pytorch 卷积结构和numel()函数

from torch import nn

class CNN(nn.Module):
    def __init__(self, num_channels=1, d=56, s=12, m=4):
        super(CNN, self).__init__()
        self.first_part = nn.Sequential(
            nn.Conv2d(num_channels, d, kernel_size=3, padding=5//2),
            nn.Conv2d(num_channels, d, kernel_size=(1,3), padding=5//2),
            nn.Conv2d(num_channels, d, kernel_size=(3,1), padding=5//2),
            nn.PReLU(d)
        )

    def forward(self, x):
        x = self.first_part(x)
        return x

model = CNN()
for m in model.first_part:
    if isinstance(m, nn.Conv2d):
        # print('m:',m.weight.data)
        print('m:',m.weight.data[0])
        print('m:',m.weight.data[0][0])
        print('m:',m.weight.data.numel()) #numel() 计算矩阵中元素的个数

结果：
m: tensor([[[-0.2822,  0.0128, -0.0244],
         [-0.2329,  0.1037,  0.2262],
         [ 0.2845, -0.3094,  0.1443]]]) #卷积核大小为3x3
m: tensor([[-0.2822,  0.0128, -0.0244],
        [-0.2329,  0.1037,  0.2262],
        [ 0.2845, -0.3094,  0.1443]]) #卷积核大小为3x3
m: 504   # = 56 x (3 x 3)  输出通道数为56，卷积核大小为3x3
m: tensor([-0.0335,  0.2945,  0.2512,  0.2770,  0.2071,  0.1133, -0.1883,  0.2738,
         0.0805,  0.1339, -0.3000, -0.1911, -0.1760,  0.2855, -0.0234, -0.0843,
         0.1815,  0.2357,  0.2758,  0.2689, -0.2477, -0.2528, -0.1447, -0.0903,
         0.1870,  0.0945, -0.2786, -0.0419,  0.1577, -0.3100, -0.1335, -0.3162,
        -0.1570,  0.3080,  0.0951,  0.1953,  0.1814, -0.1936,  0.1466, -0.2911,
        -0.1286,  0.3024,  0.1143, -0.0726, -0.2694, -0.3230,  0.2031, -0.2963,
         0.2965,  0.2525, -0.2674,  0.0564, -0.3277,  0.2185, -0.0476,  0.0558]) bias偏置的值
m: tensor([[[ 0.5747, -0.3421,  0.2847]]]) 卷积核大小为1x3
m: tensor([[ 0.5747, -0.3421,  0.2847]]) 卷积核大小为1x3
m: 168 # = 56 x (1 x 3) 输出通道数为56，卷积核大小为1x3
m: tensor([ 0.5328, -0.5711, -0.1945,  0.2844,  0.2012, -0.0084,  0.4834, -0.2020,
        -0.0941,  0.4683, -0.2386,  0.2781, -0.1812, -0.2990, -0.4652,  0.1228,
        -0.0627,  0.3112, -0.2700,  0.0825,  0.4345, -0.0373, -0.3220, -0.5038,
        -0.3166, -0.3823,  0.3947, -0.3232,  0.1028,  0.2378,  0.4589,  0.1675,
        -0.3112, -0.0905, -0.0705,  0.2763,  0.5433,  0.2768, -0.3804,  0.4855,
        -0.4880, -0.4555,  0.4143,  0.5474,  0.3305, -0.0381,  0.2483,  0.5133,
        -0.3978,  0.0407,  0.2351,  0.1910, -0.5385,  0.1340,  0.1811, -0.3008]) bias偏置的值
m: tensor([[[0.0184],
         [0.0981],
         [0.1894]]]) 卷积核大小为3x1
m: tensor([[0.0184],
        [0.0981],
        [0.1894]]) 卷积核大小为3x1
m: 168 # = 56 x (3 x 1) 输出通道数为56，卷积核大小为3x1
m: tensor([-0.2951, -0.4475,  0.1301,  0.4747, -0.0512,  0.2190,  0.3533, -0.1158,
         0.2237, -0.1407, -0.4756,  0.1637, -0.4555, -0.2157,  0.0577, -0.3366,
        -0.3252,  0.2807,  0.1660,  0.2949, -0.2886, -0.5216,  0.1665,  0.2193,
         0.2038, -0.1357,  0.2626,  0.2036,  0.3255,  0.2756,  0.1283, -0.4909,
         0.5737, -0.4322, -0.4930, -0.0846,  0.2158,  0.5565,  0.3751, -0.3775,
        -0.5096, -0.4520,  0.2246, -0.5367,  0.5531,  0.3372, -0.5593, -0.2780,
        -0.5453, -0.2863,  0.5712, -0.2882,  0.4788,  0.3222, -0.4846,  0.2170]) bias偏置的值




'''初始化后'''
class CNN(nn.Module):
    def __init__(self, num_channels=1, d=56, s=12, m=4):
        super(CNN, self).__init__()
        self.first_part = nn.Sequential(
            nn.Conv2d(num_channels, d, kernel_size=3, padding=5//2),
            nn.Conv2d(num_channels, d, kernel_size=(1,3), padding=5//2),
            nn.Conv2d(num_channels, d, kernel_size=(3,1), padding=5//2),
            nn.PReLU(d)
        )
        self._initialize_weights()
    def _initialize_weights(self):
        for m in self.first_part:
            if isinstance(m, nn.Conv2d):
                nn.init.normal_(m.weight.data, mean=0.0, std=math.sqrt(2/(m.out_channels*m.weight.data[0][0].numel())))
                nn.init.zeros_(m.bias.data)

    def forward(self, x):
        x = self.first_part(x)
        return x

model = CNN()
for m in model.first_part:
    if isinstance(m, nn.Conv2d):
        # print('m:',m.weight.data)
        print('m:',m.weight.data[0])
        print('m:',m.weight.data[0][0])
        print('m:',m.weight.data.numel()) #numel() 计算矩阵中元素的个数

结果：
m: tensor([[[-0.0284, -0.0585,  0.0271],
         [ 0.0125,  0.0554,  0.0511],
         [-0.0106,  0.0574, -0.0053]]])
m: tensor([[-0.0284, -0.0585,  0.0271],
        [ 0.0125,  0.0554,  0.0511],
        [-0.0106,  0.0574, -0.0053]])
m: 504
m: tensor([0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.,
        0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.,
        0., 0., 0., 0., 0., 0., 0., 0.])
m: tensor([[[ 0.0059,  0.0465, -0.0725]]])
m: tensor([[ 0.0059,  0.0465, -0.0725]])
m: 168
m: tensor([0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.,
        0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.,
        0., 0., 0., 0., 0., 0., 0., 0.])
m: tensor([[[ 0.0599],
         [-0.1330],
         [ 0.2456]]])
m: tensor([[ 0.0599],
        [-0.1330],
        [ 0.2456]])
m: 168
m: tensor([0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.,
        0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.,
        0., 0., 0., 0., 0., 0., 0., 0.])