{"id":64,"date":"2021-03-20T18:24:20","date_gmt":"2021-03-20T18:24:20","guid":{"rendered":"http:\/\/course.ece.cmu.edu\/~ece500\/projects\/s21-teamc8\/?p=64"},"modified":"2021-03-28T02:05:41","modified_gmt":"2021-03-28T02:05:41","slug":"jennys-status-report-for-3-20-2021","status":"publish","type":"post","link":"https:\/\/course.ece.cmu.edu\/~ece500\/projects\/s21-teamc8\/2021\/03\/20\/jennys-status-report-for-3-20-2021\/","title":{"rendered":"Jenny&#8217;s Status Report for 3\/20\/2021"},"content":{"rendered":"<p>For this week, I worked with my group to complete our Design Review paper. Additionally, I made progress on gesture detection. As per Uzair&#8217;s advice, to ignore the face and background in webcam images, I wore a generic brand blue surgical glove and extracted only that to get only the hands, as pictured below:<\/p>\n<p><img decoding=\"async\" loading=\"lazy\" class=\"alignnone wp-image-66\" src=\"http:\/\/course.ece.cmu.edu\/~ece500\/projects\/s21-teamc8\/wp-content\/uploads\/sites\/139\/2021\/03\/blue-glove-detection-300x128.png\" alt=\"\" width=\"394\" height=\"168\" srcset=\"https:\/\/course.ece.cmu.edu\/~ece500\/projects\/s21-teamc8\/wp-content\/uploads\/sites\/139\/2021\/03\/blue-glove-detection-300x128.png 300w, https:\/\/course.ece.cmu.edu\/~ece500\/projects\/s21-teamc8\/wp-content\/uploads\/sites\/139\/2021\/03\/blue-glove-detection-768x327.png 768w, https:\/\/course.ece.cmu.edu\/~ece500\/projects\/s21-teamc8\/wp-content\/uploads\/sites\/139\/2021\/03\/blue-glove-detection-1024x436.png 1024w, https:\/\/course.ece.cmu.edu\/~ece500\/projects\/s21-teamc8\/wp-content\/uploads\/sites\/139\/2021\/03\/blue-glove-detection.png 1296w\" sizes=\"(max-width: 394px) 100vw, 394px\" \/><\/p>\n<p>Next, I started generating both training and testing datasets using this method, with two labels: gesture vs no_gesture. I currently have about 300 images for each of the labels for training, and about 100 each for testing. The images below are of the gesture label in the datasets folder:<\/p>\n<p><img decoding=\"async\" loading=\"lazy\" class=\"alignnone wp-image-67\" src=\"http:\/\/course.ece.cmu.edu\/~ece500\/projects\/s21-teamc8\/wp-content\/uploads\/sites\/139\/2021\/03\/datasets-300x139.png\" alt=\"\" width=\"395\" height=\"183\" srcset=\"https:\/\/course.ece.cmu.edu\/~ece500\/projects\/s21-teamc8\/wp-content\/uploads\/sites\/139\/2021\/03\/datasets-300x139.png 300w, https:\/\/course.ece.cmu.edu\/~ece500\/projects\/s21-teamc8\/wp-content\/uploads\/sites\/139\/2021\/03\/datasets-768x357.png 768w, https:\/\/course.ece.cmu.edu\/~ece500\/projects\/s21-teamc8\/wp-content\/uploads\/sites\/139\/2021\/03\/datasets-1024x475.png 1024w\" sizes=\"(max-width: 395px) 100vw, 395px\" \/><\/p>\n<p>I then implemented the CNN training algorithm and model then began training. I tried to adjust parameters and tested which gave the best results in training and found that the highest testing accuracy (which varied from 65 to 69% validation accuracy, and about 80% training accuracy ) and\u00a0 I got was for a batch size of 15, number of steps of 20, and 3 epochs, of which the printout of the last epoch is here:<\/p>\n<p><img decoding=\"async\" loading=\"lazy\" class=\"alignnone wp-image-69\" src=\"http:\/\/course.ece.cmu.edu\/~ece500\/projects\/s21-teamc8\/wp-content\/uploads\/sites\/139\/2021\/03\/15-20-20-3-accuracy-300x153.png\" alt=\"\" width=\"464\" height=\"237\" srcset=\"https:\/\/course.ece.cmu.edu\/~ece500\/projects\/s21-teamc8\/wp-content\/uploads\/sites\/139\/2021\/03\/15-20-20-3-accuracy-300x153.png 300w, https:\/\/course.ece.cmu.edu\/~ece500\/projects\/s21-teamc8\/wp-content\/uploads\/sites\/139\/2021\/03\/15-20-20-3-accuracy-768x392.png 768w, https:\/\/course.ece.cmu.edu\/~ece500\/projects\/s21-teamc8\/wp-content\/uploads\/sites\/139\/2021\/03\/15-20-20-3-accuracy-1024x522.png 1024w, https:\/\/course.ece.cmu.edu\/~ece500\/projects\/s21-teamc8\/wp-content\/uploads\/sites\/139\/2021\/03\/15-20-20-3-accuracy.png 1839w\" sizes=\"(max-width: 464px) 100vw, 464px\" \/><\/p>\n<p>For the next week, I will first work on incorporating this into the overall pipeline and complete a finished version of the product before moving on to improving the model and accuracy. I suspect the accuracy will improve a lot if I do multi-category classification instead of binary, because there are a lot of nuances with the no_gesture label, since it incorporates everything else that is not a gesture.<\/p>\n<p>&nbsp;<\/p>\n<p>&nbsp;<\/p>\n","protected":false},"excerpt":{"rendered":"<p>For this week, I worked with my group to complete our Design Review paper. Additionally, I made progress on gesture detection. As per Uzair&#8217;s advice, to ignore the face and background in webcam images, I wore a generic brand blue surgical glove and extracted only that to get only the hands, as pictured below: Next, &hellip; <\/p>\n<p class=\"link-more\"><a href=\"https:\/\/course.ece.cmu.edu\/~ece500\/projects\/s21-teamc8\/2021\/03\/20\/jennys-status-report-for-3-20-2021\/\" class=\"more-link\">Continue reading<span class=\"screen-reader-text\"> &#8220;Jenny&#8217;s Status Report for 3\/20\/2021&#8221;<\/span><\/a><\/p>\n","protected":false},"author":430,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":[],"categories":[1],"tags":[],"_links":{"self":[{"href":"https:\/\/course.ece.cmu.edu\/~ece500\/projects\/s21-teamc8\/wp-json\/wp\/v2\/posts\/64"}],"collection":[{"href":"https:\/\/course.ece.cmu.edu\/~ece500\/projects\/s21-teamc8\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/course.ece.cmu.edu\/~ece500\/projects\/s21-teamc8\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/course.ece.cmu.edu\/~ece500\/projects\/s21-teamc8\/wp-json\/wp\/v2\/users\/430"}],"replies":[{"embeddable":true,"href":"https:\/\/course.ece.cmu.edu\/~ece500\/projects\/s21-teamc8\/wp-json\/wp\/v2\/comments?post=64"}],"version-history":[{"count":2,"href":"https:\/\/course.ece.cmu.edu\/~ece500\/projects\/s21-teamc8\/wp-json\/wp\/v2\/posts\/64\/revisions"}],"predecessor-version":[{"id":74,"href":"https:\/\/course.ece.cmu.edu\/~ece500\/projects\/s21-teamc8\/wp-json\/wp\/v2\/posts\/64\/revisions\/74"}],"wp:attachment":[{"href":"https:\/\/course.ece.cmu.edu\/~ece500\/projects\/s21-teamc8\/wp-json\/wp\/v2\/media?parent=64"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/course.ece.cmu.edu\/~ece500\/projects\/s21-teamc8\/wp-json\/wp\/v2\/categories?post=64"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/course.ece.cmu.edu\/~ece500\/projects\/s21-teamc8\/wp-json\/wp\/v2\/tags?post=64"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}