-
Notifications
You must be signed in to change notification settings - Fork 363
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
How to visualise spconv #700
Comments
Hello, have you solved the issue? I'm also currently researching interpretable learning for 3D CNNs. Specifically, I'm referring to Class Activation Mapping (CAM) and Grad-CAM, which use heatmaps to represent the importance of specific regions in an image for predicting the output. I came across a method on GitHub (https://github.com/yiskw713/3DClassActivationMapping) which is primarily designed for video inputs, where the visualization is done for each frame. I made some modifications to adapt it for point cloud learning tasks. Additionally, I encountered gradient-related issues when using sparse convolutions with spconv for generating Grad-CAM. As a result, I modified the network architecture to use conv3d, which introduces some discrepancies compared to the results obtained with sparse convolutions. I also found a paper titled "Visual Explanations From Deep 3D Convolutional Neural Networks for Alzheimer’s Disease Classification" that proposes four methods for visualizing 3D CNNs. It could be helpful to refer to and learn from. |
@huobailiu 谢谢你提供的方法。我大致看了一下您发的方法,貌似现在的3dcnn的可视化都是基于普通的conv3d。将spconv转化为conv3d之后再画热力图的方法我觉得是可行的,但是其实我是在看《Focal Sparse Convolutional Networks for 3D Object Detection》时才产生了可视化3d稀疏卷积的想法。 |
Hello, I also read this paper, I also want to achieve such an effect, may I ask you to achieve it? |
I'm wondering how to visualise spconv's focus, there are plugins for 2D convolution that show exactly which positions the current network is focusing on, and I'm wondering if spconv has a similar tool.
The text was updated successfully, but these errors were encountered: