Comments (4)
Hi,
You need to first train the DB-CNN on a database, the checkpoint will be automatically saved. Then you can load the checkpoint to test an image as in the demo.
imdb-seed-1.mat is the file containing the meta information that you need use to train and test the model.
We do not release the pre-trained DBCNN model in the github.
from dbcnn.
thanks for your reply. I will try to train a simple model. Hopefully, it won't take too long, as I only have cpu on my laptop. :-)
Best regards!
from dbcnn.
Thanks for your reply. I am currently working on downloading the correct databases. As for LIVE, they have a first and second release versions, can you provide a link to the database which you used to train the model please?
I noticed, that you used the release 2. Thanks.
I started training by running the run_exp script. But I received the following error. Should I set the opts.randomSeed=1?
Initialization: extracting bcnn feature of batch 98/98
layer| 0| 1| 2|
type| input| conv| pdist|
name | n/a | convfc | loss |
---|---|---|---|
support | n/a | 1 | 1 |
filt dim | n/a | 65536 | n/a |
filt dilat | n/a | 1 | n/a |
num filts | n/a | 1 | n/a |
stride| n/a| 1| 1|
pad| n/a| 0| 0|
----------|-------|-------|-------|
rf size| n/a| 1| 1|
rf offset| n/a| 1| 1|
rf stride | n/a | 1 | 1 |
---|---|---|---|
data size | NaNxNaN | NaNxNaN | NaNxNaN |
data depth | NaN | 1 | 1 |
data num | 8 | 8 | 8 |
---------- | ------- | ------- | ------- |
data mem | NaN | NaN | NaN |
param mem | n/a | 256KB | 0B |
parameter memory|256KB (6.6e+04 parameters)|
data memory| NaN (for batch size 8)|
Error using rng (line 96)
The current random number generator is the legacy generator. This is because you have executed a command such as rand('state',0), which activates MATLAB's legacy random
number behavior. You may not use RNG to reseed the legacy random number generator.
Use rng('default') to reinitialize the random number generator to its startup configuration, or call RNG using a specific generator type, such as rng(seed,'twister').
Error in cnn_train (line 136)
rng(epoch + opts.randomSeed) ;
Error in initializeNetworkTwoStreams (line 280)
[netc, info] = cnn_train(netc, bcnndb, @getBatch_bcnn_fromdisk, opts.inittrain, ...
Error in imdb_bcnn_train_dag (line 70)
net = initNetFn(imdb, encoderOpts, opts);
Error in run_experiments_bcnn_train (line 37)
end
Error in run_exp (line 62)
[options, imdb] = run_experiments_bcnn_train(opts);
Thanks a lot!
from dbcnn.
I didn't meet this error before. Have you tried setting opts.randomSeed=1?
from dbcnn.
Related Issues (13)
- the cross dataset test problem HOT 4
- 关于程序 HOT 4
- Pre-trained model
- Which model should I use to test on the waterloo dataset? HOT 6
- Can your provide a link to download the Live Challenge? HOT 4
- 训练时出现DEROUTPUT dimensions are incompatible with X and FILTERS HOT 3
- error finding a file HOT 2
- where can I found the SCNN labels HOT 4
- Error in vl_imreadjpeg() HOT 1
- 关于训练的问题 HOT 3
- Wrong use of vl_argparse HOT 2
- 您好,看到您的一些关于图像质量评价的介绍,想问您个问题,就是BLIINDS-II无参考的指标,我在github上复现了几个matlab的代码,文章中介绍BLIINDS-II越大表明图像质量越好,但是我复现的代码结果是相反的,请问您有这个BLIINDS-II代码吗? HOT 2
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 dbcnn.