Pytorch使用小技巧

1、nn.Conv2d默认padding为'valid'，如何设置为'same'？

使用公式计算：

• o = output
• p = padding
• k = kernel_size
• s = stride
• d = dilation

o = [i + 2*p - k - (k-1)*(d-1)]/s + 1

参考网址：

https://discuss.pytorch.org/t/how-to-keep-the-shape-of-input-and-output-same-when-dilation-conv/14338

2、在创建网络的class NetworkName(nn.Module):的def __init__(self):中，一定要加上super(NetworkName, self).__init__()

否则会报错：AttributeError: cannot assign module before Module.__init__() call

正确使用方式（代码片段来源：Neural Networks - Pytorch Tutorials）：

import torch
import torch.nn as nn
import torch.nn.functional as F


class Net(nn.Module):

    def __init__(self):
        super(Net, self).__init__()
        # 1 input image channel, 6 output channels, 5x5 square convolution
        # kernel
        self.conv1 = nn.Conv2d(1, 6, 5)
        self.conv2 = nn.Conv2d(6, 16, 5)
        # an affine operation: y = Wx + b
        self.fc1 = nn.Linear(16 * 5 * 5, 120)
        self.fc2 = nn.Linear(120, 84)
        self.fc3 = nn.Linear(84, 10)

参考网址：

https://discuss.pytorch.org/t/attributeerror-cannot-assign-module-before-module---init---call/1446