固定 Gabor 滤波器卷积神经网络

Question

我正在尝试构建一个带有一些转换层的 CNN，其中层中的一半滤波器是固定的，另一半在训练模型时是可学习的。但我没有找到任何相关内容。

我想做的与他们在本文中所做的类似https://arxiv.org/pdf/1705.04748.pdf

有没有办法在 Keras、Pytorch 中做到这一点......

Answer 1

当然。在 PyTorch 中你可以使用nn.Conv2d和

1. weight手动将其参数设置为您想要的过滤器
2. 从学习中排除这些权重

一个简单的例子是：

import torch
import torch.nn as nn

class Model(nn.Module):
    def __init__(self):
        super(Model, self).__init__()

        self.conv_learning = nn.Conv2d(1, 5, 3, bias=False)
        self.conv_gabor = nn.Conv2d(1, 5, 3, bias=False)
        # weights HAVE TO be wrapped in `nn.Parameter` even if they are not learning
        self.conv_gabor.weight = nn.Parameter(torch.randn(1, 5, 3, 3))

    def forward(self, x):
        y = self.conv_learning(x)
        y = torch.sigmoid(y)
        y = self.conv_gabor(y)

        return y.mean()

model = Model()
xs = torch.randn(10, 1, 30, 30)
ys = torch.randn(10)
loss_fn = nn.MSELoss()

# we can exclude parameters from being learned here, by filtering them
# out based on some criterion. For instance if all your fixed filters have
# "gabor" in name, the following will do
learning_parameters = (param for name, param in model.named_parameters()
                             if 'gabor' not in name)
optim = torch.optim.SGD(learning_parameters, lr=0.1)

epochs = 10
for e in range(epochs):
    y = model(xs)
    loss = loss_fn(y, ys)

    model.zero_grad()
    loss.backward()
    optim.step()