Comments (2)
punisher220
commented on June 27, 2024
Excuse me, @zimizile
I have been stuck in LIFT training dataset construction. Have you solved the problem of generating all required data for LIFT training?
Can I discuss it with you? Thank you.
from tf-lift.
punisher220
commented on June 27, 2024
Hello, @zimizile I am sorry to bother you.
I have got the img-kp-minsc-2.0.h5 files for each jpg file with valid_keypoints and other_keypoints data
with my own code for reading the files from VisualSFM.
Then I have got the scales-histogram-2.0.h5 file with the help of the helper.py.
However then I met the problem:
TypeError: No loop matching the specified signature and casting was found for ufunc true_divide
I wonder how did you solve the problem. Could you please give me some hints(to get the split-60-20-20-train-minsc-2.0.h.txt and the split-60-20-20-train-minsc-2.0.h5 files)?
from tf-lift.
Related Issues (20)
- get both keypoints and descriptors in one function call. HOT 5
- tidy up of tf-lift and lift => how to train test, or run pretrained model HOT 1
- Dockerfile HOT 5
- missing scales-histogram-minsc-2.0.h5 HOT 2
- LIFT feature matching HOT 1
- where is requirements.txt HOT 1
- how to change the dir into my own?
- Can the code work in Windows 10 System? Or the tf-lift can only run in Linux/Ubuntu system?
- Is there any Python demo to read the .sift file from VisualSFM? HOT 1
- How to visualize the train loss and accuracy curve while training? HOT 1
- What is the latest development of LIFT? Is it being under improvement? HOT 1
- Is there any related test code for Matching Score? HOT 2
- Activation for DESC is 'relu' rather than 'Tanh' in config.py by default HOT 2
- Where is the implementation of the Siamese Network? HOT 1
- I wonder a question: why LIFT performs so better than SIFT? HOT 1
- Is the Triplet loss better than the Hinge embedding loss in the DESC part? HOT 3
- What is the size of the training patches? 128×128 or 64×64? HOT 5
- ! Problems in running main.py HOT 5
- problem of file notfound HOT 5
- lift training HOT 1
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 tf-lift.