Comments (17)
Hi,
The dataset json files for pre-training are provided.
Yes for NLVR2 we perform an addition step of pre-training to learn to reason over two images.
from albef.
Thank you ! But I can not found these files, such as:coco_karpathy_train.json,vg_caption.json,conceptual_caption_train.json, conceptual_caption_val.json,sbu_caption.json. Moreover,you use these files for pretraining NLVR2 task, but these files only have one picture and one caption? How to used for pretraining?
from albef.
You can find the pre-training annotation files here: https://storage.googleapis.com/sfr-pcl-data-research/ALBEF/json_pretrain.zip. It is the same 4M data that we use to pre-train ALBEF.
The NLVR2 model is pretrained on the text-assignment task, you can find the details in our paper.
from albef.
I'm sorry. I didn't get it. ALBEF/configs/NLVR_pretrain.yaml have coco_karpathy_train.json,vg_caption.json,conceptual_caption_train.json;
However, the json_pretraining.zip do not have these files.
In the other word, I want to get the result of Table3-NLVR, what I need to do?
from albef.
As the readme file have two steps:
step 1:
python -m torch.distributed.launch --nproc_per_node=8 --use_env Pretrain_nlvr.py
--config ./configs/NLVR_pretrain.yaml
--output_dir output/NLVR_pretrain
--checkpoint [Pretrained checkpoint]
step2:
python -m torch.distributed.launch --nproc_per_node=8 --use_env NLVR.py
--config ./configs/NLVR.yaml
--output_dir output/NLVR
--checkpoint [TA pretrained checkpoint]
I want to know hwo to get NLVR_pretrain.yaml (coco_karpathy_train.json,vg_caption.json,conceptual_caption_train.json)?
These files difference from pre_json files
from albef.
For step 1, you can use
train_file: ['data/coco.json', 'data/vg.json', 'data/cc3m_train.json', 'data/cc3m_val.json', 'data/sbu.json' ]
Note that you need to modify the image paths in these json files to be your own paths.
from albef.
Then , I run :
python -m torch.distributed.launch --nproc_per_node=8 --use_env NLVR.py
--config ./configs/NLVR.yaml
--output_dir output/NLVR
--checkpoint [TA pretrained checkpoint]
from albef.
Then , I run : python -m torch.distributed.launch --nproc_per_node=8 --use_env NLVR.py --config ./configs/NLVR.yaml --output_dir output/NLVR --checkpoint [TA pretrained checkpoint]
Yes!
from albef.
The [TA pretrained checkpoint] is the pretraining checkpoint or run the following command :
python -m torch.distributed.launch --nproc_per_node=8 --use_env Pretrain_nlvr.py
--config ./configs/NLVR_pretrain.yaml
--output_dir output/NLVR_pretrain
--checkpoint [Pretrained checkpoint]
from albef.
It is the checkpoint after the Pretrain_nlvr step, you can also download it here: https://storage.googleapis.com/sfr-pcl-data-research/ALBEF/pretrain_model_nlvr.pth
from albef.
Thank your answer. I want to know how to get these files (coco_karpathy_train.json,vg_caption.json,conceptual_caption_train.json) in the Pretrain_nlvr step?
Moreover, why COCO, VG, GCC3M and SUB datasets can be used for Pretrain_nlvr?
What did you do with these datasets?
Thank you!
from albef.
coco_karpathy_train.json contains the same annotation as coco.json for pre-training
Please refer to our paper for the description of the TA task.
from albef.
Sorry, I can not understand.
where I can get these files in the Pretrain_nlvr step?
train_file: ['/export/home/project/VL/dataset/caption/coco_karpathy_train.json',
'/export/home/project/VL/dataset/caption/vg_caption.json',
'/export/home/project/VL/dataset/pretrain_caption/conceptual_caption_train.json',
'/export/home/project/VL/dataset/pretrain_caption/conceptual_caption_val.json',
'/export/home/project/VL/dataset/pretrain_caption/sbu_caption.json'
]
from albef.
NLVR2 requires an additional pre-training step with text-assignment (TA) to adapt the model for image-pair inputs. In order to perform TA, first set the paths for the json training files in configs/NLVR_pretrain.yaml, then run:
python -m torch.distributed.launch --nproc_per_node=8 --use_env Pretrain_nlvr.py
--config ./configs/NLVR_pretrain.yaml
--output_dir output/NLVR_pretrain
--checkpoint [Pretrained checkpoint]
But, the NLVR_pretrain.yaml file constains pre_training json_file can not found.
from albef.
Sorry, I can not understand. where I can get these files in the Pretrain_nlvr step? train_file: ['/export/home/project/VL/dataset/caption/coco_karpathy_train.json', '/export/home/project/VL/dataset/caption/vg_caption.json', '/export/home/project/VL/dataset/pretrain_caption/conceptual_caption_train.json', '/export/home/project/VL/dataset/pretrain_caption/conceptual_caption_val.json', '/export/home/project/VL/dataset/pretrain_caption/sbu_caption.json' ]
Those files are the SAME as ['data/coco.json', 'data/vg.json', 'data/cc3m_train.json', 'data/cc3m_val.json', 'data/sbu.json' ]
from albef.
OK, Thanks.
from albef.
Sorry, I can not understand. where I can get these files in the Pretrain_nlvr step? train_file: ['/export/home/project/VL/dataset/caption/coco_karpathy_train.json', '/export/home/project/VL/dataset/caption/vg_caption.json', '/export/home/project/VL/dataset/pretrain_caption/conceptual_caption_train.json', '/export/home/project/VL/dataset/pretrain_caption/conceptual_caption_val.json', '/export/home/project/VL/dataset/pretrain_caption/sbu_caption.json' ]
Those files are the SAME as ['data/coco.json', 'data/vg.json', 'data/cc3m_train.json', 'data/cc3m_val.json', 'data/sbu.json' ]
If those files are the same [data/xx.json]. why to run NLVR_pretrain step?
why not to directly use the pre_training checkpoint ?
I not understand NLVR_pretrain step if theNLVR_pretrain ste json files same the pretraining step.
Because, the NLVR task have two pictures and one text, why the json file same pre_training step?
from albef.
Related Issues (20)
- Question about answer ranking HOT 2
- Zero-shot capabilities on ImageNet HOT 2
- state_dict = checkpoint['model'] KeyError: 'model' When I using flickr30k.pth HOT 2
- Grounding det.json file for other grounding datasets
- pretrain task
- utils.init_distributed_mode(args) Fail HOT 1
- About dropout and no_grad.
- refcoco on lower resolution
- ITM loss HOT 1
- RefCOCO+ Fine-tuning
- TypeError: '<=' not supported between instances of 'float' and 'str' ? HOT 1
- How can I get Visual Genome ? HOT 2
- ITC & ITM & MLM weight distribution
- RuntimeError: invalid multinomial distribution (sum of probabilities <= 0)
- '/export/share HOT 2
- The code for loss computation of itc is not corresponding to the original paper HOT 2
- Overflow in `autocontrast_func`
- Reproducing the VQA candidate answers from the dataset and paper
- About the Flickr-30k dataset HOT 1
- Multilingual Support
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 albef.