
paper
文章平均质量分 97
Ashley-Yu
这个作者很懒,什么都没留下…
展开
-
FCOS论文及源码详解(七)
FCOS论文及源码详解(七)原创 2020-12-12 16:08:46 · 1024 阅读 · 5 评论 -
FCOS论文及源码详解(六)
FCOS论文及源码详解(六)原创 2020-12-12 11:16:44 · 1091 阅读 · 0 评论 -
FCOS论文及源码详解(五)
FCOS论文及源码详解(五)原创 2020-12-10 20:11:37 · 1647 阅读 · 0 评论 -
FCOS论文及源码详解(四)
FCOS论文及源码详解(四)原创 2020-12-08 21:30:55 · 1292 阅读 · 0 评论 -
FCOS论文及源码详解(三)
FCOS论文及源码详解(三)原创 2020-12-07 15:30:55 · 1109 阅读 · 0 评论 -
FCOS论文及源码详解(二)
FCOS论文及源码详解(二)原创 2020-12-06 10:53:46 · 1992 阅读 · 0 评论 -
FCOS论文及源码详解(一)
FCOS论文及源码详解(一)FCOS论文Fully Convolutional One-Stage Object DetectorMulti-level Prediction with FPN for FCOSCenter-ness for FCOS参考文献FCOS论文以下内容摘自论文(FCOS: Fully Convolutional One-Stage Object Detection),本人英语水平极差,翻译勉强看看就好Almostall state-of-the-art object dete原创 2020-12-02 12:15:01 · 3594 阅读 · 0 评论 -
Papers Notes_7_ Batch Normalization--Batch Normalization: Accelerating Deep Network Training by...
Papers Notes_7_ Batch Normalization--Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate ShiftIntroductionBatch NormalizationalgorithmworksbenefitReferencesIntroductionmini-batchestimate the gradient over the training原创 2021-09-07 15:29:15 · 252 阅读 · 0 评论 -
Papers Notes_6_ DCGAN--Unsupervised Representation Learning with Deep Convolutional GAN
Papers Notes_6_ DCGAN--Unsupervised Representation Learning with Deep Convolutional GANApproachArchitectureApproachscale up GANs using CNNs to model imagesthe all convolutional netreplace deterministic spatial pooling functions (such as maxpooling) wi原创 2021-09-06 18:13:13 · 183 阅读 · 0 评论 -
Papers Notes_5_ GAN--Generative Adversarial Nets
Papers Notes_5_ GAN--Generative Adversarial NetsAdversarial NetsReferencesAdversarial Netsdiscriminative modelgenerative modelReferencesDeep Residual Learning for Image Recognition原创 2021-08-07 20:19:41 · 232 阅读 · 0 评论 -
Papers Notes_4_ ResNet--Deep Residual Learning for Image Recognition
Papers Notes_4_ ResNet--Deep Residual Learning for Image RecognitionNetwork DepthResidual MappingArchitectureNetwork Depthnetwork depth is of crucial importance, and the leading results on the challenging ImageNet dataset all exploit “very deep” models,原创 2021-07-25 12:35:17 · 385 阅读 · 0 评论 -
Papers Notes_3_ GoogLeNet--Going deeper with convolutions
Papers Notes_3_ GoogLeNet--Going deeper with convolutionsArchitectureInception moduleGoogLeNetArchitectureInception moduleparallel conv. with different kernel sizevisual information should be processed at various scales and then aggregated→the next原创 2021-07-22 19:33:45 · 387 阅读 · 0 评论 -
Papers Notes_2_ VGG--Very Deep Convolutional Networks for Lage-scale Image Recognition
Papers Notes_2_ VGG--Very Deep Convolutional Networks for Lage-scale Image RecognitionArchitectureTrainingArchitectureinput-224×224 RGB imagepreprocess-subtract the mean RGB value,computed on the training set,from each pixelstride-fixed to 1 pixelpad原创 2021-07-21 11:06:31 · 242 阅读 · 0 评论 -
Papers Notes_1_ AlexNet--ImageNet Classification with Deep Convolutional Neural Networks
Papers Notes_1_ AlexNet--ImageNet Classification with Deep Convolutional Neural NetworksArchitectureReLU NonlinearityLocal Response NormalizationOverlapping PoolingOverall ArchitectureReducing OverfittingData AugmentationDropoutDetails of LearningReference原创 2021-07-20 10:31:14 · 153 阅读 · 0 评论