Hi Steve,
The only log file generated was logMatlab.txt; .fix.log and .fix_2b_predict.log were never generated (I've also checked hidden files)
The only error listed within logMatlab.txt is:
Error Time: 10/13/2016 15:31:23
Error using horzcat
Dimensions of matrices being concatenated are not consistent.
As for my hand label files, they all have the following syntax:
[1, 2, 5, 7, ..., 87] (followed by an empty line - i.e. I hit return afterwards)
(this is the syntax that was specified in other posts on this issue)
I tried also tried running FIX using the supplied Standard.RData training weights and I have this same error having to do with horzcat; what is FIX concatenating here and why might the dimensions be inconsistent?
This is the output from the command line:
create edge masks
run FAST
registration of standard space masks
extract features
No valid training file specified
No valid labelling file specified
Thanks again!
Hi - have you looked in the various log files (including IIRC some starting with ".") that FIX leaves around?
We've seen similar issues in the past when people have been using incorrectly put-together hand-label files to feed into the training so it's worth checking on that and on that issue in the email archives.
Cheers, Steve.
On 12 Oct 2016, at 21:21, SUBSCRIBE FSL Anonymous <[log in to unmask]> wrote:
Hi,
I'm currently trying to train FIX using the /fix -t command. i.e. ./fix -t Training.RData -l <melodic_output.ica>
After looking at the postings of users with similar issues, I checked the logMatlab.txt file. Similar to what Madelyn Glymour experienced, this file reads:
Error using horzcat
Dimensions of matrices being concatenated are not consistent.
So it seems that the feature extraction step fails, and FIX is unable to generate a features.csv file
How can this issue be resolved? There didn't seem to be a resolution in Madelyn's posting.
Thanks very much for your assistance!
FYI: I've previously been able to fully run FIX, using Standard.RData, with success; However I would now like to use FIX with my own trained data and am running into difficulty.
Further question: is it necessary to have Melview installed, in order to train fix? My understanding is that this is only a viewer and so should not be required for FIX training.
---------------------------------------------------------------------------
Stephen M. Smith, Professor of Biomedical Engineering
Head of Analysis, Oxford University FMRIB Centre
FMRIB, JR Hospital, Headington, Oxford OX3 9DU, UK
+44 (0) 1865 222726 (fax 222717)
[log in to unmask] http://www.fmrib.ox.ac.uk/~steve
---------------------------------------------------------------------------
Stop the cultural destruction of Tibet
|