在Pytorch和Captum(分类)中具有多个不同形状输入的神经网络中的特征重要性

发布于 2025-01-24 23:35:29 字数 3196 浏览 2 评论 0原文

我已经开发了一个具有三种输入类型的模型。图像,分类数据和数值数据。对于图像数据,我使用了我开发自己的网络的其他两个使用Resnet50。

class MulticlassClassification(nn.Module):
    def __init__(self, cat_size, num_col, output_size, layers, p=0.4):
        super(MulticlassClassification, self).__init__()
        
        # IMAGE: ResNet
        self.cnn = models.resnet50(pretrained = True)
        for param in self.cnn.parameters():
            param.requires_grad = False
        n_inputs = self.cnn.fc.in_features
        self.cnn.fc = nn.Sequential(
          nn.Linear(n_inputs, 250), 
          nn.ReLU(), 
          nn.Dropout(p),
          nn.Linear(250, output_size),                   
          nn.LogSoftmax(dim=1)
        )
        
        # TABULAR 
        self.all_embeddings = nn.ModuleList(
            [nn.Embedding(categories, size) for categories, size in cat_size]
        )
        self.embedding_dropout = nn.Dropout(p)
        self.batch_norm_num = nn.BatchNorm1d(num_col)

        all_layers = []
        num_cat_col = sum(e.embedding_dim for e in self.all_embeddings)
        input_size = num_cat_col + num_col

        for i in layers:
            all_layers.append(nn.Linear(input_size, i))
            all_layers.append(nn.ReLU(inplace=True))
            all_layers.append(nn.BatchNorm1d(i))
            all_layers.append(nn.Dropout(p))
            input_size = i

        all_layers.append(nn.Linear(layers[-1], output_size))

        self.layers = nn.Sequential(*all_layers)
        
        #combine
        self.combine_fc = nn.Linear(output_size * 2, output_size)

    def forward(self, image, x_categorical, x_numerical):
        embeddings = []
        for i, embedding in enumerate(self.all_embeddings):
            print(x_categorical[:,i])
            embeddings.append(embedding(x_categorical[:,i]))
        x = torch.cat(embeddings, 1)
        x = self.embedding_dropout(x)

        x_numerical = self.batch_norm_num(x_numerical)
        x = torch.cat([x, x_numerical], 1)
        x = self.layers(x)
        
        # img
        x2 = self.cnn(image)
        
        # combine
        x3 = torch.cat([x, x2], 1)
        x3 = F.relu(self.combine_fc(x3))
        
        return x

现在,经过成功的培训,我想使用Captum库来计算集成梯度。

from captum.attr import IntegratedGradients
ig = IntegratedGradients(model)

testiter = iter(testloader)
img, stack_cat, stack_num, target = next(testiter)
attributions_ig = ig.attribute(inputs=(img.cuda(), stack_cat.cuda(), stack_num.cuda()), target=target.cuda())

在这里,我有一个错误:

RuntimeError:参数1“索引”的预期张量具有以下标量类型之一:长,int;但是得到torch.cuda.floattensor(在检查嵌入的论点时)

我发现Captum将错误形状的张量注入了我的X_Categorical Input(用我的正向方法打印)。似乎Captum只看到第一个输入张量,并将其形状用于所有其他输入。我该如何改变这种行为?

我在这里找到了类似的问题( https://github.com/pytorch.com/pytorch/captum/captum/issues/issues/issues /439 )。建议将可解释的嵌入用于分类数据。当我使用它时,我得到了一个错误:

indexError:尺寸超出范围(预计在[-1,0]范围内,但获得1)

我将非常感谢任何提示,并建议如何将所有三个输入组合并解决我的问题。

I have developed a model with three inputs types. Image, categorical data and numerical data. For Image data I've used ResNet50 for the other two I develop my own network.

class MulticlassClassification(nn.Module):
    def __init__(self, cat_size, num_col, output_size, layers, p=0.4):
        super(MulticlassClassification, self).__init__()
        
        # IMAGE: ResNet
        self.cnn = models.resnet50(pretrained = True)
        for param in self.cnn.parameters():
            param.requires_grad = False
        n_inputs = self.cnn.fc.in_features
        self.cnn.fc = nn.Sequential(
          nn.Linear(n_inputs, 250), 
          nn.ReLU(), 
          nn.Dropout(p),
          nn.Linear(250, output_size),                   
          nn.LogSoftmax(dim=1)
        )
        
        # TABULAR 
        self.all_embeddings = nn.ModuleList(
            [nn.Embedding(categories, size) for categories, size in cat_size]
        )
        self.embedding_dropout = nn.Dropout(p)
        self.batch_norm_num = nn.BatchNorm1d(num_col)

        all_layers = []
        num_cat_col = sum(e.embedding_dim for e in self.all_embeddings)
        input_size = num_cat_col + num_col

        for i in layers:
            all_layers.append(nn.Linear(input_size, i))
            all_layers.append(nn.ReLU(inplace=True))
            all_layers.append(nn.BatchNorm1d(i))
            all_layers.append(nn.Dropout(p))
            input_size = i

        all_layers.append(nn.Linear(layers[-1], output_size))

        self.layers = nn.Sequential(*all_layers)
        
        #combine
        self.combine_fc = nn.Linear(output_size * 2, output_size)

    def forward(self, image, x_categorical, x_numerical):
        embeddings = []
        for i, embedding in enumerate(self.all_embeddings):
            print(x_categorical[:,i])
            embeddings.append(embedding(x_categorical[:,i]))
        x = torch.cat(embeddings, 1)
        x = self.embedding_dropout(x)

        x_numerical = self.batch_norm_num(x_numerical)
        x = torch.cat([x, x_numerical], 1)
        x = self.layers(x)
        
        # img
        x2 = self.cnn(image)
        
        # combine
        x3 = torch.cat([x, x2], 1)
        x3 = F.relu(self.combine_fc(x3))
        
        return x

Now after successful training I would like to calculate integrated gradients by using the captum library.

from captum.attr import IntegratedGradients
ig = IntegratedGradients(model)

testiter = iter(testloader)
img, stack_cat, stack_num, target = next(testiter)
attributions_ig = ig.attribute(inputs=(img.cuda(), stack_cat.cuda(), stack_num.cuda()), target=target.cuda())

And here I got an error:

RuntimeError: Expected tensor for argument #1 'indices' to have one of the following scalar types: Long, Int; but got torch.cuda.FloatTensor instead (while checking arguments for embedding)

I figured out that captum injects a wrongly shaped tensor into my x_categorical input (with the print in my forward method). It seems like captum only sees the first input tensor and uses it's shape for all other inputs. How can I change this behaviour?

I've found the similar issue here (https://github.com/pytorch/captum/issues/439). It was recommended to use Interpretable Embedding for categorical data. When I used it I got this error:

IndexError: Dimension out of range (expected to be in range of [-1, 0], but got 1)

I would be very grateful for any tips and advises how to combine all three inputs and to solve my problem.

如果你对这篇内容有疑问,欢迎到本站社区发帖提问 参与讨论,获取更多帮助,或者扫码二维码加入 Web 技术交流群。

扫码二维码加入Web技术交流群

发布评论

需要 登录 才能够评论, 你可以免费 注册 一个本站的账号。
列表为空,暂无数据
我们使用 Cookies 和其他技术来定制您的体验包括您的登录状态等。通过阅读我们的 隐私政策 了解更多相关信息。 单击 接受 或继续使用网站,即表示您同意使用 Cookies 和您的相关数据。
原文