Add exam.5

exam/step5/VGGPreprocessComplete.py

+import numpy as np
+
+def VGGPreprocessing(originImgMatrix):
+    \"The only preprocessing we do is subtracting the mean RGB value, \\
+    computed on the training set, from each pixel.\\
+    原论文中对输入的RGB矩阵做了一个减去均值的预处理，该函数实现这个预处理\"
+    if type(originImgMatrix) is not np.ndarray:
+        originImgMatrix = np.ndarray(originImgMatrix)
+
+    # 矩阵X*Y*3
+    # axis=0，代表第一维，即把X（行）消除了，所以返回的是每一列RGB的均值，形状是（Y*3）
+    # axis=1, 代表第二维，即把Y（列）消除了，所以返回的是全图的RGB的均值，形状是（3，）
+    originImgMatrix_RGBMean = np.mean(originImgMatrix, axis=(0, 1))
+
+    # 直接减就行
+    subtract_Img = originImgMatrix - originImgMatrix_RGBMean
+
+    return subtract_Img
+
+
+def VGGPreprocessingBatch(batch_originImgMatrix):
+    for index, img in enumerate(batch_originImgMatrix):
+        batch_originImgMatrix[index] = VGGPreprocessing(img)
+    return batch_originImgMatrix
+
+

exam/step5/VGGPreprocessForUsers.py

+import numpy as np
+
+def VGGPreprocessingBatch(batch_originImgMatrix):
+    '''
+    你需要对batch中的每一个img的数据作如下预处理:
+    各个像素点上rgb三个通道上的值，均减去该图片上三个通道分别的均值
+    例如整张img r通道均值为2, g通道均值为1, b通道均值为3
+    某像素点为[5,1,0], 则处理后，该像素点为[3,0,-3]
+
+    :param batch_originImgMatrix: 一个数组或者是一个numpy.ndarray，shape是(batchSize,imgSize,imgSize,3)
+    :return: 返回处理正确后的数据，shape不变，返回类型为numpy.ndarray
+    '''
+
+
+    #********** Begin **********#
+
+
+    #********** End **********#
+
+

exam/step5/VGGPreprocessTest.py

+import numpy as np
+from VGGPreprocessForUsers import VGGPreprocessingBatch as userV
+
+if __name__ == '__main__':
+    #     预期输出
+
+    '''
+    [[[ -1   0   0]
+      [  1   2   3]
+      [ -1  -1  -1]]
+    
+     [[  0   1   2]
+      [  3   4   5]
+      [ -5  -5  -5]]
+    
+     [[  1   2   3]
+      [  4   5   6]
+      [-11  -8  -5]]]'''
+
+# ----------------------example---------------------------
+    a = np.array([[[1, 2, 3], [4, 5, 6], [1, 1, 1]],
+                  [[7, 8, 9], [10, 11, 12], [2, 2, 2]],
+                  [[13, 14, 15], [16, 17, 18], [0, 3, 6]]])
+
+    print('---原始矩阵---')
+    print(a)
+    print('---处理后矩阵---')
+    c = userV(a)
+    print(c,end='')
\ No newline at end of file