> Warning: given outputs 111 not equal to unicharset of 90.
your starter traineddata has a unicharset of 90.
In your --net_spec you have specified number of unichars as 111.
> Encoding of string failed!
It means that some of the chracters in the displayed string are NOT in the
unicharset of
Hi,
*I was trying to run lstmtraining script using below command,*
./build/src/training/lstmtraining --debug_interval 100 \
--traineddata ../training/sintrain/sin/sin.traineddata \
--net_spec '[1,36,0,1 Ct3,3,16 Mp3,3 Lfys48 Lfx96 Lrx96 Lfx256 O1c111]' \
--model_output
Thank you very much Shree
On Wednesday, September 5, 2018 at 7:11:51 AM UTC+3, shree wrote:
>
> Easiest way to check is to use combine_tessdata to unpack the starter
> traineddata file and see what is included. You can use dawg2wordlist to
> verify that it is the correct files being included.
>
3 matches
Mail list logo