-
I was reading your code and noticed something strange in the VSMForCausalLM class, maybe a small bug, but not sure since I haven't tested your code yet.
Why does images_clip (preprocessed by CLIPProc…
-
is it possible to release part of training data or construction code？
-
Hello!
How do I generate the VQA test result file?
Do I add --evaluate to the finetune command, and replace the checkpoint file with the finetuned weights? Why all the answers in my generated result…
-
您好，datasets.py文件中，args.dataset参数不同会使用不同的预训练数据集，请问vqa_train_filter.json和vqa_train.json有什么不同，当args,dataset==vqav2时，会将vqa_img_feature_train.pickle和vqa_img_feature_val.pickle合并起来做训练，请问您在论文中报告的实验，预训练时具体是用哪…
-
nice work! I did some tests and found some codes in file "models/detector.py" could cause some problem:
```python
global_entity_list = [] # save all the entity type name for each senten…
-
When running `!python ../build_vqa_inputs.py --input_dir='../datasets' --output_dir='../datasets'`
I see
`Traceback (most recent call last):
File "../build_vqa_inputs.py", line 96, in
mai…
-
the url https://drive.google.com/uc?id=1YOy1uPGOt7204jSMrzMCwu3tBJUxUTan is invalid,so I can't download the mfb.pickle or maybe I have no permission
:
File "src/tasks/vqa.py", line 178, in
vqa = VQA()
File "src/tasks/vqa.py", line 48, in __init__
self.model = VQAModel(self.train_tuple.dataset.num_a…
-
Dear author:
Hello,
I am running your publication 'Bilateral Cross Modality Graph Matching Attention'
There were some errors in the source code of the paper 'For Feature Fusion in Visual Question A…
Ysis0 updated
11 months ago
-
Hello, I have read your paper on the _VQA-Med challenge at ImageCLEF 2020_ named _NLM at VQA-Med 2020: Visual Question Answering and Generation in the Medical Domain_ and I am interested in this work.…