TwoAbove · Penguin2600 · Mar 4, 2024 · Mar 5, 2024 · TwoAbove · Mar 5, 2024
diff --git a/dataScripts/tessTrain/example_truth/1039279885.gt.txt b/dataScripts/tessTrain/example_truth/1039279885.gt.txt
@@ -0,0 +1 @@
+1039279885
diff --git a/dataScripts/tessTrain/example_truth/1039279885.png b/dataScripts/tessTrain/example_truth/1039279885.png
diff --git a/dataScripts/tessTrain/example_truth/104069277.gt.txt b/dataScripts/tessTrain/example_truth/104069277.gt.txt
@@ -0,0 +1 @@
+104069277
diff --git a/dataScripts/tessTrain/example_truth/104069277.png b/dataScripts/tessTrain/example_truth/104069277.png
diff --git a/dataScripts/tessTrain/example_truth/1120865009.gt.txt b/dataScripts/tessTrain/example_truth/1120865009.gt.txt
@@ -0,0 +1 @@
+1120865009
diff --git a/dataScripts/tessTrain/example_truth/1120865009.png b/dataScripts/tessTrain/example_truth/1120865009.png
diff --git a/dataScripts/tessTrain/example_truth/1157374083.gt.txt b/dataScripts/tessTrain/example_truth/1157374083.gt.txt
@@ -0,0 +1 @@
+1157374083
diff --git a/dataScripts/tessTrain/example_truth/1157374083.png b/dataScripts/tessTrain/example_truth/1157374083.png
diff --git a/dataScripts/tessTrain/example_truth/1242187802.gt.txt b/dataScripts/tessTrain/example_truth/1242187802.gt.txt
@@ -0,0 +1 @@
+1242187802
diff --git a/dataScripts/tessTrain/example_truth/1242187802.png b/dataScripts/tessTrain/example_truth/1242187802.png
diff --git a/dataScripts/tessTrain/example_truth/1293982005.gt.txt b/dataScripts/tessTrain/example_truth/1293982005.gt.txt
@@ -0,0 +1 @@
+1293982005
diff --git a/dataScripts/tessTrain/example_truth/1293982005.png b/dataScripts/tessTrain/example_truth/1293982005.png
diff --git a/dataScripts/tessTrain/example_truth/1307855064.gt.txt b/dataScripts/tessTrain/example_truth/1307855064.gt.txt
@@ -0,0 +1 @@
+1307855064
diff --git a/dataScripts/tessTrain/example_truth/1307855064.png b/dataScripts/tessTrain/example_truth/1307855064.png
diff --git a/dataScripts/tessTrain/example_truth/1335408497.gt.txt b/dataScripts/tessTrain/example_truth/1335408497.gt.txt
@@ -0,0 +1 @@
+1335408497
diff --git a/dataScripts/tessTrain/example_truth/1335408497.png b/dataScripts/tessTrain/example_truth/1335408497.png
diff --git a/dataScripts/tessTrain/example_truth/1401381498.gt.txt b/dataScripts/tessTrain/example_truth/1401381498.gt.txt
@@ -0,0 +1 @@
+1401381498
diff --git a/dataScripts/tessTrain/example_truth/1401381498.png b/dataScripts/tessTrain/example_truth/1401381498.png
diff --git a/dataScripts/tessTrain/example_truth/1494819970.gt.txt b/dataScripts/tessTrain/example_truth/1494819970.gt.txt
@@ -0,0 +1 @@
+1494819970
diff --git a/dataScripts/tessTrain/example_truth/1494819970.png b/dataScripts/tessTrain/example_truth/1494819970.png
diff --git a/dataScripts/tessTrain/example_truth/1588056367.gt.txt b/dataScripts/tessTrain/example_truth/1588056367.gt.txt
@@ -0,0 +1 @@
+1588056367
diff --git a/dataScripts/tessTrain/example_truth/1588056367.png b/dataScripts/tessTrain/example_truth/1588056367.png
diff --git a/dataScripts/tessTrain/example_truth/1668624399.gt.txt b/dataScripts/tessTrain/example_truth/1668624399.gt.txt
@@ -0,0 +1 @@
+1668624399
diff --git a/dataScripts/tessTrain/example_truth/1668624399.png b/dataScripts/tessTrain/example_truth/1668624399.png
diff --git a/dataScripts/tessTrain/example_truth/1713389101.gt.txt b/dataScripts/tessTrain/example_truth/1713389101.gt.txt
@@ -0,0 +1 @@
+1713389101
diff --git a/dataScripts/tessTrain/example_truth/1713389101.png b/dataScripts/tessTrain/example_truth/1713389101.png
diff --git a/dataScripts/tessTrain/example_truth/1763858340.gt.txt b/dataScripts/tessTrain/example_truth/1763858340.gt.txt
@@ -0,0 +1 @@
+1763858340
diff --git a/dataScripts/tessTrain/example_truth/1763858340.png b/dataScripts/tessTrain/example_truth/1763858340.png
diff --git a/dataScripts/tessTrain/example_truth/1996779286.gt.txt b/dataScripts/tessTrain/example_truth/1996779286.gt.txt
@@ -0,0 +1 @@
+1996779286
diff --git a/dataScripts/tessTrain/example_truth/1996779286.png b/dataScripts/tessTrain/example_truth/1996779286.png
diff --git a/dataScripts/tessTrain/example_truth/2014646864.gt.txt b/dataScripts/tessTrain/example_truth/2014646864.gt.txt
@@ -0,0 +1 @@
+2014646864
diff --git a/dataScripts/tessTrain/example_truth/2014646864.png b/dataScripts/tessTrain/example_truth/2014646864.png
diff --git a/dataScripts/tessTrain/example_truth/404341978.gt.txt b/dataScripts/tessTrain/example_truth/404341978.gt.txt
@@ -0,0 +1 @@
+404341978
diff --git a/dataScripts/tessTrain/example_truth/404341978.png b/dataScripts/tessTrain/example_truth/404341978.png
diff --git a/dataScripts/tessTrain/example_truth/428256746.gt.txt b/dataScripts/tessTrain/example_truth/428256746.gt.txt
@@ -0,0 +1 @@
+428256746
diff --git a/dataScripts/tessTrain/example_truth/428256746.png b/dataScripts/tessTrain/example_truth/428256746.png
diff --git a/dataScripts/tessTrain/example_truth/97984949.gt.txt b/dataScripts/tessTrain/example_truth/97984949.gt.txt
@@ -0,0 +1 @@
+97984949
diff --git a/dataScripts/tessTrain/example_truth/97984949.png b/dataScripts/tessTrain/example_truth/97984949.png
diff --git a/dataScripts/tessTrain/example_truth/984313802.gt.txt b/dataScripts/tessTrain/example_truth/984313802.gt.txt
@@ -0,0 +1 @@
+984313802
diff --git a/dataScripts/tessTrain/example_truth/984313802.png b/dataScripts/tessTrain/example_truth/984313802.png
diff --git a/dataScripts/tessTrain/tessTrain.sh b/dataScripts/tessTrain/tessTrain.sh
@@ -0,0 +1,89 @@
+#!/bin/bash
+# Author: Charles Bock
+# Email: [email protected]
+# Date: 2024-02-27
+# Tested on a bare install of Ubuntu 22.04.3 LTS
+
+set -e
+
+# Color Stuff
+BGreen='\033[1;32m'
+NC='\033[0m'
+
+greentext () {
+   echo -e "\n${BGreen}### $1 ${NC}\n"
+}
+
+# Build tesseract
+# Upstream Docs: https://tesseract-ocr.github.io/tessdoc/Compiling-%E2%80%93-GitInstallation#installing-with-autoconf-tools
+greentext "Installing Deps and Creating File Structure"
+
+# Dont polute the directory
+mkdir -p ./tess
+cd tess
+pwd
+
+# Get Deps
+sudo apt-get install libicu-dev libpango1.0-dev libcairo2-dev
+sudo apt-get install automake ca-certificates g++ git libtool libleptonica-dev make pkg-config
+sudo apt-get install libpango1.0-dev libleptonica-dev
+
+greentext "Cloning Tesseract"
+
+git clone https://github.com/tesseract-ocr/tesseract.git 2> /dev/null || (cd tesseract ; git pull; cd ..)
+
+# Build the training tools
+# Upstream Docs: https://tesseract-ocr.github.io/tessdoc/Compiling-%E2%80%93-GitInstallation#build-with-training-tools
+greentext "Building Tesseract WITH Training Tools - This can take a long time"
+
+sudo apt-get install libicu-dev
+sudo apt-get install libpango1.0-dev
+sudo apt-get install libcairo2-dev
+
+cd tesseract
+
+./autogen.sh
+./configure
+make
+sudo make install
+sudo ldconfig
+make training
+sudo make training-install
+
+greentext "Finished Building Teseract and Training Tools"
+
+cd ..
+pwd
+
+# Install and configure tesstrain
+# Upstream Docs: https://github.com/tesseract-ocr/tesstrain?tab=readme-ov-file#choose-model-name
+
+greentext "Pulling the required ENG traineddata from github"
+wget https://github.com/tesseract-ocr/tessdata/raw/main/eng.traineddata
+sudo mv eng.traineddata /usr/local/share/tessdata
+
+greentext "Cloning Tesstrain"
+git clone https://github.com/tesseract-ocr/tesstrain.git 2> /dev/null || (cd tesstrain ; git pull; cd ..)
+cd tesstrain
+pwd
+
+greentext "Generating Tesstrain Langdata"
+make tesseract-langdata
+
+greentext "Creating and populating tesstrain ground truth Directory Structure"
+mkdir -p ./data/noita-ground-truth
+
+# Copy our example data in
+cp -ar ../../truth/example_truth/* ./data/noita-ground-truth
+
+greentext "Running Example Training - This can take some time"
+# Run training against our example data
+make training MODEL_NAME=noita
+
+if test -f ./data/noita.traineddata; then
+  greentext "Example Model was trained successfully"
+  greentext "Setup is complete and tested"
+  greentext "You are now ready for Training"
+
+  exit 0
+fi