yashkant / concat-vqa Goto Github PK

Hello,

For the table 2 in the paper, where CS score is reported, is it CS or CS-BT in the code? CS is computed for revqa, and CS-BT is computed for revqa_bt.

Hi, I want to download the data to run the model.
However, I can't download the files from dropbox. (the website https://www.dropbox.com/sh/v826l3ge7oz4vz4/AACRimDdy_BGnN2XZJDZLyY6a?dl=0)

Hi,

Thank you for sharing the code. I am wondering if you failed to upload "val_target.pkl" to the split folder?

Kind regards,

Hello! Thank you for your great work. I was able to download files from drop box, however, could you add the description of data sets in split directory? Because I am not sure which files correspond to VQA V2, which to VQA-paraphrase and so on. E.g. splits/questions_train_aug.pkl.

Jurijs

Hello,

Thanks for the code and provided extracted features for images. However, I would like to see corresponding images, where should I get them? I see that data contains information about image id, however, I am not sure where are these images.

Thanks,
Jurijs

Dear scholar,
extract_features.py didn't have the params named "imdb_gt_file" , so how to fulfill the object "For grounding truth file to extract features "

python data-release/extract_features.py --model_file data/detectron_model.pth --config_file data/detectron_config.yaml --imdb_gt_file <path_to_imdb_npy_file_generated_above> --output_folder <path_to_output_extracted_features>

Dear scholar,
I found the link vqa-maskrcnn-benchmark didn't have the folder named as "data-release",where I can download it? So I can't run the instructions about the below procedures

cd data-release
wget https://dl.fbaipublicfiles.com/vilbert-multi-task/detectron_model.pth
wget https://dl.fbaipublicfiles.com/vilbert-multi-task/detectron_config.yaml
To extract features for images, run from root directory:

python data-release/extract_features.py --model_file data/detectron_model.pth --config_file data/detectron_config.yaml --image_dir <pa

Dear scholar,
in data-release/extract_features.py, model.to("cuda") will throw errors. and the code is broken. Could you have some suggestion?

def _build_detection_model(self):
cfg.merge_from_file(self.args.config_file)
#cfg.merge_from_list(["MODEL.DEVICE", "cuda"])

    cfg.freeze()

    model = build_detection_model(cfg)
    checkpoint = torch.load(self.args.model_file, map_location=torch.device("cpu"))
    load_state_dict(model, checkpoint.pop("model"))
    
    model.to("cuda")
    
    model.eval()
    
    return model

Hello,

Could you please share the script to generate a list of negatives? Negatives, which we load from .pkl?

Jurijs

Dear scholar,
extract_features.py didn't have the params named "imdb_gt_file" , so how to fulfill the object "For grounding truth file to extract features "

python data-release/extract_features.py --model_file data/detectron_model.pth --config_file data/detectron_config.yaml --imdb_gt_file <path_to_imdb_npy_file_generated_above> --output_folder <path_to_output_extracted_features>