实现指定深度的卷积块的正确方法是什么？
pytorch 209
原文标题 ：What’s the correct way to implement convolutional blocks of specified depth?
我正在尝试在 PyTorch 中使用卷积神经网络实现贝叶斯优化，具体来说，我正在尝试将网络结构从 Matlab BayesOptExperiment 转换为 PyTorch。我希望我的网络具有以下结构：
输入数据 ->convblock-> maxpool ->convblock-> maxpool ->convblock-> avgpool -> flatten -> linear -> softmax
其中convblock包括：
[conv2Dlayer -> 批量归一化层 -> ReLU]，
重复了几次。当前版本仅在section_depth = 1达到 65-70% 左右的准确度时才能按预期工作，尽管如果我将 convblock 的深度提高到 10% 左右。我肯定错过了一些东西，但我不确定那是什么。我的网络结构：
import torch
import numpy as np
import torch.nn as nn
import torch.nn.functional as F
#...
class Net(nn.Module):
def __init__(self, section_depth):
super().__init__()
#! define network architecture
self.section_depth = section_depth
self.num_filters = round(16/np.sqrt(self.section_depth))
self.maxpool = nn.MaxPool2d(kernel_size=2, stride=2)
self.avgpool = nn.AvgPool2d(kernel_size=8)
self.block1 = nn.ModuleList()
self.block2 = nn.ModuleList()
self.block3 = nn.ModuleList()
self.batchnorm1 = nn.BatchNorm2d(self.num_filters)
self.batchnorm2 = nn.BatchNorm2d(2*self.num_filters)
self.batchnorm3 = nn.BatchNorm2d(4*self.num_filters)
for i in range(self.section_depth):
channels1 = 3 if i==0 else self.num_filters
channels2 = self.num_filters if i == 0 else 2*self.num_filters
channels3 = 2*self.num_filters if i == 0 else 4*self.num_filters
self.block1.append(nn.Conv2d(in_channels=channels1, out_channels=self.num_filters, kernel_size=3, padding='same'))
self.block2.append(nn.Conv2d(in_channels=channels2, out_channels=2*self.num_filters, kernel_size=3, padding='same'))
self.block3.append(nn.Conv2d(in_channels=channels3, out_channels=4*self.num_filters, kernel_size=3, padding='same'))
self.fc1 = nn.Linear(4*self.num_filters, 10) # ? number of outputs
self.softmax = nn.Softmax(dim=1)
def forward(self, x):
for i in self.block1:
x = F.relu(self.batchnorm1(i(x)))
x = self.maxpool(x)
for i in self.block2:
x = F.relu(self.batchnorm2(i(x)))
x = self.maxpool(x)
for i in self.block3:
x = F.relu(self.batchnorm3(i(x)))
x = self.avgpool(x)
x = torch.flatten(x, 1) # flatten all dimensions except batch
x = self.fc1(x)
x = self.softmax(x)
return x
任何帮助，将不胜感激。
