Hi, When I try to reproduce the results of xvlm with the following scrips
model=xvlm-coco # Choose the model you want to test
for dataset in VG_Relation VG_Attribution
do
python3 main_aro.py --dataset=$dataset --model-name=$model --device=cuda --batch-size 768
done
the evaluation is quite slow, takes around 15 mins for a single dataset, is there anything wrong with my scripts since clip takes only around 2 mins for the same dataset?
Hi, When I try to reproduce the results of xvlm with the following scrips
the evaluation is quite slow, takes around 15 mins for a single dataset, is there anything wrong with my scripts since clip takes only around 2 mins for the same dataset?