Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Question about class Ublock #16

Open
PoistRXE opened this issue Jun 16, 2022 · 2 comments
Open

Question about class Ublock #16

PoistRXE opened this issue Jun 16, 2022 · 2 comments

Comments

@PoistRXE
Copy link

wen博,你好
我有一个问题想请教您,是关于'train_pointgroup.py'中创建网络模型时用到的UBlock类
这个类的forward方法实现如下:

  def forward(self, input):
      output = self.blocks(input)
      identity = spconv.SparseConvTensor(output.features, output.indices, output.spatial_shape, output.batch_size)
      if len(self.nPlanes) > 1:
          output_decoder = self.conv(output)
          output_decoder = self.u(output_decoder)
          output_decoder = self.deconv(output_decoder)
          output.features = torch.cat((identity.features, output_decoder.features), dim=1)
          output = self.blocks_tail(output)

      return output

len(self.nPlanes) > 1时,output.features的维度是self.nPlanes[0]*2output的维度是self.nPlanes[0],但是self.blocks_tail()需要outputoutput.features这两个tensor的维度都是self.nPlanes[0],为什么这里会出现函数输入维度和实际输入维度不一致的情况呢?

@wenbowen123
Copy link
Owner

Did you meet any error when running the segmentation?

@PoistRXE
Copy link
Author

PoistRXE commented Jul 7, 2022

您的程序应该是没有问题的,只是我的电脑显卡是3060 laptop,和您搭建的docker环境无法兼容(1650 laptop显卡能够兼容您的docker环境),所以我没有办法运行基于gpu运行的神经网络,主要是没有办法运行和调试pointgroup net,因为另外两个网络(grasp net和nunocs net)都可以通过修改代码实现cpu运行,能够现实正常的运行和调试。
我之所以提出这个问题是我不太理解这个网络的结构,在推导网络结构的时候发现了这个问题,不知道您对这个网络是否有比较好的理解方式或解释

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants