Provided Vilbert model Not working with the data

[jialinw7]

Hi there,
I tried to run some demo using the code from this repo.
I prepared the data following the instructions in the data folder
I.E. download datasets.tar.gz and resnext152 coco features(by wget https://dl.fbaipublicfiles.com/vilbert-multi-task/datasets/coco/features_100/COCO_trainval_resnext152_faster_rcnn_genome.lmdb/data.mdb && mv data.mdb COCO_trainval_resnext152_faster_rcnn_genome.lmdb/)

I tried to evaluate the VQA performance using
CUDA_VISIBLE_DEVICES=1 python eval_tasks.py --bert_model bert-base-uncased --from_pretrained multi_task_model.bin --config_file config/bert_base_6layer_6conect.json --tasks 1 --task_specific_tokens

the multi_task_model.bin is download from
https://dl.fbaipublicfiles.com/vilbert-multi-task/multi_task_model.bin

But I got

I am wondering if someone else facing the same issues or is there something wrong with my code

[jialinw7]

Fixed by reinstalled a new virtual env

[ranery]

@jialinw7 Hi, could you elaborate on how you work it? I encounter the same issue right now.

[snat1505027]

I am also facing the same issue here.

[ranery]

Hint:

A new virtual env seems a misdirection to me.

Dive into the code, you will find that loss and score were initialized as zero but never updated.