iamhankai / versatile-filters Goto Github PK
View Code? Open in Web Editor NEWPytorch code for paper: Learning Versatile Filters for Efficient Convolutional Neural Networks (NeurIPS 2018)
License: BSD 3-Clause "New" or "Revised" License
Pytorch code for paper: Learning Versatile Filters for Efficient Convolutional Neural Networks (NeurIPS 2018)
License: BSD 3-Clause "New" or "Revised" License
Hi, I think the original code emphasizes "sharing the same weights" across all input channels, ensuring that every channel influences the weight update. In contrast, this approach allows only a subset of input channels to be involved in weight updates (a little bit of cross interaction of input channels since the update of weight is sliding along input channels dimension?), similar to group convolution when the number of channels in a group is c_hat. Am I right?
https://github.com/huawei-noah/Versatile-Filters/blob/master/vcnn.py#L56
The original code is:
weight1 = self.weight[:, :ch_len, s:self.kernel_size[0]-s, s:self.kernel_size[0]-s]
I think it should be as the Fig2(b) in the paper:
weight1 = self.weight[:, start:start+ch_len, s:self.kernel_size[0]-s, s:self.kernel_size[0]-s]
is it right?
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.