1

我发现为了从stride 1 生成(X - x + 1, Y - y + 1)大小的补丁,image 要求我们将 strides 参数设置为or 。我不知道他们如何快速计算出这个数字。conv2d 的进步(x,y)(X,Y)img.strides * 2img.strides + img.strides

但是我应该怎么做才能((X-x)/stride)+1, ((Y-y)/stride)+1从相同大小的图像中获得相同大小的补丁stride呢?


从这个 SO答案 稍作修改,通道和图像数量放在前面

def patchify(img, patch_shape):
    a,b,X, Y = img.shape                # a images and b channels
    x, y = patch_shape
    shape = (a, b, X - x + 1, Y - y + 1, x, y)
    a_str, b_str, X_str, Y_str = img.strides
    strides = (a_str, b_str, X_str, Y_str, X_str, Y_str)
    return np.lib.stride_tricks.as_strided(img, shape=shape, strides=strides)

我可以看到它创建了一个大小为 (x,y) 且步幅为 1 的滑动窗口(向右移动 1 个像素并向下移动 1 个像素)。我无法将as_strided使用的步幅参数与我们通常用于 conv2d 的步幅关联起来。

如何向上述计算as_stridedstrides 参数的函数添加参数?

def patchify(img, patch_shape, stride):    # stride=stepsize in conv2d eg: 1,2,3,...
    a,b,X,Y = img.shape                    # a images and b channels
    x, y = patch_shape
    shape = (a,b,((X-x)/stride)+1, ((Y-y)/stride)+1, x, y)
    strides = ???                          # strides for as_strided
    return np.lib.stride_tricks.as_strided(img, shape=shape, strides=strides)

img 是 4d(a, b, X, Y)

  • a=图像数量,
  • b=频道数,
  • (X,Y)= 宽度和高度

注意stride in conv2d我的意思stepsize 是不幸的是,这也称为步幅

注意 2:由于stepsize通常在两个轴上都相同,因此在我提供的代码中,我只提供了一个参数,但是将它用于两个维度。

游乐场:strides 这里 有什么用。我让它在stepsize=1 这里运行。我注意到它可能无法从链接中使用,但在粘贴到新的playground时可以使用。

这应该清楚地了解我需要什么:

[[ 0.5488135   0.71518937  0.60276338  0.54488318]
 [ 0.4236548   0.64589411  0.43758721  0.891773  ]
 [ 0.96366276  0.38344152  0.79172504  0.52889492]
 [ 0.56804456  0.92559664  0.07103606  0.0871293 ]]

# patch_size = 2x2
# stride = 1,1

[[[[ 0.5488135   0.71518937]
   [ 0.4236548   0.64589411]]

  [[ 0.71518937  0.60276338]
   [ 0.64589411  0.43758721]]

  [[ 0.60276338  0.54488318]
   [ 0.43758721  0.891773  ]]]


 [[[ 0.4236548   0.64589411]
   [ 0.96366276  0.38344152]]

  [[ 0.64589411  0.43758721]
   [ 0.38344152  0.79172504]]

  [[ 0.43758721  0.891773  ]
   [ 0.79172504  0.52889492]]]


 [[[ 0.96366276  0.38344152]
   [ 0.56804456  0.92559664]]

  [[ 0.38344152  0.79172504]
   [ 0.92559664  0.07103606]]

  [[ 0.79172504  0.52889492]
   [ 0.07103606  0.0871293 ]]]]

# stride = 2,2

[[[[[[ 0.5488135   0.71518937]
     [ 0.4236548   0.64589411]]

    [[ 0.60276338  0.54488318]
     [ 0.43758721  0.891773  ]]]


   [[[ 0.96366276  0.38344152]
     [ 0.56804456  0.92559664]]

    [[ 0.79172504  0.52889492]
     [ 0.07103606  0.0871293 ]]]]]]

# stride = 2,1

[[[[ 0.5488135   0.71518937]
   [ 0.4236548   0.64589411]]

  [[ 0.71518937  0.60276338]
   [ 0.64589411  0.43758721]]

  [[ 0.60276338  0.54488318]
   [ 0.43758721  0.891773  ]]]

 [[[ 0.96366276  0.38344152]
   [ 0.56804456  0.92559664]]

  [[ 0.38344152  0.79172504]
   [ 0.92559664  0.07103606]]

  [[ 0.79172504  0.52889492]
   [ 0.07103606  0.0871293 ]]]]
4

1 回答 1

2

这是一种方法 -

def patchify(img, patch_shape, stepsize_x=1, stepsize_y=1): 
    strided = np.lib.stride_tricks.as_strided
    x, y = patch_shape    
    p,q = img.shape[-2:]    
    sp,sq = img.strides[-2:]

    out_shp = img.shape[:-2] + (p-x+1,q-y+1,x,y)
    out_stride = img.strides[:-2] + (sp,sq,sp,sq)

    imgs = strided(img, shape=out_shp, strides=out_stride)
    return imgs[...,::stepsize_x,::stepsize_y,:,:]

样品运行 -

1]输入:

In [156]: np.random.seed(0)

In [157]: img = np.random.randint(11,99,(2,4,4))

In [158]: img
Out[158]: 
array([[[55, 58, 75, 78],
        [78, 20, 94, 32],
        [47, 98, 81, 23],
        [69, 76, 50, 98]],

       [[57, 92, 48, 36],
        [88, 83, 20, 31],
        [91, 80, 90, 58],
        [75, 93, 60, 40]]])

2] 输出 - 案例 #1:

In [159]: patchify(img, (2,2), stepsize_x=1, stepsize_y=1)[0]
Out[159]: 
array([[[[55, 58],
         [78, 20]],

        [[58, 75],
         [20, 94]],

        [[75, 78],
         [94, 32]]],


       [[[78, 20],
         [47, 98]],

        [[20, 94],
         [98, 81]],

        [[94, 32],
         [81, 23]]],


       [[[47, 98],
         [69, 76]],

        [[98, 81],
         [76, 50]],

        [[81, 23],
         [50, 98]]]])

3] 输出 - 案例 #2:

In [160]: patchify(img, (2,2), stepsize_x=2, stepsize_y=1)[0]
Out[160]: 
array([[[[55, 58],
         [78, 20]],

        [[58, 75],
         [20, 94]],

        [[75, 78],
         [94, 32]]],


       [[[47, 98],
         [69, 76]],

        [[98, 81],
         [76, 50]],

        [[81, 23],
         [50, 98]]]])

4] 输出 - 案例#3:

In [161]: patchify(img, (2,2), stepsize_x=2, stepsize_y=2)[0]
Out[161]: 
array([[[[55, 58],
         [78, 20]],

        [[75, 78],
         [94, 32]]],


       [[[47, 98],
         [69, 76]],

        [[81, 23],
         [50, 98]]]])
于 2017-11-24T09:59:07.487 回答