Comments (1)
Hi,thanks for your issue. In our paper, We find the results from Max-out Strategy
give the best performances, but we also tried top 5~50 max proposals for experiments. We also tried The bootstrap_cross_entropy method
for hard
or soft
as seen in the codes, but two methods have little differences at model testing time.
For reproducing our results as attached here, you can try to adjust pre_nms_topN
to 1 , but the inferior results may come from the other machine problems.
from collaborative-learning-for-weakly-supervised-object-detection.
Related Issues (17)
- Request for your predicted result files. HOT 1
- Hello! I have trained the network, but when testing, only the ap value appears, there is no saved image, how can I get it? HOT 1
- About WSDDN_pre_train model HOT 4
- Why would I get Segmentation fault or pagefaults 0swaps errors?
- Memory leaks during training! HOT 2
- Why are you using faster-rcnn instead of fast rcnn?
- Problem about train.sh
- Problems with training
- mAP resultts
- Initialization for premodel of different nets HOT 9
- RuntimeError: CUDA error: out of memory HOT 1
- question about training on VOC07 HOT 11
- train.sh: line 49: syntax error near unexpected token `>'
- About pytorch version HOT 2
- About GPU and training time HOT 2
- Why remove the background from the category HOT 3
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 collaborative-learning-for-weakly-supervised-object-detection.