时间戳

首页 > 解决方案 > 在 def init PyTorch 中获取 CNN 层输出大小

python - 在 def init PyTorch 中获取 CNN 层输出大小

问题描述

在 PyTorch 中定义我们的模型架构时，我们需要指定 CNN 输出层的大小以馈入该nn.Linear层。我们如何在def __init__函数中找到这一层的大小（不是在def forward()）

class model(nn.Module):

    def __init__(self,word_count,img_channel,n_out):
        super(multimodal,self).__init__()

        # CNN image encoding hyperparameters
        conv1_channel_out = 8
        conv1_kernel = 5

        pool1_size = 2

        conv2_channel_out = 16
        conv2_kernel = 16

        pool2_size = 2

        conv3_channel_out = 32
        conv3_kernel = 4

        dropout_rate = 0.1

        cnn_fc_out = 512

        comb_fc1_out = 512
        comb_fc2_out = 128

        # FNN text encoding hyperparameters
        text_fc1_out = 4096
        text_fc2_out = 512


        # Text encoding
        self.text_fc1 = nn.Linear(word_count, text_fc1_out)
        self.text_fc2 = nn.Linear(text_fc1_out, text_fc2_out)


        # Image encoding
        self.conv1 = nn.Conv2d(img_channel, conv1_channel_out, conv1_kernel)
        self.max_pool1 = nn.MaxPool2d(pool1_size)
        self.conv2 = nn.Conv2d(conv1_channel_out, conv2_channel_out, conv2_kernel)
        self.max_pool2 = nn.MaxPool2d(pool2_size)
        self.conv3 = nn.Conv2d(conv2_channel_out, conv3_channel_out, conv3_kernel)

        self.cnn_dropout = nn.Dropout(dropout_rate)
        self.cnn_fc = nn.Linear(32*24*12, cnn_fc_out)

        #Concat layer
        concat_feat = cnn_fc_out + text_fc2_out
        self.combined_fc1 = nn.Linear(concat_feat, comb_fc1_out)
        self.combined_fc2 = nn.Linear(comb_fc1_out, comb_fc2_out)
        self.output_fc = nn.Linear(comb_fc2_out, n_out)


    def forward(self, text, img):
        # Image Encoding
        x = F.relu(self.conv1(img))
        x = self.max_pool1(x)
        x = F.relu(self.conv2(x))
        x = self.max_pool2(x)
        x = F.relu(self.conv3(x))
        x = x.view(-1, 32*24*12)
        x = self.cnn_dropout(x)
        img = F.relu(self.cnn_fc(x))

        # Text Encoding
        text = F.relu(self.text_fc1(text))
        text = F.relu(self.text_fc2(text))

        # Concat the features
        concat_inp = torch.cat((text, img), 1)
        out = F.relu(self.combined_fc1(concat_inp))
        out = F.relu(self.combined_fc2(out))
        return torch.sigmoid(self.output_fc(out))

如果你看到上面，我手动 定义了 CNN 输出层的大小为 32 24 12self.cnn_fc = nn.Linear(32*24*12, cnn_fc_out)

我怎样才能避免这种情况？我知道我们也许可以打电话[model_name].[layer_name].in_features，def forward()但不能def __init__()

标签： pythonmachine-learningdeep-learningneural-networkpytorch

解决方案

我认为没有特定的方法可以做到这一点。您必须运行一个示例（您可以仅x = torch.rand((1, C, W, H))用于测试），然后在线性层之前打印出 conv 层的形状，然后记住该数字并将其硬编码到init中。或者您可以使用公式根据输入的尺寸、内核大小、填充等来计算卷积层的形状。这是关于这些公式的线程。

推荐阅读