Comments (5)
Yes I used the 256^2 images to save time and disk space. I experienced similar loss behavior in training. I would not worry about the loss behavior so much as the behavior of the descriptor layer from the snapshotted weights. If you plot the precision-recall from multiple snapshots you should see them behave differently despite a similar average loss value.
from calc.
Thanks for quick response! But I still can not understand why loss did not go down but the system achieved a better performance.
from calc.
In the end it doesn't really matter if the net learns the HOG descriptor for each warped image, because the HOG here is not very good at place recognition--so a decrease in loss may not be beneficial. The intermediate features are what we want, and since the loss is nonzero, the propagated gradient is nonzero as well. Therefore we have weights being updated every iteration. It turns out that the HOG provides just enough of a geometric prior to update the weights beneficially up to a certain point if there is sufficient training data.
from calc.
Thanks for your reply! Another question, why you used hog, not Gist or other global image descriptor
from calc.
That's a good question! We did cross validate a few types of descriptors, and also tried using just the images and no descriptor, but we did not try Gist. We chose HOG as one possibilty since alot of recent papers have used HOG to achieve some incredible place recognition results (going with accuracy over efficiency). We cite a few in our paper. It is infeasible to try every type of descriptor since there are so many out there. Since this feed is really for issue tracking, I think we should continue over email if you have further questions ([email protected])
from calc.
Related Issues (20)
- make error HOT 1
- implementation about the LA model HOT 3
- make error HOT 3
- landmark
- implementation about the landmark-based place recognition HOT 2
- compile DBoW2 error HOT 2
- Run testNet.py HOT 2
- deeplcd-test error HOT 2
- make error HOT 3
- BGR2YUV and YUV2BGR?
- What is the value of loss? HOT 3
- Using DeepLCD in LSD-SLAM HOT 3
- When I execute cmake .. && make in the build folder of DeepLCD I get the following error HOT 3
- make error HOT 9
- Docker support for managing dependencies HOT 1
- Cannot use GPU in CPU-only Caffe
- No Image received HOT 2
- Why HOG?
- gtest error HOT 2
- New File
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 calc.