03 2018 档案

CS231n笔记 Lecture 11, Detection and Segmentation
摘要：Other Computer Vision Tasks Semantic Segmentation. Pixel level, don't care about instances. Classification + Localization. Single object. Object Detec 阅读全文
posted @ 2018-03-04 16:27 ichneumon 阅读(564) 评论(0) 推荐(0)
CS231n笔记 Lecture 10, Recurrent Neural Networks
摘要：Recaption on CNN Architecture Although Serena is very beautiful, Justin is a better lecturer. Love him. Recurrent Neural Network Meant to process sequ 阅读全文
posted @ 2018-03-04 11:32 ichneumon 阅读(552) 评论(0) 推荐(0)
CS231n笔记 Lecture 9, CNN Architectures
摘要：Review: LeNet-5 1998 by LeCun, one conv layer. Case Study: AlexNet [Krizhevsky et al. 2012] It uses a lot of mordern techniques where is still limited 阅读全文
posted @ 2018-03-03 21:28 ichneumon 阅读(596) 评论(0) 推荐(0)
CS231n笔记 Lecture 8, Deep Learning Software
摘要：CPU and GPU If you aren’t careful, training can bottleneck on reading data and transferring to GPU! Solutions: - Read all data into RAM - Use SSD inst 阅读全文
posted @ 2018-03-03 17:21 ichneumon 阅读(395) 评论(0) 推荐(0)
CS231n笔记 Lecture 7, Training Neural Networks, Part 2
摘要：Review Activation Functions. Sigmoid, tanh, ReLU(good default choice). Optimization Optimization algorithms SGD. Problems: jitering or stop at saddle 阅读全文
posted @ 2018-03-03 15:59 ichneumon 阅读(282) 评论(0) 推荐(0)