mcimpoi / deep-fbanks Goto Github PK

Hi, when I try to run run_experiments.m the code I get an "out of range" in get_dcnn_features.m (ln130).

While running the code, I noticed that v and u, defined in get_dcnn_features.m (ln117) get negative values. Is that OK?

Can someone help?

Thank you,
Daniel

(I am facing this error when I run the run_experiments.m file) Please suggest how to tackle this error

Hi,
While training on OS data, I get error while computing the confusion matrix. What could be the problem here? Any help would be highly appreciated.
Thank you.

I got a 14 GB code(FV descriptor for DCNN on OpenSurface Dataset), which is too large to get an Out of Memory error in ostrain.m line 280: code = cat(2, code{:}) ;

But my memory space is quite large: 15GB physical memory and 14GB swap space.

How do you solve this Out of Memory problem?

When i run the code i get this error which is generated in line 74 of the vl_argparse.m file.
"The value of parameters in structure in args but not a structure in opts".
I am trying to solve this issue from a long time. i am running on dtd dataset and the cpu version. Please help me

HI,

Please can you help me on where i need to collect feature vectors (which variable gives feature values) before applying any encoders (vlad, fisher..)

Thanking you

Hi!
I setup code and dependencies as shown in README but when I run 'run_experiments.m' I get the error:

Error using get_dcnn_features (line 58)
Reference to non-existent field 'normalization'.

The same downloading matconvnet@59463fc or last version from website.

What could be?
Thanks in advance.

i am a newcomer and the folder is not complete,need to be create? and how to use the gitignore file

Hi. I successfuly compiled two dependencies on Ubuntu 16.04 with CUDA 10.0 and MATLAB R2019b. There seems to be no issue running the MatConvnet demo. But I got this error when I am trying to run run_experiments.m

Error using vl_argparse (line 52)
The name of the parameter number 1 is not a string.

Error in vl_nnrelu (line 41)
opts = vl_argparse(opts, varargin, 'nonrecursive') ;

Error in vl_simplenn (line 336)
      res(i+1).x = vl_nnrelu(res(i).x,[],leak{:}) ;

Error in get_dcnn_features (line 111)
      res = vl_simplenn(net, im_resized, [], res, ...

Error in os_train>get_batch_results (line 319)
    code_ = get_dcnn_features(encoder.net, ...

Error in os_train>encoder_extract_for_segments (line 269)
parfor (b = 1:numel(batches), numWorkers)

Error in os_train>encoder_train_from_segments (line 393)
code = encoder_extract_for_segments(encoder, imdb, segmentIds) ;

Error in os_train (line 27)
        encoder = encoder_train_from_segments(...

Error in run_experiments (line 109)
        os_train(...

Is it possible to fix it? Thank you very much for your time!

Hello how to identify the results,what will it be like?
kindly could u help it

For newer versions of MATLAB, matlabpool is deprecated and needs to be replaces with parpool.