3-1-2 衔接与拓展：从图像矩阵到文本向量

0416+2509165015/1.py

@@ -0,0 +1,17 @@
+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("\n1. 变暗20后：")
+print(image_dark)
+image_crop = image[0:2, 0:2]
+print("\n2. 裁剪左上角2×2后：")
+print(image_crop)
+image_flip = np.fliplr(image)
+print("\n3. 水平翻转后：")
+print(image_flip)

0416+2509165015/2.py

@@ -0,0 +1,16 @@
+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)
+white_count = np.sum(img == 255)
+black_count = np.sum(img == 0)
+print(f"1. 白色像素(255)数量：{white_count}，黑色像素(0)数量：{black_count}")
+img_flip = np.fliplr(img)
+print("\n2. 水平翻转后：")
+print(img_flip)
+img_rot90 = np.flipud(img.T)
+print("\n3. 逆时针旋转90度后：")
+print(img_rot90)

0416+2509165015/3.py

@@ -0,0 +1,11 @@
+import numpy as np
+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]])
+vector1 = feature_map1.flatten()  
+vector2 = feature_map2.flatten() 
+print("vector1:", vector1)
+print("vector2:", vector2)
+euclidean_dist = np.linalg.norm(vector1 - vector2)
+print(f"\n1. 欧几里得距离：{euclidean_dist:.4f}")
+cos_similarity = np.dot(vector1, vector2) / (np.linalg.norm(vector1) * np.linalg.norm(vector2))
+print(f"2. 余弦相似度：{cos_similarity:.4f}")

0416+2509165015/4.py

@@ -0,0 +1,17 @@
+import numpy as np
+corpus = [
+    "我 喜欢 编程",
+    "我 喜欢 学习 Python",
+    "编程 是 有趣 的"
+]
+vocab = sorted(list(set(" ".join(corpus).split())))
+print("词汇表：", vocab)
+def text_to_vector(text, vocab):
+    words = text.split()
+    vector = np.zeros(len(vocab), dtype=int)
+    for i, word in enumerate(vocab):
+        vector[i] = words.count(word)
+    return vector
+vectors = np.array([text_to_vector(text, vocab) for text in corpus])
+print("\n文本向量化结果：")
+print(vectors)