Tom followed your valuable guidance for for training Kannada - but could not completed. modified script also attached. where I made mistake?* *Awaiting further valuable guidance.* *On hearing from you further information will be submitted. With warmest regards,* *-sriranga(79yrs) * Extract of terminal is reproduced below for ready reference: * dell@ubuntu:~/ocropus_6.0$ cd kannada-boxes/ dell@ubuntu:~/ocropus_6.0/ kannada-boxes$ ./run-box-training ================================================================ === This script illustrates training of a simple, initial === character recognizer from the kind of boxdata training === files used with Tesseract. ================================================================
+ for image in 'kan/*.tif'
+ convert -depth 8 kan/alamandidoddavva.tif kan/alamandidoddavva.png
+ for image in 'kan/*.tif'
+ convert -depth 8 kan/g01.tif kan/g01.png
+ for image in 'kan/*.tif'
+ convert -depth 8 kan/g02.tif kan/g02.png
+ for image in 'kan/*.tif'
+ convert -depth 8 kan/g03.tif kan/g03.png
+ for image in 'kan/*.tif'
+ convert -depth 8 kan/g04.tif kan/g04.png
+ for image in 'kan/*.tif'
+ convert -depth 8 kan/g05.tif kan/g05.png
+ for image in 'kan/*.tif'
+ convert -depth 8 kan/g06.tif kan/g06.png
+ for image in 'kan/*.tif'
+ convert -depth 8 kan/g08.tif kan/g08.png
+ for image in 'kan/*.tif'
+ convert -depth 8 kan/g09.tif kan/g09.png
+ for image in 'kan/*.tif'
+ convert -depth 8 kan/g10.tif kan/g10.png
convert convert: kan/g10.tif: Read error at scanline 3407; got 4947830
bytes, expected 4948020. (TIFFFillStrip).
dell@ubuntu:~/ocropus_6.0/kannada-boxes$ ./run-box-training
================================================================
=== This script illustrates training of a simple, initial
=== character recognizer from the kind of boxdata training
=== files used with Tesseract.
================================================================
+ for image in 'kan/*.tif'
+ convert -depth 8 kan/alamandidoddavva.tif kan/alamandidoddavva.png
+ for image in 'kan/*.tif'
+ convert -depth 8 kan/g01.tif kan/g01.png
+ for image in 'kan/*.tif'
+ convert -depth 8 kan/g02.tif kan/g02.png
+ for image in 'kan/*.tif'
+ convert -depth 8 kan/g03.tif kan/g03.png
+ for image in 'kan/*.tif'
+ convert -depth 8 kan/g04.tif kan/g04.png
+ for image in 'kan/*.tif'
+ convert -depth 8 kan/g05.tif kan/g05.png
+ for image in 'kan/*.tif'
+ convert -depth 8 kan/g06.tif kan/g06.png
+ for image in 'kan/*.tif'
+ convert -depth 8 kan/g08.tif kan/g08.png
+ for image in 'kan/*.tif'
+ convert -depth 8 kan/g09.tif kan/g09.png
+ for image in 'kan/*.tif'
+ convert -depth 8 kan/g11.tif kan/g11.png
+ for image in 'kan/*.tif'
+ convert -depth 8 kan/g12.tif kan/g12.png
+ for image in 'kan/*.tif'
+ convert -depth 8 kan/g13.tif kan/g13.png
+ for image in 'kan/*.tif'
+ convert -depth 8 kan/g14.tif kan/g14.png
+ for image in 'kan/*.tif'
+ convert -depth 8 kan/test4.tif kan/test4.png
+ ocropus-db tess2h5 kan/alamandidoddavva.png kan/g01.png kan/g02.png
kan/g03.png kan/g04.png kan/g05.png kan/g06.png kan/g08.png kan/g09.png
kan/g11.png kan/g12.png kan/g13.png kan/g14.png kan/test4.png -o boxdata.h5
['kan/alamandidoddavva.png', 'kan/g01.png', 'kan/g02.png', 'kan/g03.png',
'kan/g04.png', 'kan/g05.png', 'kan/g06.png', 'kan/g08.png', 'kan/g09.png',
'kan/g11.png', 'kan/g12.png', 'kan/g13.png', 'kan/g14.png', 'kan/test4.png']
=== kan/alamandidoddavva.png
=== kan/g01.png
*Traceback (most recent call last):
File "/usr/local/bin/ocropus-db", line 158, in tess_readchars
cimage /= amax(cimage)
File "/usr/lib/python2.7/dist-packages/numpy/core/fromnumeric.py", line
1833, in amax
return amax(axis, out)
ValueError: zero-size array to maximum.reduce without identity*
kan/g01.png 800 ’ 0 8723 0 8723
*Traceback (most recent call last):
File "/usr/local/bin/ocropus-db", line 158, in tess_readchars
cimage /= amax(cimage)
File "/usr/lib/python2.7/dist-packages/numpy/core/fromnumeric.py", line
1833, in amax
return amax(axis, out)
ValueError: zero-size array to maximum.reduce without identity
kan/g01.png 820 ’ 0 8723 0 8723*
=== kan/g02.png
=== kan/g03.png
*Traceback (most recent call last):
File "/usr/local/bin/ocropus-db", line 158, in tess_readchars
cimage /= amax(cimage)
File "/usr/lib/python2.7/dist-packages/numpy/core/fromnumeric.py", line
1833, in amax
return amax(axis, out)
ValueError: zero-size array to maximum.reduce without identity
kan/g03.png 345 0 5538 0 5538*
=== kan/g04.png
*./run-box-training: line 31: 2643 Segmentation fault (core dumped)
ocropus-db tess2h5 kan/*.png -o boxdata.h5*
dell@ubuntu:~/ocropus_6.0/kannada-boxes$
On Thu, Aug 23, 2012 at 2:50 PM, Tom <[email protected]> wrote:
> Hi,
>
> the next step is to follow the example in "fraktur-boxes" and do something
> similar for your script. You can re-use Tesseract training files you have.
>
> As for how to update, we're still just using Mercurial for distribution,
> so if you want to read more, have a look at Mercurial tutorials, like:
> http://mercurial.selenic.com/wiki/Tutorial
>
> Tom
>
> On Thursday, August 23, 2012 8:23:04 AM UTC+2, 79yrsold wrote:
>
>> Tom,
>>
>> Without waiting for further guidance on my previous emails. I started to
>> re-install ocropus 0.6 from scratch, after deleting ocropus
>> folder containing 0.6-pre4. succeeded to run-test - vide extract of
>> terminal0.6 attached herewith.
>> How to start next step of training procedure?
>>
>> *suggestion*: it would be nice indicate the commandline to be used by
>> new users/newbies - for the *first time* installing ocropus. and
>> commandline ( to *update the existing ocropus to latest version of
>> ocropus*) to be used by old users - who had *already installed* ocropus
>>
>> Awaiting further guidance.
>> -sriranga(79yrs)
>>
>> On Thu, Aug 23, 2012 at 7:14 AM, Sriranga(78yrsold)
>> <[email protected]>wrote:
>>
>>> I tried to update the existing ocropus folder containing 0.6pre-4 to
>>> ocropus 6.0 by using the commandline as follows:
>>>
>>> dell@ubuntu:~$ cd ocropus
>>> dell@ubuntu:~/ocropus$ sudo apt-get hg clone -r ocropus-0.6
>>> https://code.google.com/p/**ocropus <https://code.google.com/p/ocropus>
>>> [sudo] password for dell:
>>> E: Command line option 'r' [from -r] is not known.
>>> dell@ubuntu:~/ocropus$
>>> I am newbie to linux - where i made mistake?
>>> Awaiting valuable guidance.
>>> w/b
>>> -sriranga(79yrs)
>>>
>>>
>>>
>>>
>>> On Thu, Aug 23, 2012 at 6:55 AM, Sriranga(78yrsold) <[email protected]
>>> > wrote:
>>>
>>>> Is extract of IRC(freenode #ocropus)discussion available? If so, where?
>>>>
>>>>
>>>> On Thu, Aug 23, 2012 at 6:49 AM, Sriranga(78yrsold) <
>>>> [email protected]> wrote:
>>>>
>>>>> Tom,
>>>>> Already re-installed version 0.6pre-4 yesterday by deleting ocropus
>>>>> folder of 0.6pre-3.
>>>>> How to updated to version 0.6. It is presumed that existing ocropus
>>>>> folder have to be deleted and re-install from scratch? yesterday night I
>>>>> spent upto 2pm without sleep (usually at 10pm- go to bed). Kindly not to
>>>>> mistake me.
>>>>> What is the commandline to be used for updating from the existing
>>>>> version to next version viz. ocropus 0.6 without necessity to re-install
>>>>> from the scaratch?.
>>>>> Awaiting further instructions.
>>>>> With warmest regards,
>>>>> -sriranga(79yrs) - *INDIA*
>>>>>
>>>>>
>>>>> On Thu, Aug 23, 2012 at 5:03 AM, Tom <[email protected]> wrote:
>>>>>
>>>>>> I have tagged the released version of OCRopus 0.6. Major changes
>>>>>> relative to 0.5.x are much simpler installation, fewer dependencies,
>>>>>> better
>>>>>> character recognition rates, and easier training. There is also a number
>>>>>> of sample scripts illustrating recognition and training.
>>>>>>
>>>>>> Thanks to everybody who provided feedback on prereleases.
>>>>>>
>>>>>> For documentation and further information, please see the project
>>>>>> page: www.ocropus.org
>>>>>>
>>>>>> Tom
>>>>>>
>>>>>> --
>>>>>> 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 ocropus+u...@**
>>>>>> googlegroups.com.
>>>>>>
>>>>>> To view this discussion on the web visit https://groups.google.com/d/
>>>>>> **msg/ocropus/-/784w6OSv3fMJ<https://groups.google.com/d/msg/ocropus/-/784w6OSv3fMJ>
>>>>>> .
>>>>>> For more options, visit
>>>>>> https://groups.google.com/**groups/opt_out<https://groups.google.com/groups/opt_out>
>>>>>> .
>>>>>>
>>>>>>
>>>>>>
>>>>>
>>>>>
>>>>
>>>
>> --
> 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].
> To view this discussion on the web visit
> https://groups.google.com/d/msg/ocropus/-/b3PL9Hi82UcJ.
>
> For more options, visit https://groups.google.com/groups/opt_out.
>
>
>
--
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 https://groups.google.com/groups/opt_out.
run-box-training
Description: Binary data
