diff --git a/260416-2509165034.py b/260416-2509165034.py
new file mode 100644
index 0000000..e9171f2
--- /dev/null
+++ b/260416-2509165034.py
@@ -0,0 +1,74 @@
+# 练习1：图像矩阵操作
+import numpy as np
+
+image = np.array([
+    [100, 150, 200],
+    [80,  120, 180],
+    [60,  90,  140]
+], dtype=np.uint8)
+
+print("原图：")
+print(image)
+
+image_dark = image - 20
+print("\n变暗20后的图像:")
+print(image_dark)
+
+image_crop = image[0:2,0:2]
+print("\n裁剪左上角后的图像:")
+print(image_crop)
+
+image_flip = np.fliplr(image)
+print("\n水平翻转后的图像:")
+print(image_flip)
+
+
+
+# 练习2：看图写代码
+import numpy as np
+
+img = np.array([
+    [255, 255, 0,   0  ],
+    [255, 255, 0,   0  ],
+    [0,   0,   255, 255],
+    [0,   0,   255, 255]
+], dtype=np.uint8)
+
+print("原始图像:")
+print(img)
+
+white_pixel_count = np.sum(img == 255)
+black_pixel_count = np.sum(img == 0)
+print(f"\n白色像素(255)的数量:{white_pixel_count}")
+print(f"黑色像素(0)的数量:{black_pixel_count}")
+
+flipped_img_horizontal = img[:,::-1]
+print("\n水平翻转后的图像:")
+print(flipped_img_horizontal)
+
+rotated_img_ccw = img.T[:,::-1]
+print("\n逆时针旋转90度后的图像:")
+print(rotated_img_ccw)
+
+
+
+
+# 练习3：特征向量计算
+import numpy as np
+
+# 假设这是从图像中提取的2个特征图
+feature_map1 = np.array([[1, 0, 1], [0, 1, 0], [1, 0, 1]])
+feature_map2 = np.array([[1, 1, 1], [1, 0, 0], [1, 0, 0]])
+
+# 补全代码：将特征图展平为向量
+vector1 = feature_map1.flatten()  # 展平
+vector2 = feature_map2.flatten()  # 展平
+
+print("vector1:", vector1)
+print("vector2:", vector2)
+
+euclidean_distance = np.linalg.norm(vector1 - vector2)
+print("\n欧几里得距离:",euclidean_distance)
+
+cosine_similarity = np.dot(vector1,vector2) / (np.linalg.norm(vector1) * np.linalg.norm(vector2))
+print("余弦相似度:",cosine_similarity)
\ No newline at end of file