Comments (1)
Hello,
- It was supposed to be an explanation for "rare" classes. That was a typo. But the reason is what we mentioned, that the class imbalance is much more amplified in the 100%. As you can see the AP frequent is better than DETR while AP rare is worse which supports our understanding that it is the class imbalance that's causing this. Further it might also be that our model is undertrained (we ran around 3 epochs on full) as opposed to the 10% model and plan to look into this in future.
- We did not run segmentation on these datasets, but based on the phrasecut results, we believe the scores would be similar to what we have reported on these datasets within a few points difference. If you are interested in trying it out, the approach would be identical to the instructions we have posted for phrasecut. Note: the train/val/test splits of referring expressions all come from COCO train, and we exclude the val and test images from our pre-training dataset.
from mdetr.
Related Issues (20)
- Can you provide the final_vg json files?
- colab sandbox is deactivated HOT 1
- Pre-training question
- Pre-trained model gives nan prediction in Colab HOT 7
- Seems cannot verify the existence of objects HOT 2
- How to define "Negative Tokens" ? HOT 1
- Bbox assertion error when using ENB models (eval & pretrain as well): assert (boxes1[:, 2:] >= boxes1[:, :2]).all() HOT 8
- how to define positive tokens? HOT 1
- ValueError: char_to_token() is not available when using Python based tokenizers HOT 1
- How to generate "tokens_negative" and "tokens_positive" when we convert our own dataset into mdetr annotations? HOT 1
- finetune have bug!!ValueError: char_to_token() is not available when using Python based tokenizers HOT 3
- Cannot find finetune_phrasecut_miniv.json HOT 1
- [Colab Error] InvalidVersion: Invalid version: '0.10.1,<0.11' HOT 2
- With the increase of MDETR training time, GPU memory occupation keeps increasing. After several epoch training, memory explodes,i.e. OOM, out of memory. HOT 1
- issue #44 "I guess its uncompleted project so I gave up this essay" HOT 1
- I would like to know how to use the model in clevr-ref+.
- Weird results while evaluating & reproducing ENB3 model on PhraseCut
- How to decode GQA evaluation results HOT 1
- run
- CLEVR-REF+ training
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 mdetr.