lucidrains/flamingo-pytorch
Implementation of 🦩 Flamingo, state-of-the-art few-shot visual question answering attention net out of Deepmind, in Pytorch
PythonMIT
Issues
- 0
Data Leakage on cross attention
#14 opened by DanielWarfield1 - 1
[Question] How media locations attribute help in interleaving visual tokens with text?
#9 opened by PrithivirajDamodaran - 9
the pretrained model weights
#4 opened by runzeer - 1
Need a sample ipython notebook
#5 opened by LITDataScience - 2
- 1
Fine-tuning of a model
#7 opened by ans92 - 1
- 1
- 0
How to use Flamingo for VQA task?
#11 opened by karndeepsingh - 2
zeroing out attention not working
#10 opened by dhansmair - 6
Missing flatten op in PerceiverResampler?
#8 opened by zengyan-97 - 4
wrong attention masks?
#6 opened by dhansmair - 7
PerceiverResampler missing some LayerNorms?
#1 opened by inspirit