Code Monkey home page Code Monkey logo

mabn's People

Contributors

junjie18 avatar ohyeat avatar ruosone avatar

Stargazers

avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar

Watchers

avatar avatar avatar avatar avatar avatar avatar avatar

Forkers

robot-ai-machinelearning davis-love-ai happog xrosliang marmotatzju guidewsp wanglixilinx unsky t1anzhenyu liuguoyou ingeniousfrog hzhang57 cxmscb dilinwang820 yutpa abhishek-prusty czifan zmhuang8 mldl yuanwei0908 kiminh dllinks liuyundong-2020 zsh965866221 weiguangfan myfamily111 canghaiwuya

mabn's Issues

det finetune's result is poor

det from_scratch seems fine, with 36.4 AP
but fine_tune only has 19.6 AP
the only thing I modified is reusing the MSRA weight

WEIGHT: "catalog://ImageNetPretrained/MSRA/R-50"

and register "R-50-FPN-MABN" to load_resnet_c2_format accordingly.

Furthermore, the native e2e_mask_rcnn_R_50_FPN_1x doesn't work anymore, the box_roi gradients would blow up in a few iterations. It seems toe be a FPN problem, since C4 model can still be trained.

ps: I am running on coco2017 dataset, but it can't be the problem

Replacing only GroupNorm with MABN

Hi
Do you think it's possible to replace only GroupNorm part with MABN and the according Conv with CenConv, the rest of well-pretrained Conv+Bn remaining the same? I followed this kind of setting to maskrcnn with MobileNet backbone and also faced the nan training problem. I don't realize the nan problem coming from which part of codes. Deos MABN works only when the whole network deploying Centralized Weight, or theoretically part of it just fine? Thanks.

MABN code is wrong

According to your code, the sta_matrix is a [16, 32] shape tensor

MABN/cls/networks/MABN.py

Line 82 in 19e897f

self.register_buffer('sta_matrix', torch.ones(self.B, 2 *self.B)/self.B)

But the var is a [16+N//2, C] shape tensor, the torch.mm API totally got errors to compute this matrix multiple of this two tensor.

MABN/cls/networks/MABN.py

Line 21 in 19e897f

var = torch.mm(sta_matrix, var)

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.