search

fawazsammani / nlxgpt

NLX-GPT: A Model for Natural Language Explanations in Vision and Vision-Language Tasks, CVPR 2022 (Oral)
44 stars 10 forks source link

For help #4

Closed maxLWS closed 2 years ago

maxLWS commented 2 years ago

Hello, we are also doing relevant research. Could you please provide the pre-training weights for caption in your paper? image

fawazsammani commented 2 years ago

Hi @maxLWS. I updated the README file with the pretrained models on Image Captioning: Please see here.

Note: You will find two folders: model1 and model2. We actually pretrained 4 different times with different random seeds. I forgot which one was used for the finetuning on the downstream tasks, but all of them should achieve similar results. I chose randomly two of these four pretrained models I have, and uploaded them here.

If there is any problem, feel free to open the issue again