visdial-bert

visdial-bert copied to clipboard

Could you please report the result pretrained on only vqa weight, in your paper, the rusults of pretrained on cc and cc+vqa are reported, but on vqa is missing. And in your provided checkpoints the weight of cc+vqa is missing

1

easonfudan

Hello, I used `download_preprocessed.sh` to download all the pretrained state dicts. Then I used `python evaluate.py -n_gpus 8 -start_path ./checkpoints-release/basemodel_dense -save_name bestmodel_plus_dense` to get the submission text file and submitted...

C0desoda

Bus error (core dumped)

1

I cannot load the data. the code run to Image_features_reader.py lines 43 stop.

Xiao-wen-Sun

Validation-only option

9

Hi, I'm having difficulties evaluating the model on the validation set. I changed the evaluate.py script as follow: - changed the split parameter to 'val' - changed the ranks_json to...

idansc

no running on batch_size=80

3

`python train.py -batch_size 80 -batch_multiply 1 -lr 2e-5 -image_lr 2e-5 -mask_prob 0.1 -sequences_per_image 2 -start_path checkpoints-release/vqa_pretrained_weights` hi, I cannot use batch_size=80 for training. What configuration are you running?

linxi1158