Distilling-Object-Detectors
Distilling-Object-Detectors copied to clipboard
twangnh
SSD
你好，我想问下那个resnet50-h是通道数为一半的resnet50而不是float16的resnet50？
---Original--- From: "twang"[email protected] Date: Fri, Jun 14, 2019 18:11 PM To: "twangnh/Distilling-Object-Detectors"[email protected]; Cc: "Author"[email protected];"疯狂三角肌"[email protected]; Subject: Re: [twangnh/Distilling-Object-Detectors] SSD (#2)
Hi, currently I dont have ssd results
— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub, or mute the thread.
The resnet50-h is obtained with halving each layer's channel number of resnet50
谢谢，还有一个问题您的论文中frcnn使用的是roipooling还是roialign？因为我在做过实验室roipooling和roipooling差别很大的。
---Original--- From: "twang"[email protected] Date: Wed, Jun 19, 2019 11:01 AM To: "twangnh/Distilling-Object-Detectors"[email protected]; Cc: "Author"[email protected];"疯狂三角肌"[email protected]; Subject: Re: [twangnh/Distilling-Object-Detectors] SSD (#2)
the resnet50-h is obtained with halving each layer's channel number of resnet50
— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub, or mute the thread.
I have seen your project on github, it is interesting that roialign and roipooling have so large difference on distillation results, do you have any update for the issue?
你可以用gluoncv去做下实验，差别很大。
---Original--- From: "twang"[email protected] Date: Tue, Jun 25, 2019 12:49 PM To: "twangnh/Distilling-Object-Detectors"[email protected]; Cc: "Author"[email protected];"疯狂三角肌"[email protected]; Subject: Re: [twangnh/Distilling-Object-Detectors] SSD (#2)
I have seen your project on github, it is interesting that roialign and roipooling have so large difference on distillation results, do you have any update for the issue?
— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub, or mute the thread.
你可以用gluoncv去做下实验，差别很大。 …
我想问一下您复现的Fine Grained feature imitation实验中roi Align和roi pooling效果会差多少？论文中roi Align提升约2.9%，那么如果是roi pooling大约提升多少呢？
看他github的
---Original--- From: "DliHjiang"<[email protected]> Date: Wed, Mar 18, 2020 14:51 PM To: "twangnh/Distilling-Object-Detectors"<[email protected]>; Cc: "Author"<[email protected]>;"疯狂三角肌"<[email protected]>; Subject: Re: [twangnh/Distilling-Object-Detectors] SSD (#2)
你可以用gluoncv去做下实验，差别很大。 …
我想问一下您复现的Fine Grained feature imitation实验中roi Align和roi pooling效果会差多少？论文中roi Align提升约2.9%，那么如果是roi pooling大约提升多少呢？
— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub, or unsubscribe.
看他github的 … ---Original--- From: "DliHjiang"<[email protected]> Date: Wed, Mar 18, 2020 14:51 PM To: "twangnh/Distilling-Object-Detectors"<[email protected]>; Cc: "Author"<[email protected]>;"疯狂三角肌"<[email protected]>; Subject: Re: [twangnh/Distilling-Object-Detectors] SSD (#2)
你可以用gluoncv去做下实验，差别很大。 …
我想问一下您复现的Fine Grained feature imitation实验中roi Align和roi pooling效果会差多少？论文中roi Align提升约2.9%，那么如果是roi pooling大约提升多少呢？
— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub, or unsubscribe.
哪里可以看到数据对比呢，我看您的GAN-KD论文里也没有Fine Grained feature imitation方法的roi align和roi pooling的对比，我最近尝试了带fpn的faster rcnn应用Fine Grained feature imitation方法，用的roi pooling，但是发现蒸馏后的结果比学生的基线还低，所以比较困惑，请问您那边实验的结果是什么样的呢？roi pooling会有提升吗？