An error occurred while loading the blip2_feature_extractor

[shy2000]

Thanks for the great work! I was trying out BLIP2 feature extractor,actually it works. But when i load the model by load_model_and_preprocess(name="blip2_feature_extractor", model_type="pretrain", is_eval=True, device=device) There're lots of missing keys. e.g. Missing keys ['visual_encoder.cls_token', 'visual_encoder.pos_embed', 'visual_encoder.patch_embed.proj.weight', 'visual_encoder.patch_embed.proj.bias', 'visual_encoder.blocks.0.norm1.weight', 'visual_encoder.blocks.0.norm1.bias', 'visual_encoder.blocks.0.attn.q_bias', 'visual_encoder.blocks.0.attn.v_bias' ...

I wonder if the pretrained model from https://storage.googleapis.com/sfr-vision-language-research/LAVIS/models/BLIP2/eva_vit_g.pth is incomplete or something else caused it.