search

YicongHong / Recurrent-VLN-BERT

Code of the CVPR 2021 Oral paper: A Recurrent Vision-and-Language BERT for Navigation
Other
150 stars 29 forks source link

Details about the no init. OSCAR model #13

Closed Jackie-Chou closed 2 years ago

Jackie-Chou commented 2 years ago

Hi Yicong, I wonder how do you initialize the no init. OSCAR model to get the results reported in the paper. Did you initialize all the parameters randomly or use some pretrained weights, e.g., initialize the language part with Bert pretrained weights?

YicongHong commented 2 years ago

Hi Jackie, the OSCAR (no init.) was initialized with all random parameters :)

Jackie-Chou commented 2 years ago

Thanks for your timely reply!