{"id":105,"date":"2021-03-27T23:34:19","date_gmt":"2021-03-27T23:34:19","guid":{"rendered":"http:\/\/course.ece.cmu.edu\/~ece500\/projects\/s21-teamb2\/?p=105"},"modified":"2021-03-27T23:34:19","modified_gmt":"2021-03-27T23:34:19","slug":"henrys-status-report-for-3-27-2021","status":"publish","type":"post","link":"https:\/\/course.ece.cmu.edu\/~ece500\/projects\/s21-teamb2\/2021\/03\/27\/henrys-status-report-for-3-27-2021\/","title":{"rendered":"Henry&#8217;s Status Report for 3\/27\/2021"},"content":{"rendered":"<p>The past two weeks I worked on:<\/p>\n<ul>\n<li>Finished the design report. I wrote most of the documentation on the visualizer component.<\/li>\n<li>formatted datasets for training. Detector required tfrecord files from DeepFashion2 dataset while classifier required images sorted into classes from DeepFashion dataset.<\/li>\n<li>Trained a clothing detector that detects bounding boxes and does simple classification of clothing articles.\n<ul>\n<li>tried yolov4 using pytorch, but API was really bad and had many problems I had to fix by looking at pull requests. Ultimately, didn&#8217;t use.<\/li>\n<li>tried efficientDet0 with tensorflow2 object detection API and it was much better documented and had more community support. Ultimately, used this.<\/li>\n<li>Using DeepFashion2 dataset, which doesn&#8217;t provide good classification labels, but has bounding boxes over every clothing item (DeepFashion only has 1 bounding box per image)<\/li>\n<li>unfortunately, I didn&#8217;t measure accuracy during training, but here are the loss figures:<\/li>\n<li><img decoding=\"async\" loading=\"lazy\" class=\"alignnone size-medium wp-image-107\" src=\"http:\/\/course.ece.cmu.edu\/~ece500\/projects\/s21-teamb2\/wp-content\/uploads\/sites\/124\/2021\/03\/Capture-1-300x164.jpg\" alt=\"\" width=\"300\" height=\"164\" srcset=\"https:\/\/course.ece.cmu.edu\/~ece500\/projects\/s21-teamb2\/wp-content\/uploads\/sites\/124\/2021\/03\/Capture-1-300x164.jpg 300w, https:\/\/course.ece.cmu.edu\/~ece500\/projects\/s21-teamb2\/wp-content\/uploads\/sites\/124\/2021\/03\/Capture-1-768x421.jpg 768w, https:\/\/course.ece.cmu.edu\/~ece500\/projects\/s21-teamb2\/wp-content\/uploads\/sites\/124\/2021\/03\/Capture-1-1024x561.jpg 1024w, https:\/\/course.ece.cmu.edu\/~ece500\/projects\/s21-teamb2\/wp-content\/uploads\/sites\/124\/2021\/03\/Capture-1-1200x658.jpg 1200w, https:\/\/course.ece.cmu.edu\/~ece500\/projects\/s21-teamb2\/wp-content\/uploads\/sites\/124\/2021\/03\/Capture-1.jpg 1295w\" sizes=\"(max-width: 300px) 85vw, 300px\" \/><\/li>\n<\/ul>\n<\/li>\n<li>Training a clothing classifier that provides more fine-grained classification.\n<ul>\n<li>Using efficientNetb0 from keras. Below is test accuracy:<\/li>\n<li><img decoding=\"async\" loading=\"lazy\" class=\"alignnone size-medium wp-image-106\" src=\"http:\/\/course.ece.cmu.edu\/~ece500\/projects\/s21-teamb2\/wp-content\/uploads\/sites\/124\/2021\/03\/Capture-300x214.jpg\" alt=\"\" width=\"300\" height=\"214\" srcset=\"https:\/\/course.ece.cmu.edu\/~ece500\/projects\/s21-teamb2\/wp-content\/uploads\/sites\/124\/2021\/03\/Capture-300x214.jpg 300w, https:\/\/course.ece.cmu.edu\/~ece500\/projects\/s21-teamb2\/wp-content\/uploads\/sites\/124\/2021\/03\/Capture.jpg 419w\" sizes=\"(max-width: 300px) 85vw, 300px\" \/><\/li>\n<li>Still requires more epochs until convergence.<\/li>\n<\/ul>\n<\/li>\n<li>Created simple clothing recognition API with aforementioned models. Currently returns top 10 most likely bounding boxes and labels.<\/li>\n<\/ul>\n<p>For Next Week:<\/p>\n<ul>\n<li>Finish training models and perform fine-tuning.<\/li>\n<li>Start training models for more fine-grained classification like shape and material.<\/li>\n<li>Implement color classification.<\/li>\n<li>Right now detector could predict differently from classifier. I&#8217;m not sure what to do when this happens, but I should figure it out.<\/li>\n<\/ul>\n<p>I am slightly ahead of schedule.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>The past two weeks I worked on: Finished the design report. I wrote most of the documentation on the visualizer component. formatted datasets for training. Detector required tfrecord files from DeepFashion2 dataset while classifier required images sorted into classes from DeepFashion dataset. Trained a clothing detector that detects bounding boxes and does simple classification of &hellip; <a href=\"https:\/\/course.ece.cmu.edu\/~ece500\/projects\/s21-teamb2\/2021\/03\/27\/henrys-status-report-for-3-27-2021\/\" class=\"more-link\">Continue reading<span class=\"screen-reader-text\"> &#8220;Henry&#8217;s Status Report for 3\/27\/2021&#8221;<\/span><\/a><\/p>\n","protected":false},"author":385,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":[],"categories":[9],"tags":[],"_links":{"self":[{"href":"https:\/\/course.ece.cmu.edu\/~ece500\/projects\/s21-teamb2\/wp-json\/wp\/v2\/posts\/105"}],"collection":[{"href":"https:\/\/course.ece.cmu.edu\/~ece500\/projects\/s21-teamb2\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/course.ece.cmu.edu\/~ece500\/projects\/s21-teamb2\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/course.ece.cmu.edu\/~ece500\/projects\/s21-teamb2\/wp-json\/wp\/v2\/users\/385"}],"replies":[{"embeddable":true,"href":"https:\/\/course.ece.cmu.edu\/~ece500\/projects\/s21-teamb2\/wp-json\/wp\/v2\/comments?post=105"}],"version-history":[{"count":1,"href":"https:\/\/course.ece.cmu.edu\/~ece500\/projects\/s21-teamb2\/wp-json\/wp\/v2\/posts\/105\/revisions"}],"predecessor-version":[{"id":108,"href":"https:\/\/course.ece.cmu.edu\/~ece500\/projects\/s21-teamb2\/wp-json\/wp\/v2\/posts\/105\/revisions\/108"}],"wp:attachment":[{"href":"https:\/\/course.ece.cmu.edu\/~ece500\/projects\/s21-teamb2\/wp-json\/wp\/v2\/media?parent=105"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/course.ece.cmu.edu\/~ece500\/projects\/s21-teamb2\/wp-json\/wp\/v2\/categories?post=105"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/course.ece.cmu.edu\/~ece500\/projects\/s21-teamb2\/wp-json\/wp\/v2\/tags?post=105"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}