search

backseason / PoolNet

Code for our CVPR 2019 paper "A Simple Pooling-Based Design for Real-Time Salient Object Detection"
MIT License
630 stars 153 forks source link

Compression network #77

Closed ljc19940403 closed 3 years ago

ljc19940403 commented 3 years ago

Recently, I have been thinking about whether it is possible to reduce the size of model parameters only by reducing part of network parameters without pruning and quantization. If this is possible, could you give me your suggestions

backseason commented 3 years ago

In the extended version of this paper, we have largely reduced the parameters of the model without pruning and quantization. Since the paper is still under submission, I cannot disclose more details at this time.

kobe @.***> 于2021年3月31日周三 下午7:56写道：

Recently, I have been thinking about whether it is possible to reduce the size of model parameters only by reducing part of network parameters without pruning and quantization. If this is possible, could you give me your suggestions

— You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub https://github.com/backseason/PoolNet/issues/77, or unsubscribe https://github.com/notifications/unsubscribe-auth/ABYO2ODQX3ZWGDVESPBVBUDTGMEU7ANCNFSM42EO55RQ .

--

From BackSeason-刘姜江 Major in Computer Science and Technology Nankai University, Tianjin,300350 P.R.China @. @.>

ljc19940403 commented 3 years ago

In the extended version of this paper, we have largely reduced the parameters of the model without pruning and quantization. Since the paper is still under submission, I cannot disclose more details at this time. kobe @.> 于2021年3月31日周三 下午7:56写道： … Recently, I have been thinking about whether it is possible to reduce the size of model parameters only by reducing part of network parameters without pruning and quantization. If this is possible, could you give me your suggestions — You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub <#77>, or unsubscribe https://github.com/notifications/unsubscribe-auth/ABYO2ODQX3ZWGDVESPBVBUDTGMEU7ANCNFSM42EO55RQ . -- From BackSeason-刘姜江 Major in Computer Science and Technology Nankai University, Tianjin,300350 P.R.China @. @.***> Looking forward to seeing your research results