Comments (5)
Which system do you use? Could you check is your "vllab_dag_loss.m" copied to matconvnet/matlab/+dagnn properly? If not, you have to manually copy it. Some people report that the copy command in MATLAB does not work on Window 10.
from lapsrn.
My system is ubuntu 14.04. The environment is matlab R2015b + CUDA8.0.
My matconvnet is installed in this path /usr/local/MATLAB/R2015b/toolbox/Matconvnet/matconvnet-1.0-beta24. I have tried install.m and is successful. I also tried copy "vllab_dag_loss.m" to matconvnet/matlab/+dagnn. But it just can not found this object. The errors are like this:
demo_LapSRN
Warning: Name is nonexistent or not a directory:
/media/trillionpowers/Data/Work/RL_SR/Basical_Model/LapSRN_model/LapSRN-master/usr/local/MATLAB/R2015b/toolbox/Matconvnet/matconvnet-1.0-beta24/matlab
In path (line 109)
In addpath (line 88)
In demo_LapSRN (line 25)
Load pretrained_models/LapSRN_x4.mat
Error using dagnn.DagNN.loadobj
Error: File: loadobj.m Line: 26 Column: 5
The input character is not valid in MATLAB statements or expressions.
Error in demo_LapSRN (line 33)
net = dagnn.DagNN.loadobj(net.net);
Thank you for your help. @phoenix104104
from lapsrn.
You should copy vllab_dag_loss.m to your own MatConvNet path. In your case, it's
/usr/local/MATLAB/R2015b/toolbox/Matconvnet/matconvnet-1.0-beta24/matlab/+dagnn
from lapsrn.
Sure. I have copied this file to this path many times and use 'vl_compilenn('enableGPu', true);' to compile.
But I still have this error when I run 'demo_LapSRN.m' and 'train_LapSRN.m'.
I have tried to Change permissions of this file in 777. But it still can not run.
Thank you for your help. @phoenix104104
from lapsrn.
Thanks a lot. I reboot my system and make it again. It's run !
from lapsrn.
Related Issues (20)
- what is the version of MatConvNet used in this code? HOT 2
- Error occurs when loading pre-trained_models HOT 1
- Error occurs when runnig demo_LapSRN.m HOT 1
- The number of epoch HOT 1
- the download link of dataset is invalid HOT 2
- Python source code HOT 2
- The Set5 (x4) result reported reproduce HOT 4
- Some questions about bilinear_kernel.m
- T91 and BSD200 are HR or LR images? HOT 3
- what should i do if i want to test a gray scale image? HOT 1
- SR video HOT 1
- PSNR HOT 1
- Train Loss HOT 1
- Some questions about the final images HOT 2
- Error when installing MatConvNet as shown on the page. HOT 4
- About the training dataset HOT 2
- train problem and times about cpu
- test dataset link 403 problem HOT 1
- Datasets URL was not found
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 lapsrn.