Re: [tesseract-ocr] Tesseract 4.0: VGSLSpecs

2016-12-16 Thread ShreeDevi Kumar 
+ Ray Smith

On 16-Dec-2016 10:58 PM, "Kay-Michael Würzner"  wrote:

> Yes,  I did and in principle everything works like a charm which is great.
> What I want to accomplish now is some understanding: Why do I have to set a
> documented parameter in some undocumented way or to be more precise set
> this parameter to a value which conflicts with the documentation to make
> the whole process work?
>
> Cheers,
> Kay
>
> On Friday, December 16, 2016 at 5:36:02 PM UTC+1, shree wrote:
>>
>> Did you try out the commands as per the LSTM training tutorial?
>>
>> On 16-Dec-2016 8:31 PM, "Kay-Michael Würzner"  wrote:
>>
>>> Dear @,
>>>
>>> I played around with training the new LSTM mode. According to the
>>> documentation of the network specification (
>>> https://github.com/tesseract-ocr/tesseract/wiki/VGSLSpecs), the last
>>> number in the first tupel called 'depth' corresponds to the type of input
>>> (i.e. 1 ... grayscale, 3 ... color). However one o the given examples uses
>>> '48' in this position:
>>>
>>> [1,1,0,48 Lbx256 O1c105]
>>>
>>> Using an assumingly corrected specification
>>>
>>> [1,48,0,1 Lbx256 O1c105]
>>>
>>> causes serious runtime issues namely each iteration takes several
>>> minutes and huge amounts of memory are adressed. Any hints on what I am
>>> doing wrong here?
>>>
>>> Many thanks in advance,
>>> Kay
>>>
>>> --
>>> You received this message because you are subscribed to the Google
>>> Groups "tesseract-ocr" group.
>>> To unsubscribe from this group and stop receiving emails from it, send
>>> an email to tesseract-oc...@googlegroups.com.
>>> To post to this group, send email to tesser...@googlegroups.com.
>>> Visit this group at https://groups.google.com/group/tesseract-ocr.
>>> To view this discussion on the web visit https://groups.google.com/d/ms
>>> gid/tesseract-ocr/167ff50a-2fbb-463c-b637-c051b2e9da82%40goo
>>> glegroups.com
>>> 
>>> .
>>> For more options, visit https://groups.google.com/d/optout.
>>>
>> --
> You received this message because you are subscribed to the Google Groups
> "tesseract-ocr" group.
> To unsubscribe from this group and stop receiving emails from it, send an
> email to tesseract-ocr+unsubscr...@googlegroups.com.
> To post to this group, send email to tesseract-ocr@googlegroups.com.
> Visit this group at https://groups.google.com/group/tesseract-ocr.
> To view this discussion on the web visit https://groups.google.com/d/
> msgid/tesseract-ocr/2206e63d-0675-4630-8251-6ad5bcc8a9c9%
> 40googlegroups.com
> 
> .
> For more options, visit https://groups.google.com/d/optout.
>

-- 
You received this message because you are subscribed to the Google Groups 
"tesseract-ocr" group.
To unsubscribe from this group and stop receiving emails from it, send an email 
to tesseract-ocr+unsubscr...@googlegroups.com.
To post to this group, send email to tesseract-ocr@googlegroups.com.
Visit this group at https://groups.google.com/group/tesseract-ocr.
To view this discussion on the web visit 
https://groups.google.com/d/msgid/tesseract-ocr/CAG2NduVK4EKyMQUzyv3KQ5Spzn8cfZ9vMM%3DCyou-ddkOn79PMA%40mail.gmail.com.
For more options, visit https://groups.google.com/d/optout.

Re: [tesseract-ocr] Tesseract 4.0: VGSLSpecs

2016-12-16 Thread Kay-Michael Würzner 
Yes,  I did and in principle everything works like a charm which is great. 
What I want to accomplish now is some understanding: Why do I have to set a 
documented parameter in some undocumented way or to be more precise set 
this parameter to a value which conflicts with the documentation to make 
the whole process work?

Cheers,
Kay

On Friday, December 16, 2016 at 5:36:02 PM UTC+1, shree wrote:
>
> Did you try out the commands as per the LSTM training tutorial?
>
> On 16-Dec-2016 8:31 PM, "Kay-Michael Würzner"  > wrote:
>
>> Dear @,
>>
>> I played around with training the new LSTM mode. According to the 
>> documentation of the network specification (
>> https://github.com/tesseract-ocr/tesseract/wiki/VGSLSpecs), the last 
>> number in the first tupel called 'depth' corresponds to the type of input 
>> (i.e. 1 ... grayscale, 3 ... color). However one o the given examples uses 
>> '48' in this position:
>>
>> [1,1,0,48 Lbx256 O1c105]
>>
>> Using an assumingly corrected specification
>>
>> [1,48,0,1 Lbx256 O1c105]
>>
>> causes serious runtime issues namely each iteration takes several minutes 
>> and huge amounts of memory are adressed. Any hints on what I am doing wrong 
>> here?
>>
>> Many thanks in advance,
>> Kay
>>
>> -- 
>> You received this message because you are subscribed to the Google Groups 
>> "tesseract-ocr" group.
>> To unsubscribe from this group and stop receiving emails from it, send an 
>> email to tesseract-oc...@googlegroups.com .
>> To post to this group, send email to tesser...@googlegroups.com 
>> .
>> Visit this group at https://groups.google.com/group/tesseract-ocr.
>> To view this discussion on the web visit 
>> https://groups.google.com/d/msgid/tesseract-ocr/167ff50a-2fbb-463c-b637-c051b2e9da82%40googlegroups.com
>>  
>> 
>> .
>> For more options, visit https://groups.google.com/d/optout.
>>
>

-- 
You received this message because you are subscribed to the Google Groups 
"tesseract-ocr" group.
To unsubscribe from this group and stop receiving emails from it, send an email 
to tesseract-ocr+unsubscr...@googlegroups.com.
To post to this group, send email to tesseract-ocr@googlegroups.com.
Visit this group at https://groups.google.com/group/tesseract-ocr.
To view this discussion on the web visit 
https://groups.google.com/d/msgid/tesseract-ocr/2206e63d-0675-4630-8251-6ad5bcc8a9c9%40googlegroups.com.
For more options, visit https://groups.google.com/d/optout.

Re: [tesseract-ocr] Tesseract 4.0: VGSLSpecs

2016-12-16 Thread ShreeDevi Kumar 
Did you try out the commands as per the LSTM training tutorial?

On 16-Dec-2016 8:31 PM, "Kay-Michael Würzner"  wrote:

> Dear @,
>
> I played around with training the new LSTM mode. According to the
> documentation of the network specification (https://github.com/tesseract-
> ocr/tesseract/wiki/VGSLSpecs), the last number in the first tupel called
> 'depth' corresponds to the type of input (i.e. 1 ... grayscale, 3 ...
> color). However one o the given examples uses '48' in this position:
>
> [1,1,0,48 Lbx256 O1c105]
>
> Using an assumingly corrected specification
>
> [1,48,0,1 Lbx256 O1c105]
>
> causes serious runtime issues namely each iteration takes several minutes
> and huge amounts of memory are adressed. Any hints on what I am doing wrong
> here?
>
> Many thanks in advance,
> Kay
>
> --
> You received this message because you are subscribed to the Google Groups
> "tesseract-ocr" group.
> To unsubscribe from this group and stop receiving emails from it, send an
> email to tesseract-ocr+unsubscr...@googlegroups.com.
> To post to this group, send email to tesseract-ocr@googlegroups.com.
> Visit this group at https://groups.google.com/group/tesseract-ocr.
> To view this discussion on the web visit https://groups.google.com/d/
> msgid/tesseract-ocr/167ff50a-2fbb-463c-b637-c051b2e9da82%
> 40googlegroups.com
> 
> .
> For more options, visit https://groups.google.com/d/optout.
>

-- 
You received this message because you are subscribed to the Google Groups 
"tesseract-ocr" group.
To unsubscribe from this group and stop receiving emails from it, send an email 
to tesseract-ocr+unsubscr...@googlegroups.com.
To post to this group, send email to tesseract-ocr@googlegroups.com.
Visit this group at https://groups.google.com/group/tesseract-ocr.
To view this discussion on the web visit 
https://groups.google.com/d/msgid/tesseract-ocr/CAG2NduVCiZh-sX--7xFJOxn6v11fpddoFqHea-htoHGFCnbs6A%40mail.gmail.com.
For more options, visit https://groups.google.com/d/optout.