OCRudoku/DatasetGenerator
Archived
4
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: 🏗️ Update architecture

Browse Source
This commit is contained in:
Louis Gallet 2024-11-28 11:37:19 +01:00
parent 3deae416b2
commit 3f91595b42
Signed by: lgallet
GPG Key ID: 84D3DF1528A84511
1 changed files with 13 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

21
main.py
View File

@ -7,7 +7,6 @@ import requests
import os import os
from multiprocessing import Pool from multiprocessing import Pool
CACHE_FOLDER = "cache/fonts" CACHE_FOLDER = "cache/fonts"
# Créer le dossier de cache s'il n'existe pas # Créer le dossier de cache s'il n'existe pas
@ -104,19 +103,21 @@ def create_letter_image(letter, output_path, font_path):
def createImageForEachLetter(args): def createImageForEachLetter(args):
""" """
Function to create an image for each of the letters passed as an argument Function to create an image for each of the letters passed as an argument
:param args: Tuple containing output folder, font path, and index :param args: Tuple containing output folder, font path, index, and type (training/validation)
""" """
output_folder, font_path, index = args output_folder, font_path, index, dataset_type = args
alphabet = string.ascii_letters # Inclut à la fois les lettres minuscules et majuscules alphabet = string.ascii_letters # Inclut à la fois les lettres minuscules et majuscules
os.makedirs(output_folder, exist_ok=True) # Ensure base output folder exists base_folder = os.path.join(output_folder, dataset_type)
os.makedirs(base_folder, exist_ok=True)
for element in alphabet: for element in alphabet:
letter_folder = os.path.join(output_folder, element) letter_folder = os.path.join(base_folder, element)
os.makedirs(letter_folder, exist_ok=True) os.makedirs(letter_folder, exist_ok=True)
create_letter_image(element, f"{letter_folder}/{element}-{index}.png", font_path) create_letter_image(element, f"{letter_folder}/{element}-{index}.png", font_path)
if __name__ == "__main__": if __name__ == "__main__":
if len(argv) < 3: if len(argv) < 3:
raise Exception("Usage: " + argv[0] + " <number-of-iterations> <api-key>") raise Exception("Usage: " + argv[0] + " <number-of-iterations> <api-key>")
@ -132,9 +133,13 @@ if __name__ == "__main__":
# Fetch fonts and cache them # Fetch fonts and cache them
fonts = [getRandomFont(api_key, usedFont) for _ in range(num_iterations)] fonts = [getRandomFont(api_key, usedFont) for _ in range(num_iterations)]
# Prepare arguments for multiprocessing # Split into training and validation datasets
args = [("dataset", fonts[i], i) for i in range(num_iterations)] num_training = int(num_iterations * 0.7)
num_validation = num_iterations - num_training
training_args = [("dataset", fonts[i], i, "training") for i in range(num_training)]
validation_args = [("dataset", fonts[i], i, "validation") for i in range(num_training, num_iterations)]
# Use multiprocessing pool # Use multiprocessing pool
with Pool() as pool: with Pool() as pool:
pool.map(createImageForEachLetter, args) pool.map(createImageForEachLetter, training_args + validation_args)