Comments (5)
- The loss seems normal. The convergence may be slow in later epochs.
- The best model selected by validation results may not achieve the optimal performance on the test set. The model reported in the paper was selected from the last epoch of the 4th generation. Since there may exist training randomness, it is recommended to test the five checkpoints in the last generation and choose the best-performing one.
- If you use the default settings on one GPU, only one triplet will be adopted for training in each mini-batch. Try to modify
--tuple-size
in the training scripts to adopt more triplets on one GPU for training. In my experiments, I adopted 4 GPUs and one triplet on each GPU, thus a batch of 4 triplets is used. In case the GPU memory is not enough for 4 triplets on only one 2080TI, maybe you need to decrease the learning rate to fit your batch size.
from openibl.
@yxgeee All right, thanks for your suggestion, I will have a try.
from openibl.
@yxgeee Hi, in your paper, you also evaluated SFRS on Oxford 5k, Paris 6k and Holidays datasets, can you share source codes that evaluate SFRS on those datasets, or tell me how do you evaluate SFRS on Oxford 5k, Paris 6k and Holidays datasets?
from openibl.
My colleague helps me test SFRS on retrieval datasets, and maybe I will merge these code in this repo after re-organization. We strictly follow all the same settings (e.g. image size, augmentation, etc.) as SARE and NetVLAD. So you could also refer to their code for evaluation details.
from openibl.
Ok, thank you.
from openibl.
Related Issues (20)
- About negative samples HOT 3
- how the training set is set up HOT 1
- Question on tab.3 of the paper HOT 2
- Evalution protocol
- Performances on Oxford and Paris HOT 6
- models for torch.hub
- .mat files HOT 3
- missing keys in state_dict HOT 1
- pitts 250k top-1 88.2% HOT 1
- About Normalize in get_transformer_train and get_transformer_test HOT 1
- reproduction problem HOT 9
- reproduction problem
- Extract descriptor of single image using models trained on custom datasets
- How to visualize the feature map like Fig.5 in paper?
- Reproducing SARE results
- Test on RParis and ROxford dataset
- about modify d=25 meters HOT 2
- Reproduce results on Tokyo247 dataset HOT 2
- authors dont reply, found a better repo
- Is the pretrained model also MIT? HOT 2
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 openibl.