vedaldi / practical-cnn

A VGG practical on convolutional neural networks
154 stars 75 forks source link

error in classificaton other letters #9

Closed itays02 closed 8 years ago

itays02 commented 8 years ago

Hello. I'm using your library for Hebrew letters classification. After updating the imdb variable, I've got today an exception of index out of " Index exceeds matrix dimensions." in vlnnloss)

The new image/ kabels db is identical to the first one(classing chars).

Appreciate your help,

-------------------------------------------- CODE --------------------------------------------------------------------- layer 0 1 2 3 4 5 6 7 8 type input conv mpool conv mpool conv relu conv softmxl name n/a
support n/a 5 2 5 2 4 1 2 1
filt dim n/a 1 n/a 20 n/a 50 n/a 500 n/a
num filts n/a 20 n/a 50 n/a 500 n/a 26 n/a
stride n/a 1 2 1 2 1 1 1 1
pad n/a 0 0 0 0 0 0 0 0
---------- ------- ------- ------- ------- ------- ------- ------- ------- -------
rf size n/a 5 6 14 16 28 28 32 32
rf offset n/a 3 3.5 7.5 8.5 14.5 14.5 16.5 16.5
rf stride n/a 1 2 2 4 4 4 4 4
---------- ------- ------- ------- ------- ------- ------- ------- ------- -------
data size NaNxNaN NaNxNaN NaNxNaN NaNxNaN NaNxNaN NaNxNaN NaNxNaN NaNxNaN NaNxNaN
data depth NaN 20 20 50 50 500 500 26 1
data num 100 100 100 100 100 100 100 100 1
---------- ------- ------- ------- ------- ------- ------- ------- ------- -------
data mem NaN NaN NaN NaN NaN NaN NaN NaN NaN
param mem n/a 2KB 0B 98KB 0B 2MB 0B 203KB 0B

parameter memory|2MB (4.8e+05 parameters)| data memory|NaN (for batch size 100)|

train: epoch 01: 1/ 76: 132.9 Hz obj:3.2 top1err:0.96 top5err:0.84 [100/100] train: epoch 01: 2/ 76: Index exceeds matrix dimensions.

Error in vl_nnloss (line 209) t = Xmax + log(sum(ex,3)) - X(ci) ;

Error in vl_simplenn (line 293) res(i+1).x = vl_nnloss(res(i).x, l.class) ;

rashaalshehhi commented 8 years ago

I have same problem. How did you solved it?