Comments (3)
Hi, thanks for your attention.
Yes, 40 classes is enough for focal loss. Since we keep the background and vanishing object classes for experimentation, so here is 42.
Actually this can be changed to 40 completely, sorry for the misleading.
from seqformer.
Thanks for your answer
Does the performance stay the same without these 2 extra classes?
from seqformer.
Yes, this has no impact on performance.
from seqformer.
Related Issues (20)
- How to get the pretained weight --pretrain_weights weights/r50_weight.pth HOT 2
- About GPU RAM requirements HOT 1
- The test score is 0.0 HOT 1
- time for training one epoch ? HOT 1
- Hi, can you please realese the remained pretrained weights of Swin Transformer? HOT 1
- running on custom dataset HOT 1
- how long does it take for pretraining on COCO? HOT 1
- How about the performance when replacing Deformable DETR to the original DETR?
- How to get the coco_keepfor_ytvis19.json? HOT 1
- Default inference paths wrong
- Missing time_attention_weights from T=1 model files HOT 2
- inference error
- where are the dataset annotation from?
- Thank you for your wonderful work!I want to know how to get quantitative results locally without uploading them to the server.
- An error occurs when training SeqFormer on YouTube-VIS 2019 and COCO 2017 jointly HOT 1
- How to get a predicted video or gif?
- format issue of the released r50 model weight HOT 1
- Facing issue while installing Pycocotools HOT 1
- Not able to reproduce the results 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 seqformer.