英文:
How to add additional layers to CNN model in PyTorch?
问题
我有一个与神经网络相关的问题。在指定模型参数方面，我是一个初学者。我发现了这个关于在PyTorch中构建的DNA序列模型的示例，我想进行改进。在示例中，部署了一个基本的CNN模型，现在我想部署一个更深的模型，具有更多的层次。
基本的CNN模型
这些不是优化过的模型，只是一些初始尝试，用于测试PyTorch在DNA上下文中的使用
class DNA_CNN(nn.Module):
def init(self,
seq_len,
num_filters=32,
kernel_size=3):
super().init()
self.seq_len = seq_len
self.conv_net = nn.Sequential(# 4代表4个核苷酸nn.Conv1d(4, num_filters, kernel_size=kernel_size),nn.ReLU(inplace=True),nn.Flatten(),nn.Linear(num_filters*(seq_len-kernel_size+1), 1))def forward(self, xb):# 重新整形视图为batch_size x 4通道 x seq_len# 转置以正确排序通道xb = xb.permute(0,2,1)#print(xb.shape)out = self.conv_net(xb)return out
英文:
I have a question related to neural networks. I am a beginner in terms of specifying model parameters. I found this amazing example about DNA seq model built in PyTorch, which I want to improve. In the example, a basic CNN model was deployed and now I want to deploy a deeper model with more layers.
# basic CNN model# These aren't optimized models, just something to start with, just testing pytorch with context of DNAclass DNA_CNN(nn.Module):def __init__(self,seq_len,num_filters=32,kernel_size=3):super().__init__()self.seq_len = seq_lenself.conv_net = nn.Sequential(# 4 is for the 4 nucleotidesnn.Conv1d(4, num_filters, kernel_size=kernel_size),nn.ReLU(inplace=True),nn.Flatten(),nn.Linear(num_filters*(seq_len-kernel_size+1), 1))def forward(self, xb):# reshape view to batch_size x 4channel x seq_len# permute to put channel in correct orderxb = xb.permute(0,2,1)#print(xb.shape)out = self.conv_net(xb)return out
答案1
得分: 1
使用相同的填充来实现模块化代码，以保持序列的长度（在应用卷积之前在边界添加零）：from typing import Listclass DNA_CNN(nn.Module):def __init__(self,seq_len: int,num_filters: List[int] = [32, 64],kernel_size: int = 3):super().__init__()self.seq_len = seq_len# CNN 模块self.conv_net = nn.Sequential()num_filters = [4] + num_filtersfor idx in range(len(num_filters) - 1):self.conv_net.add_module(f"conv_{idx}",nn.Conv1d(num_filters[idx], num_filters[idx + 1],kernel_size=kernel_size, padding='same'))self.conv_net.add_module(f"relu_{idx}", nn.ReLU(inplace=True))self.conv_net.add_module("flatten", nn.Flatten())self.conv_net.add_module("linear",nn.Linear(num_filters[-1]*seq_len, 1))def forward(self, xb: torch.Tensor):"""前向传播."""xb = xb.permute(0, 2, 1)out = self.conv_net(xb)return out
要更改内核大小，您可以传递一个列表给 kernel_size，然后在卷积中使用 kernel_size=kernel_size[idx]。
如果出于某种原因您想要移除填充，您可以在卷积中移除 padding='same'，并更改 Linear 定义以匹配新的形状：
nn.Linear(num_filters[-1] * (seq_len - (len(num_filters)-1) * (kernel_size-1), 1)
英文:
Modular code to do so using padding same to keep the length of the sequence (by adding zeros in the borders before applying convolutions):
from typing import Listclass DNA_CNN(nn.Module):def __init__(self,seq_len: int,num_filters: List[int] = [32, 64],kernel_size: int = 3):super().__init__()self.seq_len = seq_len# CNN moduleself.conv_net = nn.Sequential()num_filters = [4] + num_filtersfor idx in range(len(num_filters) - 1):self.conv_net.add_module(f"conv_{idx}",nn.Conv1d(num_filters[idx], num_filters[idx + 1],kernel_size=kernel_size, padding='same'))self.conv_net.add_module(f"relu_{idx}", nn.ReLU(inplace=True))self.conv_net.add_module("flatten", nn.Flatten())self.conv_net.add_module("linear",nn.Linear(num_filters[-1]*seq_len, 1))def forward(self, xb: torch.Tensor):"""Forward pass."""xb = xb.permute(0, 2, 1)out = self.conv_net(xb)return out
To change the kernel size, you can pass a list to kernel_size and simply use kernel_size=kernel_size[idx] in the convolution.
If for some reasons you want to remove the padding you can remove padding='same' in convolution and change the Linear definition to match the new shape:
nn.Linear(num_filters[-1] * (seq_len - (len(num_filters)-1) * (kernel_size-1), 1)
通过集体智慧和协作来改善编程学习和解决问题的方式。致力于成为全球开发者共同参与的知识库，让每个人都能够通过互相帮助和分享经验来进步。
评论