Comments (5)
hi @versatran01 ! thanks for considering to contribute to the library :D
I totally agree with you about the naming convention. We are totally open to refactor it if that makes sense and the use of the package more clear. Could you list what do you have in mind to implement ? We could start from there to break down and define a proper API for the transforms submodule.
Regarding the epsilon value, this is to prevent NaN values during the backprop. It happened to me in the past that by missing this value, the gradients where quite unstable and prone to exploit. So that's a trick that pytorch core developers recommended to me to put in practice.
from kornia.
@versatran01 I put this link as reference: https://github.com/ros/geometry/blob/melodic-devel/tf/src/tf/transformations.py
some of the conversions were initially based on this.
from kornia.
The default epsilon value (1e-6) is too large. Datasets like ScanNet provide camera poses with very high precision (1e-5 ~ 1e-8). The epsilon value should be much smaller than this value.
Also, it would be good if the user can set epsilon by themselves. Currently "DepthWarper" called "relative_transformation" with default eps value (1e-6). The user who is using DepthWarper cannot set the eps value if they want high precision.
from kornia.
eps should not be part of the function signature, see #79 for more discussion.
from kornia.
closed in favor of #79
from kornia.
Related Issues (20)
- Reduce repository size from history HOT 1
- SOLD2 - ability to load the pretrained model from an arbitrary path HOT 1
- SOLD2 output line and junction heatmaps have different shape than eachother and from the original tensor HOT 4
- [milestone] :pill: Code coverage tracker HOT 1
- [milestone] :rock: Onnx support tracker HOT 1
- Add the deprecated decorator in `depth_to_3d` HOT 2
- Update Image Denoising docs page HOT 3
- Error loading image HOT 5
- [Feature Request] Skeletonization HOT 2
- apply_colormap off-by-one error
- Usage of `|` in type annotation causes `torch.jit.script` to not work HOT 4
- Drop `scipy` from dev dependencies
- Drop `cv2` from dev dependencies
- Add an alias `average_enpoint_error = aepe` (or viceversa) HOT 2
- ImportError: cannot import name 'QuaternionCoeffOrder' from 'kornia.geometry.conversions' HOT 1
- Remove old `grad` / `jit` / `nn` markers from tests
- Create test for Auto Modules with `InputTensor` / `OutputTensor`
- expose `average_endpoint_error` on `kornia.metrics.__init__.py`
- Add ONNX tests for `Resize` / `Reshape` operators
- VisualPrompter for SAM with multiple keypoint prompts leads to IndexError HOT 3
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 kornia.