Comments (5)
Line 120 of the util.py file should also be modified.
Thanks for your issue. I've modified the details in windows OS in readme.md .
from deepimagestitching-1.0.
Thanks for your reply! It working successfully.
from deepimagestitching-1.0.
Hi, I found that the production of the test set is like distorting one picture, and getting two pictures with different perspectives. If I want to input pictures A and B (different viewing angles, solve the homography matrix), get the registered picture,is that ok?
from deepimagestitching-1.0.
Hi, I found that the production of the test set is like distorting one picture, and getting two pictures with different perspectives. If I want to input pictures A and B (different viewing angles, solve the homography matrix), get the registered picture,is that ok?
The proposed dataset is a synthetic dataset that neglects the parallax. Specifically, all the objects in the synthetic dataset are assumed at the same depth. Therefore, it can not be well generalized in real scenes with parallax. If your input images are shot from the same virtual center (pure rotation shooting), it can still work. If not, the performance will be degraded to some extent.
from deepimagestitching-1.0.
Hello, thanks for your code! I modified the utils function according to your requirements under Windows OS, but it shows "list index out of range"? For Dataset_gen/ dataset.py is OK.
python train_H.py --train_folder ../../dataset/training
--test_folder ../../dataset/testing
--summary_dir ../summary/homography
--snapshot_dir ../checkpoints/homography
--gpu 0
--batch 4
--iters 600000
There are the following problems. As a beginner, I don't know what to do
from deepimagestitching-1.0.
Related Issues (10)
- test example error HOT 2
- something wrong happened when running dataset.py HOT 1
- Maxpool in UNet should keep the size? HOT 5
- Pretrained model for deep homography network HOT 2
- Can't open pretrained model HOT 1
- ValueError: The channel dimension of the inputs should be defined. Found 'None'.
- 运行出错 HOT 1
- tensorDLT
- Paper PDF
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 deepimagestitching-1.0.