Comments (1)
lenck
commented on May 6, 2024
Hi,
have you tried to profile it to see what takes the most of the time? (e.g. described here)
The 128x128 sized output is quite big and it means that each time it has to create new (presumably GPU) variable c_ on line 46 with ~1.6M elements so this may cause the biggest overhead...
If the creation of a new variable would be the biggest bottleneck, then probably creating a new custom layer which would take as argument list of indicies c_ instead of the class labels maybe a solution. If the indexing would be the problem (e.g. that matlab is not able to effectively serialise line 58) then probably writing custom kernel for that may be the way to go...
from matconvnet.
Related Issues (20)
- Latest versions vl_compilenn fail
- vl_compilenn directory
- Error in vl_testnn('gpu', true). MATLAB: mex: ErrInvalidMEXFile
- Error vl_compilenn('enableGpu', true) HOT 1
- cuda11.1 HOT 1
- 未定义的函数 'vl_testnn'
- this is why
- D:\Software\matconvnet-1.0-beta25\matlab\src\bits\datacu.hpp(89): error: identifier "cudnnConvolutionFwdPreference_t" is undefined D:\Software\matconvnet-1.0-beta25\matlab\src\bits\datacu.hpp(94): error: identifier "cudnnConvolutionBwdFilterPreference_t" is undefined D:\Software\matconvnet-1.0-beta25\matlab\src\bits\datacu.hpp(99): error: identifier "cudnnConvolutionBwdDataPreference_t" is undefined D:\Software\matconvnet-1.0-beta25\matlab\src\bits\datacu.hpp(141): error: identifier "cudnnConvolutionFwdPreference_t" is undefined D:\Software\matconvnet-1.0-beta25\matlab\src\bits\datacu.hpp(147): error: identifier "cudnnConvolutionBwdFilterPreference_t" is undefined D:\Software\matconvnet-1.0-beta25\matlab\src\bits\datacu.hpp(153): error: identifier "cudnnConvolutionBwdDataPreference_t" is undefined 6 errors detected in the compilation of "D:/Software/matconvnet-1.0-beta25/matlab/src/bits/data.cu". HOT 1
- every time i reopen the matlab porject，need to recompile the matconvnet，why？
- Question about the matrix format of vgg19
- Error in vl_compilenn>mex_compile (line 583) and vl_compilenn (line 492) HOT 1
- How to solve?
- The NVCC compiler 'C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v10.2\bin\nvcc' does not appear to be valid. HOT 1
- Issue when compiling with GPU enabled HOT 1
- error in vl_compilenn HOT 1
- Is vl_nnconv implemented based on the FFT operator? HOT 1
- Convert pytorch model to matconvnet model
- Matlab crack after run again Matconvnet
- Reference to non-existent field ‘dilate‘.
- Have trouble compiling MatConvNet
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
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.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from matconvnet.