Tesseract Version: 4.1.0
I am trying to fine tune tesseract on custom dataset with the following
Makefile:
export
SHELL := /bin/bash
HOME := $(PWD)
TESSDATA = $(HOME)/tessdata
LANGDATA = $(HOME)/langdata
# Train directory
# TRAIN := $(HOME)/train_data
TRAIN := /media/vimaan/Data/OCR/tesseract_train
# Name of the model to be built
MODEL_NAME = eng
LANG_CODE = eng
# Name of the model to continue from
CONTINUE_FROM = eng
TESSDATA_REPO = _best
# Normalization Mode - see src/training/language_specific.sh for details
NORM_MODE = 1
# BEGIN-EVAL makefile-parser --make-help Makefile
help:
@echo ""
@echo " Targets"
@echo ""
@echo " unicharset Create unicharset"
@echo " lists Create lists of lstmf filenames for
training and eval"
@echo " training Start training"
@echo " proto-model Build the proto model"
@echo " leptonica Build leptonica"
@echo " tesseract Build tesseract"
@echo " tesseract-langs Download tesseract-langs"
@echo " langdata Download langdata"
@echo " clean Clean all generated files"
@echo ""
@echo " Variables"
@echo ""
@echo " MODEL_NAME Name of the model to be built"
@echo " CORES No of cores to use for compiling
leptonica/tesseract"
@echo " LEPTONICA_VERSION Leptonica version. Default:
$(LEPTONICA_VERSION)"
@echo " TESSERACT_VERSION Tesseract commit. Default:
$(TESSERACT_VERSION)"
@echo " LANGDATA_VERSION Tesseract langdata version. Default:
$(LANGDATA_VERSION)"
@echo " TESSDATA_REPO Tesseract model repo to use. Default:
$(TESSDATA_REPO)"
@echo " TRAIN Train directory"
@echo " RATIO_TRAIN Ratio of train / eval training data"
# END-EVAL
# Ratio of train / eval training data
RATIO_TRAIN := 0.90
ALL_BOXES = data/all-boxes
ALL_LSTMF = data/all-lstmf
# Create unicharset
unicharset: data/unicharset
# Create lists of lstmf filenames for training and eval
#lists: $(ALL_LSTMF) data/list.train data/list.eval
lists: $(ALL_LSTMF)
train-lists: data/list.train data/list.eval
data/list.train: $(ALL_LSTMF)
total=`cat $(ALL_LSTMF) | wc -l` \
no=`echo "$$total * $(RATIO_TRAIN) / 1" | bc`; \
head -n "$$no" $(ALL_LSTMF) > "$@"
data/list.eval: $(ALL_LSTMF)
total=`cat $(ALL_LSTMF) | wc -l` \
no=`echo "($$total - $$total * $(RATIO_TRAIN)) / 1" | bc`; \
tail -n "$$no" $(ALL_LSTMF) > "$@"
# Start training
training: data/$(MODEL_NAME).traineddata
data/unicharset: $(ALL_BOXES)
mkdir -p data/$(START_MODEL)
combine_tessdata -u $(TESSDATA)/$(CONTINUE_FROM).traineddata
$(TESSDATA)/$(CONTINUE_FROM).
unicharset_extractor --output_unicharset "$(TRAIN)/my.unicharset"
--norm_mode $(NORM_MODE) "$(ALL_BOXES)"
#merge_unicharsets data/$(START_MODEL)/$(START_MODEL).lstm-unicharset
$(GROUND_TRUTH_DIR)/my.unicharset "$@"
merge_unicharsets $(TESSDATA)/$(CONTINUE_FROM).lstm-unicharset
$(TRAIN)/my.unicharset "$@"
$(ALL_BOXES): $(sort $(patsubst %.tif,%.box,$(wildcard $(TRAIN)/*.tif)))
find $(TRAIN) -name '*.box' -exec cat {} \; > "$@"
$(TRAIN)/%.box: $(TRAIN)/%.tif $(TRAIN)/%.gt.txt
python generate_line_box.py -i "$(TRAIN)/$*.tif" -t
"$(TRAIN)/$*.gt.txt" > "$@"
$(ALL_LSTMF): $(sort $(patsubst %.tif,%.lstmf,$(wildcard $(TRAIN)/*.tif)))
find $(TRAIN) -name '*.lstmf' -exec echo {} \; | sort -R -o "$@"
$(TRAIN)/%.lstmf: $(TRAIN)/%.box
tesseract $(TRAIN)/$*.tif $(TRAIN)/$* --dpi 300 --psm 7 lstm.train
# Build the proto model
proto-model: data/$(MODEL_NAME)/$(MODEL_NAME).traineddata
data/$(MODEL_NAME)/$(MODEL_NAME).traineddata: $(LANGDATA) data/unicharset
combine_lang_model \
--input_unicharset data/unicharset \
--script_dir $(LANGDATA) \
--words $(LANGDATA)/$(MODEL_NAME)/$(MODEL_NAME).wordlist \
--numbers $(LANGDATA)/$(MODEL_NAME)/$(MODEL_NAME).numbers \
--puncs $(LANGDATA)/$(MODEL_NAME)/$(MODEL_NAME).punc \
--output_dir data/ \
--lang $(MODEL_NAME)
data/checkpoints/$(MODEL_NAME)_checkpoint: unicharset proto-model
mkdir -p data/checkpoints
lstmtraining \
--continue_from $(TESSDATA)/$(CONTINUE_FROM).lstm \
--old_traineddata $(TESSDATA)/$(CONTINUE_FROM).traineddata \
--traineddata data/$(MODEL_NAME)/$(MODEL_NAME).traineddata \
--model_output data/checkpoints/$(MODEL_NAME) \
--debug_interval -1 \
--train_listfile data/list.train \
--eval_listfile data/list.eval \
--sequential_training \
--max_iterations 170000
data/$(MODEL_NAME).traineddata: data/checkpoints/$(MODEL_NAME)_checkpoint
lstmtraining \
--stop_training \
--continue_from $^ \
--old_traineddata $(TESSDATA)/$(CONTINUE_FROM).traineddata \
--traineddata data/$(MODEL_NAME)/$(MODEL_NAME).traineddata \
--model_output $@
# Clean all generated files
clean:
find data/train -name '*.box' -delete
find data/train -name '*.lstmf' -delete
rm -rf data/all-*
rm -rf data/list.*
rm -rf data/$(MODEL_NAME)
rm -rf data/unicharset
rm -rf data/checkpoints
The number of .lstmf files being generated is significantly lower than .box
files being generated.
For eg:
Number of .tif files: 10k
Number of .gt.txt files: 10k
Number of .box files: 10k
Number of .lstmf files: 8k.
Could anyone point me out to the possible reasons for this issue
On Friday, June 29, 2018 at 5:39:09 PM UTC+5:30, shree wrote:
>
> I modified the makefile for ocrd-train to do fine-tuning. It is pasted
> below:
>
> export
>
> SHELL := /bin/bash
> LOCAL := $(PWD)/usr
> PATH := $(LOCAL)/bin:$(PATH)
> HOME := /home/ubuntu
> TESSDATA = $(HOME)/tessdata_best
> LANGDATA = $(HOME)/langdata
>
> # Name of the model to be built
> MODEL_NAME = frk
>
> # Name of the model to continue from
> CONTINUE_FROM = frk
>
> # Normalization Mode - see src/training/language_specific.sh for details
> NORM_MODE = 2
>
> # Tesseract model repo to use. Default: $(TESSDATA_REPO)
> TESSDATA_REPO = _best
>
> # Train directory
> TRAIN := data/train
>
> # BEGIN-EVAL makefile-parser --make-help Makefile
>
> help:
> @echo ""
> @echo " Targets"
> @echo ""
> @echo " unicharset Create unicharset"
> @echo " lists Create lists of lstmf filenames for training
> and eval"
> @echo " training Start training"
> @echo " proto-model Build the proto model"
> @echo " leptonica Build leptonica"
> @echo " tesseract Build tesseract"
> @echo " tesseract-langs Download tesseract-langs"
> @echo " langdata Download langdata"
> @echo " clean Clean all generated files"
> @echo ""
> @echo " Variables"
> @echo ""
> @echo " MODEL_NAME Name of the model to be built"
> @echo " CORES No of cores to use for compiling
> leptonica/tesseract"
> @echo " LEPTONICA_VERSION Leptonica version. Default:
> $(LEPTONICA_VERSION)"
> @echo " TESSERACT_VERSION Tesseract commit. Default:
> $(TESSERACT_VERSION)"
> @echo " LANGDATA_VERSION Tesseract langdata version. Default:
> $(LANGDATA_VERSION)"
> @echo " TESSDATA_REPO Tesseract model repo to use. Default:
> $(TESSDATA_REPO)"
> @echo " TRAIN Train directory"
> @echo " RATIO_TRAIN Ratio of train / eval training data"
>
> # END-EVAL
>
> # Ratio of train / eval training data
> RATIO_TRAIN := 0.90
>
> ALL_BOXES = data/all-boxes
> ALL_LSTMF = data/all-lstmf
>
> # Create unicharset
> unicharset: data/unicharset
>
> # Create lists of lstmf filenames for training and eval
> lists: $(ALL_LSTMF) data/list.train data/list.eval
>
> data/list.train: $(ALL_LSTMF)
> total=`cat $(ALL_LSTMF) | wc -l` \
> no=`echo "$$total * $(RATIO_TRAIN) / 1" | bc`; \
> head -n "$$no" $(ALL_LSTMF) > "$@"
>
> data/list.eval: $(ALL_LSTMF)
> total=`cat $(ALL_LSTMF) | wc -l` \
> no=`echo "($$total - $$total * $(RATIO_TRAIN)) / 1" | bc`; \
> tail -n "+$$no" $(ALL_LSTMF) > "$@"
>
> # Start training
> training: data/$(MODEL_NAME).traineddata
>
> data/unicharset: $(ALL_BOXES)
> combine_tessdata -u $(TESSDATA)/$(CONTINUE_FROM).traineddata
> $(TESSDATA)/$(CONTINUE_FROM).
> unicharset_extractor --output_unicharset "$(TRAIN)/my.unicharset"
> --norm_mode $(NORM_MODE) "$(ALL_BOXES)"
> merge_unicharsets $(TESSDATA)/$(CONTINUE_FROM).lstm-unicharset
> $(TRAIN)/my.unicharset "$@"
> $(ALL_BOXES): $(sort $(patsubst %.tif,%.box,$(wildcard $(TRAIN)/*.tif)))
> find $(TRAIN) -name '*.box' -exec cat {} \; > "$@"
> $(TRAIN)/%.box: $(TRAIN)/%.tif $(TRAIN)/%-gt.txt
> python generate_line_box.py -i "$(TRAIN)/$*.tif" -t "$(TRAIN)/$*-gt.txt" >
> "$@"
>
> $(ALL_LSTMF): $(sort $(patsubst %.tif,%.lstmf,$(wildcard $(TRAIN)/*.tif)))
> find $(TRAIN) -name '*.lstmf' -exec echo {} \; | sort -R -o "$@"
>
> $(TRAIN)/%.lstmf: $(TRAIN)/%.box
> tesseract $(TRAIN)/$*.tif $(TRAIN)/$* --psm 6 lstm.train
>
> # Build the proto model
> proto-model: data/$(MODEL_NAME)/$(MODEL_NAME).traineddata
>
> data/$(MODEL_NAME)/$(MODEL_NAME).traineddata: $(LANGDATA) data/unicharset
> combine_lang_model \
> --input_unicharset data/unicharset \
> --script_dir $(LANGDATA) \
> --words $(LANGDATA)/$(MODEL_NAME)/$(MODEL_NAME).wordlist \
> --numbers $(LANGDATA)/$(MODEL_NAME)/$(MODEL_NAME).numbers \
> --puncs $(LANGDATA)/$(MODEL_NAME)/$(MODEL_NAME).punc \
> --output_dir data/ \
> --lang $(MODEL_NAME)
>
> data/checkpoints/$(MODEL_NAME)_checkpoint: unicharset lists proto-model
> mkdir -p data/checkpoints
> lstmtraining \
> --continue_from $(TESSDATA)/$(CONTINUE_FROM).lstm \
> --old_traineddata $(TESSDATA)/$(CONTINUE_FROM).traineddata \
> --traineddata data/$(MODEL_NAME)/$(MODEL_NAME).traineddata \
> --model_output data/checkpoints/$(MODEL_NAME) \
> --debug_interval -1 \
> --train_listfile data/list.train \
> --eval_listfile data/list.eval \
> --sequential_training \
> --max_iterations 3000
>
> data/$(MODEL_NAME).traineddata: data/checkpoints/$(MODEL_NAME)_checkpoint
> lstmtraining \
> --stop_training \
> --continue_from $^ \
> --old_traineddata $(TESSDATA)/$(CONTINUE_FROM).traineddata \
> --traineddata data/$(MODEL_NAME)/$(MODEL_NAME).traineddata \
> --model_output $@
>
> # Clean all generated files
> clean:
> find data/train -name '*.box' -delete
> find data/train -name '*.lstmf' -delete
> rm -rf data/all-*
> rm -rf data/list.*
> rm -rf data/$(MODEL_NAME)
> rm -rf data/unicharset
> rm -rf data/checkpoints
>
> On Fri, Jun 29, 2018 at 5:31 PM Lorenzo Bolzani <l.bo...@gmail.com
> <javascript:>> wrote:
>
>>
>>
>> Hi,
>> I'm trying to do fine tuning of an existing model using line images and
>> text labels. I'm running this version:
>>
>> tesseract 4.0.0-beta.3-56-g5fda
>> leptonica-1.76.0
>> libgif 5.1.4 : libjpeg 8d (libjpeg-turbo 1.4.2) : libpng 1.2.54 :
>> libtiff 4.0.6 : zlib 1.2.8 : libwebp 0.4.4 : libopenjp2 2.3.0
>> Found AVX2
>> Found AVX
>> Found SSE
>>
>>
>>
>> I used OCR-D to generate lstmf files for the demo data.
>>
>> If I run the make command it works fine.
>>
>> make training MODEL_NAME=prova
>>
>> Now I isolated this command from the build:
>>
>> lstmtraining \
>> --traineddata data/prova/prova.traineddata \
>> --net_spec "[1,36,0,1 Ct3,3,16 Mp3,3 Lfys48 Lfx96 Lrx96 Lfx256 O1c`head
>> -n1 data/unicharset`]" \
>> --model_output data/checkpoints/prova \
>> --learning_rate 20e-4 \
>> --train_listfile data/list.train \
>> --eval_listfile data/list.eval \
>> --max_iterations 10000
>>
>> and it works fine.
>>
>> Now I'm trying to modify it to fine tune the existing eng model. I made a
>> few attempts, all ending into different errors (see the attached file for
>> full output).
>>
>> I used:
>>
>> combine_tessdata -e /usr/local/share/tessdata/eng.traineddata
>> extracted/eng.lstm
>>
>> to extract the eng.lstm model.
>>
>> This seems to works but I'm not sure it is the correct.
>>
>> lstmtraining \
>> --continue_from extracted/eng.lstm \
>> --traineddata data/prova/prova.traineddata \
>> --old_traineddata extracted/eng.traineddata \
>> --model_output data/checkpoints/prova \
>> --learning_rate 20e-4 \
>> --train_listfile data/list.train \
>> --eval_listfile data/list.eval \
>> --max_iterations 10000
>>
>> (extracted/eng.traineddata is just a copy of eng.traineddata)
>>
>>
>> The training resume exactly with the RMS of prova_checkpoint (6%) so it
>> looks like it is training from that checkpoint, not the eng.lstm.
>>
>> Is this correct? What should I change?
>>
>> I'm following this guide:
>>
>>
>> https://github.com/tesseract-ocr/tesseract/wiki/TrainingTesseract-4.00#fine-tuning-for--a-few-characters
>>
>>
>> I think continue_from and traineddata should refer to the eng model and
>> old_traineddata should point to prova.traineddata, but if I do that I get a
>> segmentation fault:
>>
>> [...]
>> !int_mode_:Error:Assert failed:in file weightmatrix.cpp, line 244
>> !int_mode_:Error:Assert failed:in file weightmatrix.cpp, line 244
>> Segmentation fault
>>
>> What am I missing?
>>
>>
>> Thanks, bye
>>
>> Lorenzo
>>
>> --
>> 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 tesser...@googlegroups.com <javascript:>.
>> To post to this group, send email to tesser...@googlegroups.com
>> <javascript:>.
>> 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/CAMgOLLyOJN31PdWQumXPO3JjuAc1Yz2BZYpMd4ftzBHgZkEaxA%40mail.gmail.com
>>
>> <https://groups.google.com/d/msgid/tesseract-ocr/CAMgOLLyOJN31PdWQumXPO3JjuAc1Yz2BZYpMd4ftzBHgZkEaxA%40mail.gmail.com?utm_medium=email&utm_source=footer>
>> .
>> For more options, visit https://groups.google.com/d/optout.
>>
>
>
> --
>
> ____________________________________________________________
> भजन - कीर्तन - आरती @ http://bhajans.ramparivar.com
>
--
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 view this discussion on the web visit
https://groups.google.com/d/msgid/tesseract-ocr/e3ba3b90-a8c8-4085-bec5-cf918034ba2a%40googlegroups.com.
