卷积运算的意外结果

时间:2018-12-16 22:36:20

标签: machine-learning deep-learning computer-vision pytorch

这是我编写的用于执行一次卷积并输出形状的代码。

使用http://cs231n.github.io/convolutional-networks/中的公式来计算输出大小:

  

您可以说服自己正确的公式来计算   (WF + 2P)/ S + 1给许多神经元“适合”

用于计算输出大小的公式已在以下实现

def output_size(w , f , stride , padding) : 
        return (((w - f) + (2 * padding)) / stride) + 1

问题是output_size计算得出的大小为2690.5,这与卷积的结果1350不同:

%reset -f

import torch
import torch.nn.functional as F
import numpy as np
from PIL import Image
import torch.nn as nn
import torchvision
import torchvision.transforms as transforms
from pylab import plt
plt.style.use('seaborn')
%matplotlib inline

width = 60
height = 30
kernel_size_param = 5
stride_param = 2
padding_param = 2

img = Image.new('RGB', (width, height), color = 'red')

in_channels = 3
out_channels = 3

class ConvNet(nn.Module):
    def __init__(self):
        super(ConvNet, self).__init__()
        self.layer1 = nn.Sequential(
            nn.Conv2d(in_channels, 
                      out_channels, 
                      kernel_size=kernel_size_param, 
                      stride=stride_param, 
                      padding=padding_param))

    def forward(self, x):
        out = self.layer1(x)

        return out

# w : input volume size
# f : receptive field size of the Conv Layer neurons
# output_size computes spatial size of output volume - spatial dimensions are (width, height)
def output_size(w , f , stride , padding) : 
    return (((w - f) + (2 * padding)) / stride) + 1

w = width * height * in_channels
f = kernel_size_param * kernel_size_param

print('output size :' , output_size(w , f , stride_param , padding_param))

model = ConvNet()

criterion = nn.CrossEntropyLoss()
optimizer = torch.optim.Adam(model.parameters(), lr=.001)

img_a = np.array(img)
img_pt = torch.tensor(img_a).float()
result = model(img_pt.view(3, width , height).unsqueeze_(0))
an = result.view(30 , 15 , out_channels).data.numpy()

# print(result.shape)
# print(an.shape)

# print(np.amin(an.flatten('F')))

print(30 * 15 * out_channels)

我正确实现了output_size吗?如何修改此模型,以使Conv2d的结果与output_size的结果具有相同的形状?

1 个答案:

答案 0 :(得分:2)

问题是输入图像不是正方形,因此应在输入图像的widthheigth上应用公式。 同样,您也不应该在公式中使用nb_channels,因为我们明确定义了在输出中需要多少个通道。 然后,您使用f=kernel_size而不是公式中所述的f=kernel_size*kernel_size

w = width 
h = height
f = kernel_size_param
output_w =  int(output_size(w , f , stride_param , padding_param))
output_h =  int(output_size(h , f , stride_param , padding_param))
print("Output_size", [out_channels, output_w, output_h]) #--> [1, 3, 30 ,15]

然后输出大小:

print("Output size", result.shape)  #--> [1, 3, 30 ,15]  

公式来源:http://cs231n.github.io/convolutional-networks/