LinWeizheDragon / Retrieval-Augmented-Visual-Question-Answering

This is the official repository for Retrieval Augmented Visual Question Answering

LinWeizheDragon/Retrieval-Augmented-Visual-Question-Answering Issues

检索器支持中文吗？
Closed a month ago1
使用BLIP2生成答案
Closed 2 months ago
Where can I find the speed comparison between DPR and FLMR, PREFLMR
Closed 23 days ago27
Question about release of infoseek data split
Closed 2 months ago11
Question about infoseek wikipedia chunking and results split
Closed 2 months ago4
Question: minimum hardware requirements to run experiments
Closed 2 months ago1
Question about using BLIP2 as the answer generator
Closed 2 months ago1
Inquiry Regarding Your Awesome work "Fine-grained Late-interaction Multi-modal Retrieval for Retrieval Augmented Visual Question Answering"
Closed 4 months ago1
关于更新DPR检索的问题
Closed 4 months ago7
关于代码中TRiG中检索器的问题
Closed 4 months ago2
FLMR中Feature-based Vison的一些问题
Closed 4 months ago1
Release code of Fine-grained Late-interaction Multi-modal Retrieval (FLMR)
Closed 4 months ago5
下载相关https://biglmdiag.blob.core.windows.net/vinvl/datasets/coco_caption
Closed 4 months ago1
下载相关
Closed 5 months ago2
RAVQA-v2 code
Closed 5 months ago7
训练RAVQA时，评估阶段输出没有结果
Closed 6 months ago2
训练RAVQA
Closed 6 months ago1
我加载了您分享的RAVQA的最后测试的检查点文件，但是提示错误，请问怎么解决呢？
Closed 6 months ago1
在用RAVQA做测试时，每个passages的输出时下边这样的。这正常吗？
Closed 6 months ago5
训练RAVQA时的输出是下边这样的，正常吗？
Closed 6 months ago
DPR problem
Closed 7 months ago10
wandb connection problem
Closed 6 months ago4
Model download problem
Closed 7 months ago3
ValueError: You have to specify either decoder_input_ids or decoder_inputs_embeds
Closed 8 months ago3
[ERROR] - __main__ : Uncaught exception: <class 'lightning_lite.utilities.exceptions.MisconfigurationException'> --> The provided lr scheduler `LambdaLR` doesn't follow PyTorch's LRScheduler API. You should override the `LightningModule.lr_scheduler_step` hook with your own logic if you are using a custom LR scheduler.
Closed 8 months ago13
AttributeError: 'DPRQuestionEncoderTokenizerFast' object has no attribute 'resize_token_embeddings'
Closed 8 months ago11
could you share the prediction results of the test set?
Closed 9 months ago1
Could someone provide a trained checkpoint file
Closed a year ago5
vinvl_large
Closed a year ago1
some questions about implementing RAG.
Closed a year ago3
The hardware requirements for this model.
Closed a year ago6
About image features
Closed a year ago10
Didn't find dpr_training_annotations
Closed a year ago10
Some bug when processing img_key
Closed a year ago1
performance using GPT-3 pretrain
Closed a year ago1
Missing file okvqa/train_okvqa.yaml and okvqa/test_okvqa.yaml
Closed a year ago5
Missing maskrcnn_benchamrk.data module
Closed a year ago3
Hello, your work is very good. When can you publish the code
Closed a year ago2