Comments (7)
Hi, please see the newly added demo_notebook.ipynb.
from cnngeometric_pytorch.
Hi, the link http://www.di.ens.fr/willow/research/cnngeometric/other_resources/test_pairs_pf.csv is not working from your location?
from cnngeometric_pytorch.
thank you very much. U save my days. But what is the meaning of these values.
XA1 | XA2 | XA3 | XA4 | XA5 | XA6 | XA7 | XA8 | XA9 | XA10.......YB10
Meanwhile , i don't understand the train.csv (A22 A21 A12 A11 ty tx ) ,if i only want the Rotation and
translation , how to set the values??
from cnngeometric_pytorch.
Hi the values (A22 A21 A12 A11 ty tx ) correspond to the 2x2 affine transformation matrix, plus the translation vector: [x',y']^T = [A11 A12;A21 A22] [x,y]^T + [tx,ty]^T
The values XAi, YAi, XBi, YBi correspond to the annotated points in the ProposalFlow dataset.
from cnngeometric_pytorch.
if i want use the weights trained on my data to test my picture for getting a result like you shows in the github, what should i do ?
from cnngeometric_pytorch.
Thanks a lot! U are a so kind man!!!
from cnngeometric_pytorch.
thank you very much. U save my days. But what is the meaning of these values.
XA1 | XA2 | XA3 | XA4 | XA5 | XA6 | XA7 | XA8 | XA9 | XA10.......YB10
Meanwhile , i don't understand the train.csv (A22 A21 A12 A11 ty tx ) ,if i only want the Rotation and
translation , how to set the values??
where is (A22 A21 A12 A11 ty tx )?
from cnngeometric_pytorch.
Related Issues (20)
- datasets
- How to get predicted target point from result and source point HOT 9
- How to visualize the feature point pairs' matching results ?
- Training with affine AND TPS HOT 1
- Could not find trained_models! HOT 1
- Different demo result
- PCK mismatch for ResNet
- Confusion about revert points
- TypeError on CNNGeometric HOT 2
- as_matrix problem
- License of this repo
- Train homography model on StreetView dataset
- Evaluation method about TSS dataset
- caculate the pck
- There is problem in the judgment condition of resizing image
- Regarding datasets
- Weights for the feature extractors? HOT 4
- How should to train this model with our own dataset? HOT 1
- Attempting to test pretrained model on my own image data pairs - weird results HOT 2
- Get weird result while using pretrained model
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 cnngeometric_pytorch.