I used the ocropus-ctrain to train the neural network for sinhala script. It
gave the following error. Could you help me on this error?
anushka@anushka-Ideapad-Z460:~/ocro/ocropy$ ocropus-ctrain -K 10 chars.db -o
chars.cmodel
classifier <ocrolib.mlp.AutoMlpModel instance at 0x939cf8c>
training...
=== chars.db
total 42
# determining per-class cutoff
classes 21 stats 2.0 2.0 2.0 2.0 ntrain 2
# sampling the classes
A:2 C:2 D:2 T:2 b:2 d:2 e:2 g:2 h:2 i:2 j:2 k:2 l:2 m:2 n:2
p:2 r:2 s:2 t:2 v:2 y:2
# training 42
summary statistics:
[('A', 2), ('C', 2), ('D', 2), ('T', 2), ('b', 2), ('d', 2), ('e', 2), ('g',
2), ('h', 2), ('i', 2), ('j', 2), ('k', 2), ('l', 2), ('m', 2), ('n', 2),
('p', 2), ('r', 2), ('s', 2), ('t', 2), ('v', 2), ('y', 2)]
training 42 variants representing 42 training characters
starting classifier training
AutoMLP initial 0.408 20 4 1.0000
AutoMLP initial 0.175 40 4 1.0000
Traceback (most recent call last):
File "/usr/local/bin/ocropus-ctrain", line 311, in <module>
for progress in classifier.updateModel1(verbose=1):
File "/usr/local/lib/python2.7/dist-packages/ocrolib/common.py", line
1788, in updateModel1
for progress in
self.classifier.train1(self.rows,array(self.classes,'i'),*args,**kw):
File "/usr/local/lib/python2.7/dist-packages/ocrolib/mlp.py", line 500, in
train1
samples=training)
File "/usr/local/lib/python2.7/dist-packages/ocrolib/mlp.py", line 387, in
train
self.init(data,cls,nhidden=nhidden,eps=eps)
File "/usr/local/lib/python2.7/dist-packages/ocrolib/mlp.py", line 325, in
init
self.w1 = array(data[selection(xrange(len(data)),nhidden)] *
eps/scale,'f')
File "/usr/lib/python2.7/random.py", line 320, in sample
raise ValueError, "sample larger than population"
ValueError: sample larger than population
--
You received this message because you are subscribed to the Google Groups
"ocropus" group.
To post to this group, send email to [email protected].
To unsubscribe from this group, send email to
[email protected].
For more options, visit this group at
http://groups.google.com/group/ocropus?hl=en.
