【pytorch】簡單的一個模型做cifar10 分類（二）
前面用的網路是pytorch官方給的一個範例網路，本文參照書本換了一個網路，如下：
程式碼如下：
class CNNnet(nn.Module):
def __init__(self):
super(CNNnet,self).__init__()
self.conv1 = nn.Conv2d(in_channels=3, out_channels=16, kernel_size=5,stride=1)
self.pool1 = nn.MaxPool2d(kernel_size=2, stride=2)
self.conv2 = nn.Conv2d(in_channels=16, out_channels=36,kernel_size=3,stride=1)
self.pool2 = nn.MaxPool2d(kernel_size=2, stride=2)
self.fc1 = nn.Linear(1296, 128) # 1296 = 36 * 6 *6
self.fc2 = nn.Linear(128, 10)
def forward(self,x):
x =self.pool1(F.relu(self.conv1(x)))
x =self.pool2(F.relu(self.conv2(x)))
x = x.view(-1, 36*6*6)
x = F.relu(self.fc2(F.relu(self.fc1(x))))
return x
其中36*6*6怎麼計算來的，c*H*W，H和W都是用如下鏈接給的計算方式得到的：
【pytorch】折積層輸出尺寸的計算公式和分組折積的weight尺寸的計算https://mp.csdn.net/console/editor/html/107954603
結果如何呢？
當用瞭如下顯示初始化方式後，結果爲：
for m in net.modules():
if isinstance(m, nn.Conv2d):
nn.init.normal_(m.weight)
nn.init.xavier_normal_(m.weight)
nn.init.kaiming_normal_(m.weight) # 折積層初始化
nn.init.constant_(m.bias, 0)
elif isinstance(m, nn.Linear):
nn.init.normal_(m.weight) # 全連線層參數初始化
可以看出，其好像陷入了鞍點。其損失沒有下降了，那我還是把這個顯式初始化參數去掉試一下。
還真有效果，終於loss有值了，但是基本穩定在2.多，2個epoch時：
Accuracy of the network on the 10000 test images: 9 %
Accuracy of plane : 0 %
Accuracy of car : 89 %
Accuracy of bird : 0 %
Accuracy of cat : 0 %
Accuracy of deer : 0 %
Accuracy of dog : 0 %
Accuracy of frog : 4 %
Accuracy of horse : 0 %
Accuracy of ship : 0 %
Accuracy of truck : 0 %
那epoch=10來說，還是加上了顯式初始化哈，結果如下：
[10, 2000] loss: 1.785
[10, 4000] loss: 1.834
[10, 6000] loss: 1.833
[10, 8000] loss: 1.813
[10, 10000] loss: 1.865
[10, 12000] loss: 1.834
Finished Training
Accuracy of the network on the 10000 test images: 35 %
Accuracy of plane : 27 %
Accuracy of car : 44 %
Accuracy of bird : 12 %
Accuracy of cat : 42 %
Accuracy of deer : 38 %
Accuracy of dog : 9 %
Accuracy of frog : 47 %
Accuracy of horse : 42 %
Accuracy of ship : 64 %
Accuracy of truck : 24 %
堪憂呀。沒有達到書本上的結果。才發現初始學習率lr太高啦！改爲lr=0.001。
optimizer = optim.SGD(net.parameters(), lr=0.001, momentum=0.9)
還是如下：
我把初始化全部去掉看看
[1, 2000] loss: 2.133
[1, 4000] loss: 1.955
[1, 6000] loss: 1.930
[1, 8000] loss: 1.907
[1, 10000] loss: 1.850
[1, 12000] loss: 1.849
[2, 2000] loss: 1.774
[2, 4000] loss: 1.805
[2, 6000] loss: 1.802
[2, 8000] loss: 1.781
[2, 10000] loss: 1.790
[2, 12000] loss: 1.796
[3, 2000] loss: 1.763
[3, 4000] loss: 1.784
[3, 6000] loss: 1.830
[3, 8000] loss: 1.771
[3, 10000] loss: 1.805
[3, 12000] loss: 1.830
[4, 2000] loss: 1.803
[4, 4000] loss: 1.805
[4, 6000] loss: 1.814
[4, 8000] loss: 1.790
[4, 10000] loss: 1.805
[4, 12000] loss: 1.805
[5, 2000] loss: 1.834
[5, 4000] loss: 1.851
[5, 6000] loss: 1.846
[5, 8000] loss: 1.836
[5, 10000] loss: 1.857
[5, 12000] loss: 1.859
[6, 2000] loss: 1.814
[6, 4000] loss: 1.811
[6, 6000] loss: 1.859
[6, 8000] loss: 1.908
[6, 10000] loss: 1.873
[6, 12000] loss: 1.857
[7, 2000] loss: 1.812
[7, 4000] loss: 1.865
[7, 6000] loss: 1.836
[7, 8000] loss: 1.873
[7, 10000] loss: 1.873
[7, 12000] loss: 1.912
[8, 2000] loss: 1.840
[8, 4000] loss: 1.880
[8, 6000] loss: 1.897
[8, 8000] loss: 1.881
[8, 10000] loss: 1.855
[8, 12000] loss: 1.882
[9, 2000] loss: 1.812
[9, 4000] loss: 1.820
[9, 6000] loss: 1.873
[9, 8000] loss: 1.824
[9, 10000] loss: 1.868
[9, 12000] loss: 1.870
[10, 2000] loss: 1.853
[10, 4000] loss: 1.842
[10, 6000] loss: 1.832
[10, 8000] loss: 1.820
[10, 10000] loss: 1.878
[10, 12000] loss: 1.838
Finished Training
Accuracy of the network on the 10000 test images: 34 %
Accuracy of plane : 13 %
Accuracy of car : 49 %
Accuracy of bird : 12 %
Accuracy of cat : 38 %
Accuracy of deer : 48 %
Accuracy of dog : 14 %
Accuracy of frog : 35 %
Accuracy of horse : 39 %
Accuracy of ship : 59 %
Accuracy of truck : 30 %