Hi,
i am trying to train a tesseract model with my own data. This is my code :
import os
# Pfade konfigurieren
TRAIN_DATA_DIR = "./data1"
TRAIN_LISTFILE = "./trainingsliste.txt"
OUTPUT_DIR = "./output"
TRAINEDDATA = "./tesseract-4.1/tessdata/deu.traineddata"
# Prüfe notwendige Pfade
if not os.path.exists(TRAIN_DATA_DIR) or not os.path.exists(TRAIN_LISTFILE)
or not os.path.exists(TRAINEDDATA):
raise FileNotFoundError("Ein oder mehrere benötigte
Verzeichnisse/Dateien fehlen.")
# Ausgabeverzeichnis erstellen, falls nicht vorhanden
if not os.path.exists(OUTPUT_DIR):
os.makedirs(OUTPUT_DIR)
# Trainingskonfiguration
MAX_ITERATIONS = 200
os.environ['OMP_THREAD_LIMIT'] = '16'
# Trainingsbefehl
command = f'lstmtraining --model_output {OUTPUT_DIR}/font_name
--traineddata {TRAINEDDATA} --train_listfile {TRAIN_LISTFILE}
--max_iterations {MAX_ITERATIONS}'
result = os.system(command + " > train_output.txt 2>&1")
print("Ausgeführter Befehl:", command)
if result != 0:
with open('train_output.txt', 'r') as file:
output = file.read()
print("Fehler beim Training:", output)
raise Exception("Fehler beim Starten des Trainingsprozesses.") and this
is the error: Must specify an input layer as the first layer, not !!
Failed to create network from spec:
--
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/22f84b7e-9dd8-4904-b09a-5f71a1c9e6dan%40googlegroups.com.
