Open David-Jin opened 7 years ago
You could adjust according to various of scripts I provided.
I personally don't see strong evidence of the advantage of ResNet over VGGNet in the SSD framework.
@David-Jin Maybe, because VGG16 is pretrained on the ILSVRC CLS-LOC dataset, but ResNet is not pretrained on the ILSVRC CLS-LOC dataset. @weiliu89 Did you test the map of ssd model using VGG16 pretrained only imagenet cls task dataset?
@XHUJOY ResNet has shown some advantage over VGGNet under Faster R-CNN framework. Maybe I didn't use ResNet in the most optimal way, or maybe my (reduced) VGGNet baseline is better than the one which is used in Faster R-CNN.
is the reduced VGGNet trained by youself? I can't find the paper about the model and i know deeplab use the same arch which initted by gaussian random value.
@XHUJOY I manually subsampled parameters from fc6 and fc7 of the original VGGNet. I don't think deeplab is trained from scratch.
Hi, could you please comment on SSD runtime with ResNet-101 compared to VGG-16 reduced. In theory ResNet should be faster with less Flops, but in my runs I see x3 slower performance. Using GTX 1080 with cuda7.5+cudnn v5 on 300x300 input.
@borissherman in my experience, the GTX 1080 need cuda8.0
@zt706 Yes, thanks, found that also, x1.5 improvement with cuda 8.0 on GTX 1080.
I also don't see strong evidence of the advantage of ResNet50 over VGGNet16 ,maybe VGGNet is enough for detection mission. darknet19 is even more simple than VGGNet
@weiliu89 Hi, I know you just added scripts for training ResNet under SSD branch.