not match the number of voxles of mask and dataset

Hi,

I’m doing MVPA using 3dsvm, and I’m having trouble making a training model.
Using functional localizer, I’ve made an MT mask where there are 75 voxels.
With this and beta dataset to be trained, I tried making a model. Below is the command lines:
3dsvm -trainvol trainBlock.nii
-trainlabels trainLabel.1D
-model trainSet.model.nii
-mask ${baseDir}/roiMT.top75.nii

But there was FATAL ERROR as:
Number of voxels in mask file: ‘/Users/minsunpark/Desktop/MyMVPA/Analyzed_Data/mae4lhs/MT/3dDec/roiMT.top75.nii’ and training dataset: ‘trainBlock.nii’ do not match.

So I looked into the 3dinfo, then the number of voxels in each three directions are different between trainBlock.nii and roiMT.top75.nii.
How can I fix this? I would very much thank for your help!

Below are the contents of 3dinfo:
< roiMT.top75.nii >
Dataset File: /Users/minsunpark/Desktop/MyMVPA/Analyzed_Data/mae4lhs/MT/3dDec/roiMT.top75.nii
Identifier Code: AFN_8KQ80CRmsW0_ToQoiV9XFg Creation Date: Fri Aug 10 17:16:22 2018
Template Space: ORIG
Dataset Type: Echo Planar (-epan)
Byte Order: LSB_FIRST {assumed} [this CPU native = LSB_FIRST]
Storage Mode: NIFTI
Storage Space: 5,156,320 (5.2 million [mega]) bytes
Geometry String: “MATRIX(3,0,0,-92.49069,0,3,0,-111.5018,0,0,3,-83.63406):65,74,67”
Data Axes Tilt: Plumb
Data Axes Orientation:
first (x) = Right-to-Left
second (y) = Anterior-to-Posterior
third (z) = Inferior-to-Superior [-orient RAI]
R-to-L extent: -92.491 [R] -to- 99.509 [L] -step- 3.000 mm [ 65 voxels]
A-to-P extent: -111.502 [A] -to- 107.498 [P] -step- 3.000 mm [ 74 voxels]
I-to-S extent: -83.634 [I] -to- 114.366 [S] -step- 3.000 mm [ 67 voxels]
Number of time steps = 8 Time step = 1.00000s Origin = 0.00000s
– At sub-brick #0 ‘rank’ datum type is short: 0 to 102
– At sub-brick #1 ‘rank’ datum type is short: 0 to 104
– At sub-brick #2 ‘rank’ datum type is short: 0 to 97
** For info on all 8 sub-bricks, use ‘3dinfo -verb’ **

< trainBlock.nii >
Dataset File: ./Analyzed_data/mae4lhs/TASK/3dDec/trainBlock.nii
Identifier Code: AFN_G3Nv9_UmsyLgucdIO_6UbA Creation Date: Sat Aug 11 01:57:54 2018
Template Space: ORIG
Dataset Type: Echo Planar (-epan)
Byte Order: LSB_FIRST {assumed} [this CPU native = LSB_FIRST]
Storage Mode: NIFTI
Storage Space: 44,366,400 (44 million [mega]) bytes
Geometry String: “MATRIX(3,0,0,-96.70753,0,3,0,-121.4756,0,0,3,-89.43157):65,79,72”
Data Axes Tilt: Plumb
Data Axes Orientation:
first (x) = Right-to-Left
second (y) = Anterior-to-Posterior
third (z) = Inferior-to-Superior [-orient RAI]
R-to-L extent: -96.708 [R] -to- 95.292 [L] -step- 3.000 mm [ 65 voxels]
A-to-P extent: -121.476 [A] -to- 112.524 [P] -step- 3.000 mm [ 79 voxels]
I-to-S extent: -89.432 [I] -to- 123.568 [S] -step- 3.000 mm [ 72 voxels]
Number of time steps = 30 Time step = 1.00000s Origin = 0.00000s
– At sub-brick #0 ‘L_adp#0_Coef’ datum type is float: -326.942 to 2464.32
– At sub-brick #1 ‘L_adp#2_Coef’ datum type is float: -375.409 to 187.813
– At sub-brick #2 ‘L_adp#4_Coef’ datum type is float: -277.125 to 2141.06
** For info on all 30 sub-bricks, use ‘3dinfo -verb’ **

You can use 3dfractionize to downsample the ROI to your dataset.

Thanks a lot! It worked.