神经网络基础篇——刘二大人

#测试卷积尺寸
import torch
in_channels,out_channels = 5,10
width,height = 100,100
kernel_size = 3
batch_size = 1

input = torch.randn(batch_size,
                    in_channels,
                    width,
                    height)
conv_layer = torch.nn.Conv2d(
                            in_channels,
                            out_channels,
                            kernel_size=kernel_size
)
output = conv_layer(input)

print(input.shape)
print(output.shape)
print(conv_layer.weight.shape)#卷积层权重尺寸

# torch.Size([1, 5, 100, 100])
# torch.Size([1, 10, 98, 98])
# torch.Size([10, 5, 3, 3])

定义卷积层，注意四个值，输入通道数、输出通道数、卷积核大小、

import torch
input = [3,4,6,5,7,
         2,4,6,8,2,
         1,6,7,8,4,
         9,7,4,6,2,
         3,7,5,4,1]
input = torch.Tensor(input).view(1,1,5,5)

conv_layer = torch.nn.Conv2d(1,1,kernel_size=3,padding=1,bias=False)

kernel = torch.Tensor([1,2,3,4,5,6,7,8,9]).view(1,1,3,3)
conv_layer.weight.data = kernel.data

output = conv_layer(input)
print(output)

#输出结果
# tensor([[[[ 91., 168., 224., 215., 127.],
#           [114., 211., 295., 262., 149.],
#           [192., 259., 282., 214., 122.],
#           [194., 251., 253., 169.,  86.],
#           [ 96., 112., 110.,  68.,  31.]]]],
#        grad_fn=<MkldnnConvolutionBackward>)
#

将上面代码的padding=1改为stride=2.结果如下：

tensor([[[[211., 262.],
          [251., 169.]]]], grad_fn=<MkldnnConvolutionBackward>)

pooling层不会改变通道的数量









语言的艺术：错误率从3%到2%，不是降低了1%，而是降低了百分之30