airsplay/vokenization
PyTorch code for EMNLP 2020 Paper "Vokenization: Improving Language Understanding with Visual Supervision"
PythonMIT
Issues
- 5
About the finetune accuracy
#9 opened by yxgnahz - 0
processed_tokens variable is incorrectly calculated in function 'vokenization.vokenize_corpus_mp::reducer'
#13 opened by CoderChen01 - 0
- 1
about voken regression and voken constrastive
#11 opened by lizhiustc - 0
How to fine-tune on SQUAD?
#10 opened by peihaowang - 1
AttributeError in extract_vision_keys.py
#8 opened by VickiCui - 1
Error in extract_vision_keys
#7 opened by Richar-Du - 0
Revokenization
#6 opened by vilhil - 2
Do vokens need when fine-tuning?
#5 opened by VickiCui - 2
- 3
RuntimeError: stack expects each tensor to be equal size, but got [14] at entry 0 and [12] at entry 1
#2 opened by zhanhl316 - 4