DataSampler.lua:230: bad argument #3 to 'narrow'

[AbuBakrCh]

While training my own dataset, after one epoch I am getting this error:

/data/mabubakr/torch/install/bin/lua: ...mabubakr/torch/install/share/lua/5.2/threads/threads.lua:183: [thread 2 callback] /data/mabubakr/code/deepmask/DataSampler.lua:230: bad argument #3 to 'narrow' (out of range at /data/mabubakr/torch/pkg/torch/lib/TH/generic/THTensor.c:435)
stack traceback:
[C]: in function 'narrow'
/data/mabubakr/code/deepmask/DataSampler.lua:230: in function 'cropTensor'
/data/mabubakr/code/deepmask/DataSampler.lua:254: in function 'cropMask'
/data/mabubakr/code/deepmask/DataSampler.lua:154: in function 'maskSampling'
/data/mabubakr/code/deepmask/DataSampler.lua:111: in function 'get'
/data/mabubakr/code/deepmask/DataLoader.lua:70: in function </data/mabubakr/code/deepmask/DataLoader.lua:64>
(...tail calls...)
[C]: in function 'xpcall'
...mabubakr/torch/install/share/lua/5.2/threads/threads.lua:234: in function 'callback'
...a/mabubakr/torch/install/share/lua/5.2/threads/queue.lua:65: in function <...a/mabubakr/torch/install/share/lua/5.2/threads/queue.lua:41>
[C]: in function 'pcall'
...a/mabubakr/torch/install/share/lua/5.2/threads/queue.lua:40: in function 'dojob'
[string " local Queue = require 'threads.queue'..."]:15: in main chunk
stack traceback:
[C]: in function 'error'
...mabubakr/torch/install/share/lua/5.2/threads/threads.lua:183: in function 'dojob'
/data/mabubakr/code/deepmask/DataLoader.lua:95: in function 'for iterator'
/data/mabubakr/code/deepmask/TrainerDeepMask.lua:68: in function 'train'
train.lua:117: in main chunk
[C]: in function 'dofile'
...bakr/torch/install/lib/luarocks/rocks/trepl/scm-1/bin/th:150: in main chunk
[C]: in ?

[kvananth]

Hey, were you able to solve this problem?

[AbuBakrCh]

My dataset had wrong segmentation values.

Try to round numbers to maximum two decimal places.
Remove negative values.
Check for other issues in your annotation file.