For the transfer attack implemented in the script LAVIS_tool/_train_adv_img_blip.py, the target image features come from the function where blip_model is loaded through lavis package. However, it seems like there is no implementation of the forward_encoder_image function in the source code of lavis, thus triggering the error: AttributeError: 'Blip2OPT' object has no attribute 'forward_encoder_image'. How to solve this issue?
yukodada
commented
4 weeks ago
For the transfer attack implemented in the script LAVIS_tool/_train_adv_img_blip.py, the target image features come from the function where blip_model is loaded through lavis package. However, it seems like there is no implementation of the forward_encoder_image function in the source code of lavis, thus triggering the error: AttributeError: 'Blip2OPT' object has no attribute 'forward_encoder_image'. How to solve this issue?