tesseract: Deserialize header failed LSTM files
@Shreeshrii Im trying to run the below code for lstm training but I could not get the supposed output because everything seems to be correct. Please could anyone check and let me know where Im going wrong.
OS - Windows 10 Tesseract version : 4.1
`C:\Program Files\Tesseract-OCR>lstmtraining --traineddata D:\ProjectOCR\Train\new2\new2.TRAINEDDATA --F D:\ProjectOCR\Train\font_properties.txt --X C:\Users\samuel.preethamlam\Downloads\langdata-master\langdata-master --U D:\ProjectOCR\Train\new2.unicharset --model_output D:\ProjectOCR\Train --train_listfile C:\Users\samuel.preethamlam\Downloads\eng.training_files.txt --net_spec “[1,40,0,1 Ct5,5,64 Mp3,3 Lfys128 Lbx256 Lbx256]”
Num outputs,weights in Series: 1,40,0,1:1, 0
Num outputs,weights in Series: C5,5:25, 0 Ft64:64, 1664
Total weights = 1664 [C5,5Ft64]:64, 1664 Mp3,3:64, 0 Lfys128:128, 98816 Lbx256:512, 788480 Lbx256:512, 1574912
Total weights = 2463872
Built network:[1,40,0,1[C5,5Ft64]Mp3,3Lfys128Lbx256Lbx256] from request [1,40,0,1 Ct5,5,64 Mp3,3 Lfys128 Lbx256 Lbx256]
Training parameters: Debug interval = 0, weights = 0.1, learning rate = 0.001, momentum=0.5 null char=2
Deserialize header failed: /home/shree/tesstutorial/engtest/eng.Tungsten.exp0.lstmf Load of page 0 failed! Deserialize header failed: /home/shree/tesstutorial/engtest/eng.Tungsten.exp1.lstmf Deserialize header failed: /home/shree/tesstutorial/engtest/eng.Tungsten.exp-1.lstmf Deserialize header failed: /home/shree/tesstutorial/engtest/eng.Tungsten.exp-4.lstmf Deserialize header failed: /home/shree/tesstutorial/engtest/eng.Tungsten.exp-3.lstmf Deserialize header failed: /home/shree/tesstutorial/engtest/eng.Tungsten.exp-2.lstmf Load of images failed!!`
About this issue
- Original URL
- State: closed
- Created 5 years ago
- Comments: 19
That’s right. The file with list of .lstmf files should have Unix EOL characters. It can easily be created by:
@zdenop This issue can be closed.