From 96ee97f802d81250da7e90d8f5a3c2c092fe2e9e Mon Sep 17 00:00:00 2001
From: "lamonov.pavel" <pavel.lamonov@sbps.ru>
Date: Tue, 8 Jul 2025 09:09:58 +0300
Subject: [PATCH] =?UTF-8?q?=D0=A0=D0=B0=D0=B7=D0=B4=D0=B5=D0=BB=D0=B5?=
 =?UTF-8?q?=D0=BD=D0=B8=D0=B5=20=D0=B4=D0=B0=D1=82=D0=B0=D1=81=D0=B5=D1=82?=
 =?UTF-8?q?=D0=B0=20=D0=BD=D0=B0=20=D1=82=D1=80=D0=B5=D0=BD=D0=B8=D1=80?=
 =?UTF-8?q?=D0=BE=D0=B2=D0=BE=D1=87=D0=BD=D1=8B=D0=B5=20=D0=B8=20=D0=B2?=
 =?UTF-8?q?=D0=B0=D0=BB=D0=B8=D0=B4=D0=B0=D1=86=D0=B8=D0=BE=D0=BD=D0=BD?=
 =?UTF-8?q?=D1=8B=D0=B5=20=D0=B4=D0=B0=D0=BD=D0=BD=D1=8B=D0=B5.?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 scripts/dataset_validation.py | 29 ++++++++++++++++++++++++++---
 1 file changed, 26 insertions(+), 3 deletions(-)

diff --git a/scripts/dataset_validation.py b/scripts/dataset_validation.py
index 7cc6a9e..ec2279b 100644
--- a/scripts/dataset_validation.py
+++ b/scripts/dataset_validation.py
@@ -1,5 +1,6 @@
-import os
 import cv2
+import os
+import random
 from PIL import Image
 
 def rename_files(directory_path: str):
@@ -56,11 +57,33 @@ def resize_to_height(dir_path: str, target_height=48):
             new_width = int(float(img.width) * width_percent)
             resized_img = img.resize((new_width, target_height), Image.LANZOS)
             resized_img.save(os.path.join(dir_path, filename))
-            
-    
+
+def split_dataset(dir_path: str):
+    images_dir = os.path.join(dir_path, "images")
+    filenames = os.listdir(images_dir)
+    dataset_length = len(filenames)
+    random.shuffle(filenames)
+    train_ratio = 0.8
+    val_ratio = 0.2
+    train_files_len = round(dataset_length * train_ratio)
+    val_files_len = round(dataset_length * val_ratio)
+    train_files = filenames[:train_files_len]
+    val_files = filenames[train_files_len:train_files_len+val_files_len]
+    train_file_path = os.path.join(dir_path, "train.txt")
+    val_file_path = os.path.join(dir_path, "val.txt")
+    with open(train_file_path, "w") as train_file:
+        for filename in train_files:
+            label, _ = filename.split(".")
+            train_file.write(f"{filename}\t{label}\n")
+
+    with open(val_file_path, "w") as val_file:
+        for filename in val_files:
+            label, _ = filename.split(".")
+            val_file.write(f"{filename}\t{label}\n")
 
 # rename_files("train_data/images/")
 # check_images("train_data/images/")
 # check_labels("train_data/images/")
 # check_symbols("train_data/")
 # max_height("train_data/images")
+split_dataset("train_data/")