noahrecher

I'm experiencing the same issue as @williamtrayn0r. There seems to be a mismatch between the architecture defined in build_sam3D.py and the checkpoint you provided. Could you help us resolve this?

I am using the "vit_b_ori" ViT in buildsam3d and the latest checkpoints downloaded from your repository. Please let me know if you require further information. Thank you!

I changed it but I'm still getting an error: RuntimeError: Error(s) in loading state_dict for Sam3D: Missing key(s) in state_dict: "image_encoder.blocks.6.norm1.weight", "image_encoder.blocks.6.norm1.bias", "image_encoder.blocks.6.attn.rel_pos_d", "image_encoder.blocks.6.attn.rel_pos_h", "image_encoder.blocks.6.attn.rel_pos_w", "image_encoder.blocks.6.attn.qkv.weight", "image_encoder.blocks.6.attn.qkv.bias", "image_encoder.blocks.6.attn.proj.weight", "image_encoder.blocks.6.attn.proj.bias", "image_encoder.blocks.6.norm2.weight",...

This worked, ty!