Comments (3)
btw,there is also a long waiting after "start epoch:[],..."
from transgeo2022.
This is not expected. The accuracy computation involves large matrix multiplication and it could be slow if the CPU is slow or the memory is small. You can try making the matrix multiplication smaller or putting it GPU.
The waiting time after the "start epoch" is also related to the matrix multiplication in the sampler. You can remove "--mining" to avoid using hard sample mining.
from transgeo2022.
I made some changes according to your suggestion,it helps a lot.
Besides,are there any pretrained models of VIGOR? I failed to find any 'model_best' file of VIGOR in the link you provided in readme.
from transgeo2022.
Related Issues (20)
- No images in 'trains' or 'val'
- Grad strides do not match bucket view strides HOT 5
- Help about parameter setting HOT 5
- Do I need to download the data set to my computer? HOT 2
- Graduation Project HOT 3
- Have semi-positives been used for training? HOT 15
- About this dataset. CVPR subset-selected
- Dataset Problem HOT 1
- multi-card training HOT 3
- 怎么产生热力图(注意力图),并将其与原图像叠加? HOT 1
- Issue with the Loss function?
- the parameter configuration of the CVACT dataset HOT 2
- Learning rate setting HOT 3
- Test model for Street-view image and Aerial-view image HOT 1
- About accuracy HOT 1
- Poor reproduction results HOT 4
- training on single GPU HOT 1
- Polar coordinate conversio HOT 1
- About CVUSA dataset csv files HOT 1
- differences between VIGOR SAME , CROSS
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 transgeo2022.