Pruning faster RCNN for my datasets(vgg 2x)

[liangzz1991]

you only give the pruned .prototxt for VOC datasets, but i want to get the pruned model of faster_vgg2x for my own datasets, what should I do??? if i also use this network structure of prototxt, i need the pre-trained ImageNet models of network structure of prototxt(vgg 2x).

[ethanhe42]

just finetune it for your dataset

[liangzz1991]

@yihui-he finetune need the pre-trained ImageNet models of pruned vgg(conv1_1 :output=11,etc), if I use a standard structure of vgg to finetune, these conv layers will not be assigned parameters, what should I do?

[ethanhe42]

I mean just use my faster rcnn to finetune

On Wed, Nov 15, 2017 at 5:59 PM, liangzz1991 notifications@github.com wrote:

@yihui-he https://github.com/yihui-he finetune need the pre-trained ImageNet models of pruned vgg(conv1_1 :output=11,etc), if I use a standard structure of vgg to finetune, these conv layers will not be assigned parameters, what should I do?

— You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub https://github.com/yihui-he/channel-pruning/issues/62#issuecomment-344791044, or mute the thread https://github.com/notifications/unsubscribe-auth/AJkBS7sI-zkUrfF6lkmQimGKjZ_nrubFks5s25blgaJpZM4Qc6QM .

-- Best, Yihui He yihui-he.github.io

[liangzz1991]

@yihui-he thank you

[ethanhe42]

you can download the pretrained ImageNet models now: https://github.com/yihui-he/channel-pruning/releases/tag/faster-RCNN-2X4X