From bc845b45afa186d2909f5237178ff500a0f7f72c Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=E5=BE=A1=E5=9D=82=E6=98=B4?= <gugugulaocuchen@gmail.com>
Date: Wed, 27 Nov 2024 17:01:26 +0800
Subject: [PATCH] =?UTF-8?q?=E5=9B=BE=E5=83=8F=E9=A2=84=E5=A4=84=E7=90=86?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 实验六/pretrain.py | 34 ++++++++++++++++++++++++++++++++++
 1 file changed, 34 insertions(+)

diff --git a/实验六/pretrain.py b/实验六/pretrain.py
index e69de29..56360e5 100644
--- a/实验六/pretrain.py
+++ b/实验六/pretrain.py
@@ -0,0 +1,34 @@
+import cv2 as cv
+import os
+import tqdm
+
+
+# 获取目录下所有文件的路径
+def get_img_names(directory):
+    file_paths = []
+    for root, dirs, files in os.walk(directory):
+        for file in files:
+            file_paths.append(os.path.join(root, file))
+    return file_paths
+
+
+# 导入并预处理
+def pretrain(img_path, save_path):
+    img = cv.imread(img_path, cv.IMREAD_GRAYSCALE)
+    _,img = cv.threshold(img,0,255,cv.THRESH_BINARY+cv.THRESH_OTSU)
+    img = cv.blur(img, (3, 3))
+
+    os.makedirs(os.path.dirname(save_path), exist_ok=True)
+
+    cv.imwrite(save_path, img)
+
+if __name__ == '__main__':
+    trains_paths=get_img_names('DataImages-Train/')
+    for train_path in tqdm.tqdm(trains_paths,desc='预处理训练文件中：'):
+        save_path=os.path.join('cache/pretrains/train', os.path.basename(train_path))
+        pretrain(train_path,save_path)
+
+    tests_paths=get_img_names('DataImages-Test/')
+    for test_path in tqdm.tqdm(tests_paths,desc='预处理测试文件中：'):
+        save_path=os.path.join('cache/pretrains/test', os.path.basename(test_path))
+        pretrain(test_path,save_path)
\ No newline at end of file