Comments (1)
Hi,
It looks like you're confusing the contrastive_align_loss with the contrastive_loss.
In our paper and published results, we do not use the contrastive loss (which is akin to an image-text matching loss from other vision+language pre-training papers). We only left it in the code for completeness since it is something we tried at some point, and thought it would be useful if other users of our code base were interested in experimenting with it. For the two losses that we do use, read the following:
-
Contrastive align loss, which is calculated between the predictions of the decoder and the embedded representations of the text and the output of the cross encoder. Relevant lines in the code:
Line 81 in fdee8c5
Line 203 in fdee8c5
Line 496 in fdee8c5
-
Contrastive alignment -> loss_contrastive_align that we just discussed above. Soft token prediction is loss_labels
Line 464 in fdee8c5
Hope this makes it more clear! :)
from mdetr.
Related Issues (20)
- Can you provide the final_vg json files?
- Issues with training on a single node
- requirements for running the demo notebook HOT 2
- Minor Typo in eval_lvis.py
- Generate tokens_positive for just COCO for pre-training!!
- 2D Object Detection of Drone Images
- Unexpected key(s) in state_dict: "transformer.text_encoder.embeddings.position_ids".
- 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.