Comments (2)
Hi, thanks for the great work. I am curious about how you have trained your network to predict confidence. Does one of the losses mentioned in the paper supervise the confidence estimate? If not, then could you please provide the loss function you used to supervise the confidence?
Furthermore, it seems like the confidence is appropriately predicted in the range [0, 1], however, the output of the network block that outputs the confidences is only a convolutional layer, and I see no sigmoid layer. How come?
Thanks!
Thanks for your interest! It was supervised by: 1-|depth_gt-depth_pred|/depth_gt
with L1 loss.
It should have been constrained into 0-1 by Sigmoid function, while is not the case due to code legacy issues.
from metric3d.
Thanks!
from metric3d.
Related Issues (20)
- Pixel represented focal length or real world scale focal length(mm) HOT 4
- Some problems in Training HOT 3
- Supporting old GPUs? HOT 3
- metric_scale in nyu.py HOT 1
- Speed Up Inference HOT 2
- NYU dataset and json HOT 1
- Inference Speed data
- normals not normal HOT 2
- Unable to adjust scale of depth correctly in the wild-mode HOT 1
- How to convert the DINO2reg-ViT model to an ONNX model HOT 2
- torch.hub.load error HOT 4
- Failed to find function: mono.model.backbones.convnext_large HOT 1
- Fine tune on custom dataset HOT 8
- Sparse GT depth from LiDAR for supervision? HOT 1
- Question regarding losses HOT 1
- Depth scale vs Metric scale HOT 6
- What does the pkl file contain in training with Matterport3D? HOT 1
- generate only a depth matrix without generating a 3D point cloud HOT 2
- Is there any reference code to generate kitti dataset annotation?
- Camera parameters of taskonomy HOT 2
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from metric3d.