Someone please help me with this issue
I am trying to finetune the arabic trained data based on some arabic
numerals, for which i have around 12 images in my ground truth folder but
the list.train and list.eval is empty
Don't know why they are empty.
Here is my code i am using to train along with the error
make training MODEL_NAME=ara_tnr START_MODEL=ara MAX_ITERATIONS=50
FINETUNE_TYPE=Impact RATIO_TRAIN=0.9
You are using make version: 4.3
lstmtraining \
--debug_interval 0 \
--traineddata data/ara_tnr/ara_tnr.traineddata \
--old_traineddata
/home/saad/tesseract/tesstrain/usr/share/tessdata/ara.traineddata \
--continue_from data/ara/ara_tnr.lstm \
--learning_rate 0.0001 \
--model_output data/ara_tnr/checkpoints/ara_tnr \
--train_listfile data/ara_tnr/list.train \
--eval_listfile data/ara_tnr/list.eval \
--max_iterations 50 \
--target_error_rate 0.01
Failed to load list of training filenames from data/ara_tnr/list.train
make: *** [Makefile:327: data/ara_tnr/checkpoints/ara_tnr_checkpoint] Error
1
--
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 [email protected].
To view this discussion on the web visit
https://groups.google.com/d/msgid/tesseract-ocr/0f02cb8f-6d2b-441b-b5f1-562875fb05d9n%40googlegroups.com.
