我正在尝试使用张量板来可视化我的pytorch模型并遇到问题。输入张量的形状为(-1、1、20、15),输出张量的形状为(-1、6)。我的模型结合了5个卷积网络的列表。
软件包:
pytorch模型如下:
import torch
from torch import nn
from torch.nn import functional as F
class MyModel(nn.Module):
"""example"""
def __init__(self, nchunks=[2, 5, 3, 2, 3], resp_size=6):
super().__init__()
self.nchunks = nchunks
self.conv = [nn.Conv2d(1, 2, (2, x)) for x in nchunks]
self.pool = nn.Sequential(
nn.AdaptiveMaxPool1d(output_size=10), nn.Flatten(start_dim=1)
)
self.bn = nn.BatchNorm1d(100)
self.fc1 = nn.Linear(100, 100)
self.fc2 = nn.Linear(100, 100)
self.fc3 = nn.Linear(100, resp_size)
def forward(self, x):
xi = torch.split(x, self.nchunks, dim=3)
xi = [f(subx.float()).view(-1, 2, 19) for f, subx in zip(self.conv, xi)]
xi = [self.pool(subx) for subx in xi]
xi = torch.cat(xi, dim=1)
xi = self.bn(xi)
xi = F.relu(self.fc1(xi))
xi = F.relu(self.fc2(xi))
xi = self.fc3(xi)
return xi
这是张量板摘要编写器的代码:
from torch.utils.tensorboard import SummaryWriter
x = torch.rand((5,1,20,15))
model = MyModel()
writer = SummaryWriter('logs')
writer.add_graph(model, x)
返回这样的错误:
RuntimeError: Cannot insert a Tensor that requires grad as a constant. Consider making it a parameter or input, or detaching the gradient
Tensor:
(1,1,.,.) =
-0.2108 -0.4986
-0.4009 -0.1910
(2,1,.,.) =
0.2383 -0.4147
0.2642 0.0456
[ torch.FloatTensor{2,1,2,2} ]
我认为该模型存在一些问题,但是我不确定会发生什么。
这个类似的github issue与我的问题无关,因为我没有使用多GPU。
答案 0 :(得分:0)
我通过替换
解决了问题[nn.Conv2d(1, 2, (2, x)) for x in nchunks]
与
nn.ModuleList([nn.Conv2d(1, 2, (2, x)) for x in nchunks])