salesforce / ALBEF

Code for ALBEF: a new vision-language pre-training method
BSD 3-Clause "New" or "Revised" License
1.45k stars 193 forks source link

Questions about the results of NLVR2 #94

Open junyubi opened 1 year ago

junyubi commented 1 year ago

Downloaded the 4M data pre-trained checkpoints you provided, and then did NLVR2 pre-training and fine-tuning. The results are as follows, which are lower than the results in the paper. May I ask what is the reason? image