainval2017\/person_keypoints_train2017.json<\/span><span class=\"sh\">\"<\/span>\n<span class=\"p\">)<\/span>\n\n<span class=\"nf\">len<\/span><span class=\"p\">(<\/span><span class=\"n\">cap_train2017_data<\/span><span class=\"p\">),<\/span> <span class=\"nf\">len<\/span><span class=\"p\">(<\/span><span class=\"n\">ins_train2017_data<\/span><span class=\"p\">),<\/span> <span class=\"nf\">len<\/span><span class=\"p\">(<\/span><span class=\"n\">pk_train2017_data<\/span><span class=\"p\">)<\/span>\n<span class=\"c1\"># (118287, 118287, 118287)\n<\/span>\n<span class=\"n\">cap_val2017_data<\/span> <span class=\"o\">=<\/span> <span class=\"nc\">CocoCaptions<\/span><span class=\"p\">(<\/span>\n    <span class=\"n\">root<\/span><span class=\"o\">=<\/span><span class=\"sh\">\"<\/span><span class=\"s\">data\/coco\/imgs\/val2017<\/span><span class=\"sh\">\"<\/span><span class=\"p\">,<\/span>\n    <span class=\"n\">annFile<\/span><span class=\"o\">=<\/span><span class=\"sh\">\"<\/span><span class=\"s\">data\/coco\/anns\/trainval2017\/captions_val2017.json<\/span><span class=\"sh\">\"<\/span>\n<span class=\"p\">)<\/span>\n\n<span class=\"n\">ins_val2017_data<\/span> <span class=\"o\">=<\/span> <span class=\"nc\">CocoCaptions<\/span><span class=\"p\">(<\/span>\n    <span class=\"n\">root<\/span><span class=\"o\">=<\/span><span class=\"sh\">\"<\/span><span class=\"s\">data\/coco\/imgs\/val2017<\/span><span class=\"sh\">\"<\/span><span class=\"p\">,<\/span>\n    <span class=\"n\">annFile<\/span><span class=\"o\">=<\/span><span class=\"sh\">\"<\/span><span class=\"s\">data\/coco\/anns\/trainval2017\/instances_val2017.json<\/span><span class=\"sh\">\"<\/span>\n<span class=\"p\">)<\/span>\n\n<span class=\"n\">pk_val2017_data<\/span> <span class=\"o\">=<\/span> <span class=\"nc\">CocoCaptions<\/span><span class=\"p\">(<\/span>\n    <span class=\"n\">root<\/span><span class=\"o\">=<\/span><span class=\"sh\">\"<\/span><span class=\"s\">data\/coco\/imgs\/val2017<\/span><span class=\"sh\">\"<\/span><span class=\"p\">,<\/span>\n    <span class=\"n\">annFile<\/span><span class=\"o\">=<\/span><span class=\"sh\">\"<\/span><span class=\"s\">data\/coco\/anns\/trainval2017\/person_keypoints_val2017.json<\/span><span class=\"sh\">\"<\/span>\n<span class=\"p\">)<\/span>\n\n<span class=\"nf\">len<\/span><span class=\"p\">(<\/span><span class=\"n\">cap_val2017_data<\/span><span class=\"p\">),<\/span> <span class=\"nf\">len<\/span><span class=\"p\">(<\/span><span class=\"n\">ins_val2017_data<\/span><span class=\"p\">),<\/span> <span class=\"nf\">len<\/span><span class=\"p\">(<\/span><span class=\"n\">pk_val2017_data<\/span><span class=\"p\">)<\/span>\n<span class=\"c1\"># (5000, 5000, 5000)\n<\/span>\n<span class=\"n\">test2017_data<\/span> <span class=\"o\">=<\/span> <span class=\"nc\">CocoCaptions<\/span><span class=\"p\">(<\/span>\n    <span class=\"n\">root<\/span><span class=\"o\">=<\/span><span class=\"sh\">\"<\/span><span class=\"s\">data\/coco\/imgs\/test2017<\/span><span class=\"sh\">\"<\/span><span class=\"p\">,<\/span>\n    <span class=\"n\">annFile<\/span><span class=\"o\">=<\/span><span class=\"sh\">\"<\/span><span class=\"s\">data\/coco\/anns\/test2017\/image_info_test2017.json<\/span><span class=\"sh\">\"<\/span>\n<span class=\"p\">)<\/span>\n\n<span class=\"n\">testdev2017_data<\/span> <span class=\"o\">=<\/span> <span class=\"nc\">CocoCaptions<\/span><span class=\"p\">(<\/span>\n    <span class=\"n\">root<\/span><span class=\"o\">=<\/span><span class=\"sh\">\"<\/span><span class=\"s\">data\/coco\/imgs\/test2017<\/span><span class=\"sh\">\"<\/span><span class=\"p\">,<\/span>\n    <span class=\"n\">annFile<\/span><span class=\"o\">=<\/span><span class=\"sh\">\"<\/span><span class=\"s\">data\/coco\/anns\/test2017\/image_info_test-dev2017.json<\/span><span class=\"sh\">\"<\/span>\n<span class=\"p\">)<\/span>\n\n<span class=\"nf\">len<\/span><span class=\"p\">(<\/span><span class=\"n\">test2017_data<\/span><span class=\"p\">),<\/span> <span class=\"nf\">len<\/span><span class=\"p\">(<\/span><span class=\"n\">testdev2017_data<\/span><span class=\"p\">)<\/span>\n<span class=\"c1\"># (40670, 20288)\n<\/span>\n<span class=\"n\">cap_train2017_data<\/span><span class=\"p\">[<\/span><span class=\"mi\">2<\/span><span class=\"p\">]<\/span>\n<span class=\"c1\"># (<pil.image.image image=\"\" mode=\"RGB\" size=\"640x428\">,\n#  ['A flower vase is sitting on a porch stand.',\n#   'White vase with different colored flowers sitting inside of it. ',\n#   'a white vase with many flowers on a stage',\n#   'A white vase filled with different colored flowers.',\n#   'A vase with red and white flowers outside on a sunny day.'])\n<\/pil.image.image><\/span>\n<span class=\"n\">cap_train2017_data<\/span><span class=\"p\">[<\/span><span class=\"mi\">47<\/span><span class=\"p\">]<\/span>\n<span class=\"c1\"># (<pil.image.image image=\"\" mode=\"RGB\" size=\"640x427\">,\n#  ['A man standing in front of a microwave next to pots and pans.',\n#   'A man displaying pots and utensils on a wall.',\n#   'A man stands in a kitchen and motions towards pots and pans. ',\n#   'a man poses in front of some pots and pans ',\n#   'A man pointing to pots hanging from a pegboard on a gray wall.'])\n<\/pil.image.image><\/span>\n<span class=\"n\">cap_train2017_data<\/span><span class=\"p\">[<\/span><span class=\"mi\">64<\/span><span class=\"p\">]<\/span>\n<span class=\"c1\"># (<pil.image.image image=\"\" mode=\"RGB\" size=\"480x640\">,\n#  ['A little girl holding wet broccoli in her hand. ',\n#   'The young child is happily holding a fresh vegetable. ',\n#   'A little girl holds a hand full of wet broccoli. ',\n#   'A little girl holds a piece of broccoli towards the camera.',\n#   'a small kid holds on to some vegetables '])\n<\/pil.image.image><\/span>\n<span class=\"n\">ins_train2017_data<\/span><span class=\"p\">[<\/span><span class=\"mi\">2<\/span><span class=\"p\">]<\/span> <span class=\"c1\"># Error\n<\/span>\n<span class=\"n\">ins_train2017_data<\/span><span class=\"p\">[<\/span><span class=\"mi\">47<\/span><span class=\"p\">]<\/span> <span class=\"c1\"># Error\n<\/span>\n<span class=\"n\">ins_train2017_data<\/span><span class=\"p\">[<\/span><span class=\"mi\">67<\/span><span class=\"p\">]<\/span> <span class=\"c1\"># Error\n<\/span>\n<span class=\"n\">pk_train2017_data<\/span><span class=\"p\">[<\/span><span class=\"mi\">2<\/span><span class=\"p\">]<\/span>\n<span class=\"c1\"># (<pil.image.image image=\"\" mode=\"RGB\" size=\"640x428\">, [])\n<\/pil.image.image><\/span>\n<span class=\"n\">pk_train2017_data<\/span><span class=\"p\">[<\/span><span class=\"mi\">47<\/span><span class=\"p\">]<\/span> <span class=\"c1\"># Error\n<\/span>\n<span class=\"n\">pk_train2017_data<\/span><span class=\"p\">[<\/span><span class=\"mi\">64<\/span><span class=\"p\">]<\/span> <span class=\"c1\"># Error\n<\/span>\n<span class=\"n\">cap_val2017_data<\/span><span class=\"p\">[<\/span><span class=\"mi\">2<\/span><span class=\"p\">]<\/span>\n<span class=\"c1\"># (<pil.image.image image=\"\" mode=\"RGB\" size=\"640x483\">,\n#  ['Bedroom scene with a bookcase, blue comforter and window.',\n#   'A bedroom with a bookshelf full of books.',\n#   'This room has a bed with blue sheets and a large bookcase',\n#   'A bed and a mirror in a small room.',\n#   'a bed room with a neatly made bed a window and a book shelf'])\n<\/pil.image.image><\/span>\n<span class=\"n\">cap_val2017_data<\/span><span class=\"p\">[<\/span><span class=\"mi\">47<\/span><span class=\"p\">]<\/span>\n<span class=\"c1\"># (<pil.image.image image=\"\" mode=\"RGB\" size=\"640x480\">,\n#  ['A group of people cutting a ribbon on a street.',\n#   'A man uses a pair of big scissors to cut a pink ribbon.',\n#   'A man cutting a ribbon at a ceremony ',\n#   'A group of people on the sidewalk watching two young children.',\n#   'A group of people holding a large pair of scissors to a ribbon.'])\n<\/pil.image.image><\/span>\n<span class=\"n\">cap_val2017_data<\/span><span class=\"p\">[<\/span><span class=\"mi\">64<\/span><span class=\"p\">]<\/span>\n<span class=\"c1\"># (<pil.image.image image=\"\" mode=\"RGB\" size=\"375x500\">,\n#  ['A man and a women posing next to one another in front of a table.',\n#   'A man and woman hugging in a restaurant',\n#   'A man and woman standing next to a table.',\n#   'A happy man and woman pose for a picture.',\n#   'A man and woman posing for a picture in a sports bar.'])\n<\/pil.image.image><\/span>\n<span class=\"n\">ins_val2017_data<\/span><span class=\"p\">[<\/span><span class=\"mi\">2<\/span><span class=\"p\">]<\/span> <span class=\"c1\"># Error\n<\/span>\n<span class=\"n\">ins_val2017_data<\/span><span class=\"p\">[<\/span><span class=\"mi\">47<\/span><span class=\"p\">]<\/span> <span class=\"c1\"># Error\n<\/span>\n<span class=\"n\">ins_val2017_data<\/span><span class=\"p\">[<\/span><span class=\"mi\">64<\/span><span class=\"p\">]<\/span> <span class=\"c1\"># Error\n<\/span>\n<span class=\"n\">pk_val2017_data<\/span><span class=\"p\">[<\/span><span class=\"mi\">2<\/span><span class=\"p\">]<\/span>\n<span class=\"c1\"># (<pil.image.image image=\"\" mode=\"RGB\" size=\"640x483\">, [])\n<\/pil.image.image><\/span>\n<span class=\"n\">pk_val2017_data<\/span><span class=\"p\">[<\/span><span class=\"mi\">47<\/span><span class=\"p\">]<\/span> <span class=\"c1\"># Error\n<\/span>\n<span class=\"n\">pk_val2017_data<\/span><span class=\"p\">[<\/span><span class=\"mi\">64<\/span><span class=\"p\">]<\/span> <span class=\"c1\"># Error\n<\/span>\n<span class=\"n\">test2017_data<\/span><span class=\"p\">[<\/span><span class=\"mi\">2<\/span><span class=\"p\">]<\/span>\n<span class=\"c1\"># (<pil.image.image image=\"\" mode=\"RGB\" size=\"640x427\">, [])\n<\/pil.image.image><\/span>\n<span class=\"n\">test2017_data<\/span><span class=\"p\">[<\/span><span class=\"mi\">47<\/span><span class=\"p\">]<\/span>\n<span class=\"c1\"># (<pil.image.image image=\"\" mode=\"RGB\" size=\"640x406\">, [])\n<\/pil.image.image><\/span>\n<span class=\"n\">test2017_data<\/span><span class=\"p\">[<\/span><span class=\"mi\">64<\/span><span class=\"p\">]<\/span>\n<span class=\"c1\"># (<pil.image.image image=\"\" mode=\"RGB\" size=\"640x427\">, [])\n<\/pil.image.image><\/span>\n<span class=\"n\">testdev2017_data<\/span><span class=\"p\">[<\/span><span class=\"mi\">2<\/span><span class=\"p\">]<\/span>\n<span class=\"c1\"># (<pil.image.image image=\"\" mode=\"RGB\" size=\"640x427\">, [])\n<\/pil.image.image><\/span>\n<span class=\"n\">testdev2017_data<\/span><span class=\"p\">[<\/span><span class=\"mi\">47<\/span><span class=\"p\">]<\/span>\n<span class=\"c1\"># (<pil.image.image image=\"\" mode=\"RGB\" size=\"480x640\">, [])\n<\/pil.image.image><\/span>\n<span class=\"n\">testdev2017_data<\/span><span class=\"p\">[<\/span><span class=\"mi\">64<\/span><span class=\"p\">]<\/span>\n<span class=\"c1\"># (<pil.image.image image=\"\" mode=\"RGB\" size=\"640x480\">, [])\n<\/pil.image.image><\/span>\n<span class=\"kn\">import<\/span> <span class=\"n\">matplotlib.pyplot<\/span> <span class=\"k\">as<\/span> <span class=\"n\">plt<\/span>\n\n<span class=\"k\">def<\/span> <span class=\"nf\">show_images<\/span><span class=\"p\">(<\/span><span class=\"n\">data<\/span><span class=\"p\">,<\/span> <span class=\"n\">ims<\/span><span class=\"p\">,<\/span> <span class=\"n\">main_title<\/span><span class=\"o\">=<\/span><span class=\"bp\">None<\/span><span class=\"p\">):<\/span>\n    <span class=\"nb\">file<\/span> <span class=\"o\">=<\/span> <span class=\"n\">data<\/span><span class=\"p\">.<\/span><span class=\"n\">root<\/span><span class=\"p\">.<\/span><span class=\"nf\">split<\/span><span class=\"p\">(<\/span><span class=\"sh\">'<\/span><span class=\"s\">\/<\/span><span class=\"sh\">'<\/span><span class=\"p\">)[<\/span><span class=\"o\">-<\/span><span class=\"mi\">1<\/span><span class=\"p\">]<\/span>\n    <span class=\"n\">fig<\/span><span class=\"p\">,<\/span> <span class=\"n\">axes<\/span> <span class=\"o\">=<\/span> <span class=\"n\">plt<\/span><span class=\"p\">.<\/span><span class=\"nf\">subplots<\/span><span class=\"p\">(<\/span><span class=\"n\">nrows<\/span><span class=\"o\">=<\/span><span class=\"mi\">1<\/span><span class=\"p\">,<\/span> <span class=\"n\">ncols<\/span><span class=\"o\">=<\/span><span class=\"mi\">3<\/span><span class=\"p\">,<\/span> <span class=\"n\">figsize<\/span><span class=\"o\">=<\/span><span class=\"p\">(<\/span><span class=\"mi\">14<\/span><span class=\"p\">,<\/span> <span class=\"mi\">8<\/span><span class=\"p\">))<\/span>\n    <span class=\"n\">fig<\/span><span class=\"p\">.<\/span><span class=\"nf\">suptitle<\/span><span class=\"p\">(<\/span><span class=\"n\">t<\/span><span class=\"o\">=<\/span><span class=\"n\">main_title<\/span><span class=\"p\">,<\/span> <span class=\"n\">y<\/span><span class=\"o\">=<\/span><span class=\"mf\">0.9<\/span><span class=\"p\">,<\/span> <span class=\"n\">fontsize<\/span><span class=\"o\">=<\/span><span class=\"mi\">14<\/span><span class=\"p\">)<\/span>\n    <span class=\"n\">x_crd<\/span> <span class=\"o\">=<\/span> <span class=\"mf\">0.02<\/span>\n    <span class=\"k\">for<\/span> <span class=\"n\">i<\/span><span class=\"p\">,<\/span> <span class=\"n\">axis<\/span> <span class=\"ow\">in<\/span> <span class=\"nf\">zip<\/span><span class=\"p\">(<\/span><span class=\"n\">ims<\/span><span class=\"p\">,<\/span> <span class=\"n\">axes<\/span><span class=\"p\">.<\/span><span class=\"nf\">ravel<\/span><span class=\"p\">()):<\/span>\n        <span class=\"k\">if<\/span> <span class=\"n\">data<\/span><span class=\"p\">[<\/span><span class=\"n\">i<\/span><span class=\"p\">][<\/span><span class=\"mi\">1<\/span><span class=\"p\">]:<\/span>\n            <span class=\"n\">im<\/span><span class=\"p\">,<\/span> <span class=\"n\">anns<\/span> <span class=\"o\">=<\/span> <span class=\"n\">data<\/span><span class=\"p\">[<\/span><span class=\"n\">i<\/span><span class=\"p\">]<\/span>\n            <span class=\"n\">axis<\/span><span class=\"p\">.<\/span><span class=\"nf\">imshow<\/span><span class=\"p\">(<\/span><span class=\"n\">X<\/span><span class=\"o\">=<\/span><span class=\"n\">im<\/span><span class=\"p\">)<\/span>\n            <span class=\"n\">y_crd<\/span> <span class=\"o\">=<\/span> <span class=\"mf\">0.0<\/span>\n            <span class=\"k\">for<\/span> <span class=\"n\">j<\/span><span class=\"p\">,<\/span> <span class=\"n\">ann<\/span> <span class=\"ow\">in<\/span> <span class=\"nf\">enumerate<\/span><span class=\"p\">(<\/span><span class=\"n\">iterable<\/span><span class=\"o\">=<\/span><span class=\"n\">anns<\/span><span class=\"p\">):<\/span>\n                <span class=\"n\">text_list<\/span> <span class=\"o\">=<\/span> <span class=\"n\">ann<\/span><span class=\"p\">.<\/span><span class=\"nf\">split<\/span><span class=\"p\">()<\/span>\n                <span class=\"k\">if<\/span> <span class=\"nf\">len<\/span><span class=\"p\">(<\/span><span class=\"n\">text_list<\/span><span class=\"p\">)<\/span> <span class=\"o\">&gt;<\/span> <span class=\"mi\">9<\/span><span class=\"p\">:<\/span>\n                    <span class=\"n\">text<\/span> <span class=\"o\">=<\/span> <span class=\"sh\">\"<\/span><span class=\"s\"> <\/span><span class=\"sh\">\"<\/span><span class=\"p\">.<\/span><span class=\"nf\">join<\/span><span class=\"p\">(<\/span><span class=\"n\">text_list<\/span><span class=\"p\">[<\/span><span class=\"mi\">0<\/span><span class=\"p\">:<\/span><span class=\"mi\">10<\/span><span class=\"p\">])<\/span> <span class=\"o\">+<\/span> <span class=\"sh\">\"<\/span><span class=\"s\"> ...<\/span><span class=\"sh\">\"<\/span>\n                <span class=\"k\">else<\/span><span class=\"p\">:<\/span>\n                    <span class=\"n\">text<\/span> <span class=\"o\">=<\/span> <span class=\"sh\">\"<\/span><span class=\"s\"> <\/span><span class=\"sh\">\"<\/span><span class=\"p\">.<\/span><span class=\"nf\">join<\/span><span class=\"p\">(<\/span><span class=\"n\">text_list<\/span><span class=\"p\">)<\/span>\n                <span class=\"n\">plt<\/span><span class=\"p\">.<\/span><span class=\"nf\">figtext<\/span><span class=\"p\">(<\/span><span class=\"n\">x<\/span><span class=\"o\">=<\/span><span class=\"n\">x_crd<\/span><span class=\"p\">,<\/span> <span class=\"n\">y<\/span><span class=\"o\">=<\/span><span class=\"n\">y_crd<\/span><span class=\"p\">,<\/span> <span class=\"n\">fontsize<\/span><span class=\"o\">=<\/span><span class=\"mi\">10<\/span><span class=\"p\">,<\/span>\n                            <span class=\"n\">s<\/span><span class=\"o\">=<\/span><span class=\"sa\">f<\/span><span class=\"sh\">'<\/span><span class=\"si\">{<\/span><span class=\"n\">j<\/span><span class=\"si\">}<\/span><span class=\"s\">:<\/span><span class=\"se\">\\n<\/span><span class=\"si\">{<\/span><span class=\"n\">text<\/span><span class=\"si\">}<\/span><span class=\"sh\">'<\/span><span class=\"p\">)<\/span>\n                <span class=\"n\">y_crd<\/span> <span class=\"o\">-=<\/span> <span class=\"mf\">0.06<\/span>\n            <span class=\"n\">x_crd<\/span> <span class=\"o\">+=<\/span> <span class=\"mf\">0.325<\/span>\n            <span class=\"k\">if<\/span> <span class=\"n\">i<\/span> <span class=\"o\">==<\/span> <span class=\"mi\">2<\/span> <span class=\"ow\">and<\/span> <span class=\"nb\">file<\/span> <span class=\"o\">==<\/span> <span class=\"sh\">\"<\/span><span class=\"s\">val2017<\/span><span class=\"sh\">\"<\/span><span class=\"p\">:<\/span>\n                <span class=\"n\">x_crd<\/span> <span class=\"o\">+=<\/span> <span class=\"mf\">0.06<\/span>\n        <span class=\"k\">elif<\/span> <span class=\"ow\">not<\/span> <span class=\"n\">data<\/span><span class=\"p\">[<\/span><span class=\"n\">i<\/span><span class=\"p\">][<\/span><span class=\"mi\">1<\/span><span class=\"p\">]:<\/span>\n            <span class=\"n\">im<\/span><span class=\"p\">,<\/span> <span class=\"n\">_<\/span> <span class=\"o\">=<\/span> <span class=\"n\">data<\/span><span class=\"p\">[<\/span><span class=\"n\">i<\/span><span class=\"p\">]<\/span>\n            <span class=\"n\">axis<\/span><span class=\"p\">.<\/span><span class=\"nf\">imshow<\/span><span class=\"p\">(<\/span><span class=\"n\">X<\/span><span class=\"o\">=<\/span><span class=\"n\">im<\/span><span class=\"p\">)<\/span>\n    <span class=\"n\">fig<\/span><span class=\"p\">.<\/span><span class=\"nf\">tight_layout<\/span><span class=\"p\">()<\/span>\n    <span class=\"n\">plt<\/span><span class=\"p\">.<\/span><span class=\"nf\">show<\/span><span class=\"p\">()<\/span>\n\n<span class=\"n\">ims<\/span> <span class=\"o\">=<\/span> <span class=\"p\">(<\/span><span class=\"mi\">2<\/span><span class=\"p\">,<\/span> <span class=\"mi\">47<\/span><span class=\"p\">,<\/span> <span class=\"mi\">64<\/span><span class=\"p\">)<\/span>\n\n<span class=\"nf\">show_images<\/span><span class=\"p\">(<\/span><span class=\"n\">data<\/span><span class=\"o\">=<\/span><span class=\"n\">cap_train2017_data<\/span><span class=\"p\">,<\/span> <span class=\"n\">ims<\/span><span class=\"o\">=<\/span><span class=\"n\">ims<\/span><span class=\"p\">,<\/span>\n             <span class=\"n\">main_title<\/span><span class=\"o\">=<\/span><span class=\"sh\">\"<\/span><span class=\"s\">cap_train2017_data<\/span><span class=\"sh\">\"<\/span><span class=\"p\">)<\/span>\n<span class=\"nf\">show_images<\/span><span class=\"p\">(<\/span><span class=\"n\">data<\/span><span class=\"o\">=<\/span><span class=\"n\">cap_val2017_data<\/span><span class=\"p\">,<\/span> <span class=\"n\">ims<\/span><span class=\"o\">=<\/span><span class=\"n\">ims<\/span><span class=\"p\">,<\/span> \n             <span class=\"n\">main_title<\/span><span class=\"o\">=<\/span><span class=\"sh\">\"<\/span><span class=\"s\">cap_val2017_data<\/span><span class=\"sh\">\"<\/span><span class=\"p\">)<\/span>\n<span class=\"nf\">show_images<\/span><span class=\"p\">(<\/span><span class=\"n\">data<\/span><span class=\"o\">=<\/span><span class=\"n\">test2017_data<\/span><span class=\"p\">,<\/span> <span class=\"n\">ims<\/span><span class=\"o\">=<\/span><span class=\"n\">ims<\/span><span class=\"p\">,<\/span>\n            <span class=\"n\">main_title<\/span><span class=\"o\">=<\/span><span class=\"sh\">\"<\/span><span class=\"s\">test2017_data<\/span><span class=\"sh\">\"<\/span><span class=\"p\">)<\/span>\n<span class=\"nf\">show_images<\/span><span class=\"p\">(<\/span><span class=\"n\">data<\/span><span class=\"o\">=<\/span><span class=\"n\">testdev2017_data<\/span><span class=\"p\">,<\/span> <span class=\"n\">ims<\/span><span class=\"o\">=<\/span><span class=\"n\">ims<\/span><span class=\"p\">,<\/span> \n            <span class=\"n\">main_title<\/span><span class=\"o\">=<\/span><span class=\"sh\">\"<\/span><span class=\"s\">testdev2017_data<\/span><span class=\"sh\">\"<\/span><span class=\"p\">)<\/span>\n<\/code><\/pre>\n<div class=\"highlight__panel js-actions-panel\">\n<div class=\"highlight__panel-action js-fullscreen-code-action\">\n    <svg xmlns=\"http:\/\/www.w3.org\/2000\/svg\" width=\"20px\" height=\"20px\" viewbox=\"0 0 24 24\" class=\"highlight-action crayons-icon highlight-action--fullscreen-on\"><title>\u0648\u0627\u0631\u062f \u062d\u0627\u0644\u062a \u062a\u0645\u0627\u0645 \u0635\u0641\u062d\u0647 \u0634\u0648\u06cc\u062f<\/title>\n    <path d=\"M16 3h6v6h-2V5h-4V3zM2 3h6v2H4v4H2V3zm18 16v-4h2v6h-6v-2h4zM4 19h4v2H2v-6h2v4z\"\/>\n<\/svg><\/p>\n<p>    <svg xmlns=\"http:\/\/www.w3.org\/2000\/svg\" width=\"20px\" height=\"20px\" viewbox=\"0 0 24 24\" class=\"highlight-action crayons-icon highlight-action--fullscreen-off\"><title>\u0627\u0632 \u062d\u0627\u0644\u062a \u062a\u0645\u0627\u0645 \u0635\u0641\u062d\u0647 \u062e\u0627\u0631\u062c \u0634\u0648\u06cc\u062f<\/title>\n    <path d=\"M18 7h4v2h-6V3h2v4zM8 9H2V7h4V3h2v6zm10 8v4h-2v-6h6v2h-4zM8 15v6H6v-4H2v-2h6z\"\/>\n<\/svg><\/p>\n<\/div>\n<\/div>\n<\/div>\n<p><\/p>\n<p><img decoding=\"async\" src=\"https:\/\/media2.dev.to\/dynamic\/image\/width=800%2Cheight=%2Cfit=scale-down%2Cgravity=auto%2Cformat=auto\/https%3A%2F%2Fdev-to-uploads.s3.amazonaws.com%2Fuploads%2Farticles%2Fh21i7dlxm0tm6bup0ad0.png\" alt=\"\u062a\u0648\u0636\u06cc\u062d\u0627\u062a \u062a\u0635\u0648\u06cc\u0631\" loading=\"lazy\" width=\"800\" height=\"539\" title=\"\"><\/p>\n<p><img decoding=\"async\" src=\"https:\/\/media2.dev.to\/dynamic\/image\/width=800%2Cheight=%2Cfit=scale-down%2Cgravity=auto%2Cformat=auto\/https%3A%2F%2Fdev-to-uploads.s3.amazonaws.com%2Fuploads%2Farticles%2Fuj5sx5elbe4r0n46kkma.png\" alt=\"\u062a\u0648\u0636\u06cc\u062d\u0627\u062a \u062a\u0635\u0648\u06cc\u0631\" loading=\"lazy\" width=\"800\" height=\"299\" title=\"\"><\/p>\n<p><img decoding=\"async\" src=\"https:\/\/media2.dev.to\/dynamic\/image\/width=800%2Cheight=%2Cfit=scale-down%2Cgravity=auto%2Cformat=auto\/https%3A%2F%2Fdev-to-uploads.s3.amazonaws.com%2Fuploads%2Farticles%2Fndsvg3wx7h7y8o0sp5ki.png\" alt=\"\u062a\u0648\u0636\u06cc\u062d\u0627\u062a \u062a\u0635\u0648\u06cc\u0631\" loading=\"lazy\" width=\"800\" height=\"377\" title=\"\"><\/p>\n<\/p><\/div>\n","protected":false},"excerpt":{"rendered":"<p>\u0628\u0631\u0627\u06cc \u0645\u0646 \u06cc\u06a9 \u0642\u0647\u0648\u0647 \u0628\u062e\u0631\u2615 *\u06cc\u0627\u062f\u062f\u0627\u0634\u062a \u0647\u0627: \u067e\u0633\u062a \u0645\u0646 \u0628\u0627 \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u0627\u0632 CocoCaptions () \u062a\u0648\u0636\u06cc\u062d \u0645\u06cc \u062f\u0647\u062f train2014 \u0628\u0627 captions_train2014.json\u060c instances_train2014.json \u0648 person_keypoints_train2014.json\u060c val2014 \u0628\u0627 captions_val2014.json\u060c instances_val2014.json \u0648 person_keypoints_val2014.json \u0648 test2017 \u0628\u0627 image_info_test2014.json\u060c image_info_test2015.json \u0648 image_info_test-dev2015.json. \u067e\u0633\u062a \u0645\u0646 \u0628\u0627 \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u0627\u0632 CocoCaptions () \u062a\u0648\u0636\u06cc\u062d \u0645\u06cc \u062f\u0647\u062f train2017 \u0628\u0627 stuff_train2017.json\u060c val2017 \u0628\u0627 stuff_val2017.json\u060c stuff_train2017_pixelmaps \u0628\u0627 stuff_train2017.json\u060c &hellip;<\/p>\n","protected":false},"author":2,"featured_media":91994,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"fifu_image_url":"","fifu_image_alt":"","footnotes":""},"categories":[339],"tags":[],"class_list":["post-91993","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-dev"],"_links":{"self":[{"href":"https:\/\/nabfollower.com\/blog\/wp-json\/wp\/v2\/posts\/91993","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/nabfollower.com\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/nabfollower.com\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/nabfollower.com\/blog\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/nabfollower.com\/blog\/wp-json\/wp\/v2\/comments?post=91993"}],"version-history":[{"count":0,"href":"https:\/\/nabfollower.com\/blog\/wp-json\/wp\/v2\/posts\/91993\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/nabfollower.com\/blog\/wp-json\/wp\/v2\/media\/91994"}],"wp:attachment":[{"href":"https:\/\/nabfollower.com\/blog\/wp-json\/wp\/v2\/media?parent=91993"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/nabfollower.com\/blog\/wp-json\/wp\/v2\/categories?post=91993"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/nabfollower.com\/blog\/wp-json\/wp\/v2\/tags?post=91993"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}