Open LUO77123 opened 2 years ago
Here I give some experience in my UniFormer, you can also follow our work to do it~
drop_path_rate
has been used in the models. As for dropout
, it does not work if you have used droppath
.Here I give some experience in my UniFormer, you can also follow our work to do it~
drop_path_rate
has been used in the models. As fordropout
, it does not work if you have useddroppath
.- All the backbones are the same in both classification, detection and segmentation.
最后想请问一下,在cswin.py的159行 if last_stage: self.branch_num = 1,165-171行表明最后一层 LePEAttention只执行一次(因为224的输入,最后一层特征图是7x7,所以窗口就是7x7),但是用在下游检测任务,最后一层特征图不是77(以896为例,最后一层特征图是28x28,如果 LePEAttention只执行一次,那么窗口就是28x28),所以对于下游任务,最后一层 LePEAttention只执行几次喃(1还是2)?但是给的预训练权重,因为都是224224(窗口7x7)或者384384(窗口12x12),最后一层LePEAttention只执行一次,没有2次的预训练权重,作者是怎么用到下游任务的喃
这样一看,swin用的固定7x7窗口在下游任务(如检测)上如果不进行fine-tuning的话对于stage4来说也不是full-attention,这里应该也是默认这种情况的,所以这里对于下游任务来说stage4应该可以看做7x7的swin咯
这样一看,swin用的固定7x7窗口在下游任务(如检测)上如果不进行fine-tuning的话对于stage4来说也不是full-attention,这里应该也是默认这种情况的,所以这里对于下游任务来说stage4应该可以看做7x7的swin咯
7x7就需要2个LePEAttention,这样导入权重就只能导入四分之三,直接用整个特征图吧
1.Since drop_rate, attn_drop_rate and drop_path_rate are 0 by default, drop_path is not enabled.I want to know how much drop_path_rate , attn_drop_rate and drop_path_rate are set, and the effect of the model will be better.thanks! 由于 drop_rate, attn_drop_rate和drop_path_rate默认为0,未启用drop_path,想知道将drop_path_rate, attn_drop_rate和drop_path_rate 设置为多少,模型的效果会好一点()论文没有提到,源码默认为0)。谢谢! 2.The model compares Swin as a backbone on Mask R-CNN. I want to know whether the initial channel number (DIM) of Swin-T is 96 and that of CSwin-T is 64, that is, is CSwin-T configured in the detection network backbone in the following table? Models #Dim #Blocks sw #heads #Param. FLOPs CSWin-T 64 1,2,21,1 1,2,7,7 2,4,8,16 23M 4.3G CSWin-S 64 2,4,32,2 1,2,7,7 2,4,8,16 35M 6.9G CSWin-B 96 2,4,32,2 1,2,7,7 4,8,16,32 78M 15.0G CSWin-L 144 2,4,32,2 1,2,7,7 6,12,24,48 173M 31.5G 模型在Mask R-CNN上作为Backbone对比了SWin,我想知道Swin-T的初始通道数(dim)是96,而CSWin-T的初始通道数(dim)是64吗,也就是说CSWin-T是下表配置在检测网络backbone中吗? Models #Dim #Blocks sw #heads #Param. FLOPs CSWin-T 64 1,2,21,1 1,2,7,7 2,4,8,16 23M 4.3G CSWin-S 64 2,4,32,2 1,2,7,7 2,4,8,16 35M 6.9G CSWin-B 96 2,4,32,2 1,2,7,7 4,8,16,32 78M 15.0G CSWin-L 144 2,4,32,2 1,2,7,7 6,12,24,48 173M 31.5G