PVEN改进基于关系网络

最新推荐文章于 2023-02-12 00:08:13 发布

无名之辈_

最新推荐文章于 2023-02-12 00:08:13 发布

阅读量355

点赞数

文章标签：网络深度学习神经网络

本文链接：https://blog.csdn.net/nini_k/article/details/118694687

版权

本文介绍了如何基于深度学习改进关系网络，首先将batch['id']转化为one-hot编码，然后在epoch循环中应用关系网络。实验中尝试了两种版本：一是使用fc层对全局信息进行分类；二是参照'learning to compare'的数据组织方式。由于训练中断，计划从上次停止处继续训练。

摘要由CSDN通过智能技术生成

先实现一个简单的关系网络

def dense_to_one_hot(labels_dense, num_classes):
   """Convert class labels from scalars to one-hot vectors."""
   num_labels = labels_dense.shape[0]
   index_offset = np.arange(num_labels) * num_classes
   labels_one_hot = np.zeros((num_labels, num_classes))
   labels_one_hot.flat[index_offset + labels_dense.ravel()] = 1
   return labels_one_hot

class RelationNetwork(nn.Module):
    """docstring for RelationNetwork"""
    def __init__(self,input_size,hidden_size):
        super(RelationNetwork, self).__init__()
        # self.layer1 = nn.Sequential(
        #                 nn.Conv2d(128,64,kernel_size=3,padding=1),
        #                 nn.BatchNorm2d(64, momentum=1, affine=True),
        #                 nn.ReLU(),
        #                 nn.MaxPool2d(2))
        # self.layer2 = nn.Sequential(
        #                 nn.Conv2d(64,64,kernel_size=3,padding=1),
        #                 nn.BatchNorm2d(64, momentum=1, affine=True),
        #                 nn.ReLU(),
        #                 nn.MaxPool2d(2))
        self.fc1 = nn.Linear(input_size,hidden_size)
        self.fc2 = nn.Linear(hidden_size,576)

    def forward(self,x):
        # out = self.layer1(x)
        # out = self.layer2(out)
        # out = out.view(out.size(0),-1)
        out = F.relu(self.fc1