no net component in the dagnet.net from demo.m file about dbcnn

[zwx8981]

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.

[fbiying87]

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!

[fbiying87]

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!

[zwx8981]

I didn't meet this error before. Have you tried setting opts.randomSeed=1?