ConceptBERT

ConceptBERT copied to clipboard

# Patching CVE-2007-4559 Hi, we are security researchers from the Advanced Research Center at [Trellix](https://www.trellix.com). We have began a campaign to patch a widespread bug named CVE-2007-4559. CVE-2007-4559 is a...

TrellixVulnTeam

In conceptBERT - vilbert - knowledgeGraph - conceptnet_graph.py from conceptBert.vilbert import get_txt_questions But there isn't such a py file get_txt_questions

Macro-1998

Pre-trained model for fine-tuning on OK-VQA

2

Hello, I'm trying to reproduce this work. Now I'm in the step of fine-tuning on OK-VQA. How can I get the pre-trained model (pytorch_model_11.bin) required for fine-tuning? /nas-data/vilbert/data2/save_final/VQA_bert_base_6layer_6conect-beta_vilbert_vqa/pytorch_model_11.bin Thank you.

monste12

For training on 1024 batch size, it is still showing cuda out of memory error on 5 gpus. Is distributed training is available for this implementation?

chirag1903

Is it need huge computation for all of knowledge concepts embedding?And the predict answer from KG?

1

Hello Sir, Do you retrievals KG to reduce the number of facts? And the output is scores of candidates from KG?

heyichang

Pretrained model folder?

6

Hi, I'm trying to load the pretrained model from base to train on VQA dataset, but I'm unable to find the indicated model data files. It states " The data...

adrielkuek

lmdb.Error: /nas-data/vilbert/data2/coco/vilbert-job-0.1.dev10-g7158c0c.d20200127182633/coco_trainval_resnet101_faster_rcnn_genome.lmdb/: No such file or directory

2

请问这个文件在哪里获得呢？ python-BaseException File "/home/zzu_zxw/.pycharm_helpers/pydev/pydevd.py", line 1496, in _exec pydev_imports.execfile(file, globals, locals) # execute the script File "/home/zzu_zxw/.pycharm_helpers/pydev/_pydev_imps/_pydev_execfile.py", line 18, in execfile exec(compile(contents+"\n", file, 'exec'), glob, loc) File "/home/zzu_zxw/zjl_data/ConceptBERT/conceptBert/train_tasks.py", line 581,...

1286169349

pytorch size mismatch issue

1

We use the following command for fine-tuning the OKVQA model: ``` python3 -u train_tasks.py --model_version 3 --bert_model=bert-base-uncased \ --from_pretrained=/workspace/ConceptBERT-master/conceptBert/vilbert/data2/kilbert_base_model/pytorch_model_11.bin \ --from_pretrained_conceptBert=/workspace/ConceptBERT-master/conceptBert/outputs/train1_vqa_trained_model/VQA_bert_base_6layer_6conect/pytorch_model_18.bin \ --output_dir=/workspace/ConceptBERT-master/conceptBert/outputs/train2_okvqa_trained_model/ \ --summary_writer =/workspace/ConceptBERT-master/conceptBert/outputs/tensorboards/ \ --num_workers 0 \...

Andrew82106