Question

我正在尝试为回归目的创建CNN。输入是图像数据。出于学习目的，我有10张形状为(10,3,448,448)的图像，其中10张是图像，3张是通道，448张是高度和宽度。
输出标签为(10,245)。这是我的建筑

class CNN(nn.Module):
    def __init__(self):
        super(CNN, self).__init__()
        self.conv1 = nn.Conv2d(3, 32, kernel_size=5)
        self.conv2 = nn.Conv2d(32, 32, kernel_size=5)
        self.conv3 = nn.Conv2d(32,64, kernel_size=5)
        self.fc1 = nn.Linear(3*3*64, 256)
        self.fc2 = nn.Linear(256, 245)

    def forward(self, x):
        x = F.relu(self.conv1(x))
        #x = F.dropout(x, p=0.5, training=self.training)
        x = F.relu(F.max_pool2d(self.conv2(x), 2))
        x = F.dropout(x, p=0.5, training=self.training)
        x = F.relu(F.max_pool2d(self.conv3(x),2))
        x = F.dropout(x, p=0.5, training=self.training)
        x = x.view(-1,3*3*64 )
        x = F.relu(self.fc1(x))
        x = F.dropout(x, training=self.training)
        x = self.fc2(x)
        return x

cnn = CNN()
print(cnn)

it = iter(train_loader)
X_batch, y_batch = next(it)
print(cnn.forward(X_batch).shape)

使用批次大小2，我希望模型产生的数据形状为(2,245)。但是它正在产生形状为(2592, 245)

的数据

Answer 1

在self.conv3之后，您有形状为[2，64，108，108]的张量，该张量在重整后会产生[2592，576]。这就是2592的来源。更改行： “ self.fc1 = nn.Linear（3 * 3 * 64，256）” 和 “ x = x.view（-1,3 * 3 * 64）” 以便在图层之后使用适当的图像尺寸。

下面是固定代码：

class CNN(nn.Module):
    def __init__(self):
        super(CNN, self).__init__()
        self.conv1 = nn.Conv2d(3, 32, kernel_size=5)
        self.conv2 = nn.Conv2d(32, 32, kernel_size=5)
        self.conv3 = nn.Conv2d(32,64, kernel_size=5)
        self.fc1 = nn.Linear(108*108*64, 256)
        self.fc2 = nn.Linear(256, 245)

    def forward(self, x):
        print (x.shape)
        x = F.relu(self.conv1(x))
        print (x.shape)
        #x = F.dropout(x, p=0.5, training=self.training)
        x = F.relu(F.max_pool2d(self.conv2(x), 2))
        print (x.shape)
        x = F.dropout(x, p=0.5, training=self.training)
        print (x.shape)
        x = F.relu(F.max_pool2d(self.conv3(x),2))
        print (x.shape)
        x = F.dropout(x, p=0.5, training=self.training)
        print (x.shape)
        x = x.view(-1,108*108*64 )
        print (x.shape)
        x = F.relu(self.fc1(x))
        x = F.dropout(x, training=self.training)
        x = self.fc2(x)
        return x

cnn = CNN()
print(cnn)

# X_batch, y_batch = next(it)
print(cnn.forward(X_batch).shape)

使用pytorch进行卷积神经网络回归

1 个答案: