E:\python3.11\python.exe C:\Users\12890\Desktop\deepseek_python_20250730_31eda7.py
Traceback (most recent call last):
File "C:\Users\12890\Desktop\deepseek_python_20250730_31eda7.py", line 52, in <module>
convert_sam_to_onnx()
File "C:\Users\12890\Desktop\deepseek_python_20250730_31eda7.py", line 16, in convert_sam_to_onnx
sam = sam_model_registry[MODEL_TYPE](checkpoint=MODEL_PATH)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "E:\python3.11\Lib\site-packages\segment_anything\build_sam.py", line 38, in build_sam_vit_b
return _build_sam(
^^^^^^^^^^^
File "E:\python3.11\Lib\site-packages\segment_anything\build_sam.py", line 106, in _build_sam
sam.load_state_dict(state_dict)
File "E:\python3.11\Lib\site-packages\torch\nn\modules\module.py", line 2593, in load_state_dict
raise RuntimeError(
RuntimeError: Error(s) in loading state_dict for Sam:
Missing key(s) in state_dict: "image_encoder.pos_embed", "image_encoder.patch_embed.proj.weight", "image_encoder.patch_embed.proj.bias", "image_encoder.blocks.0.norm1.weight", "image_encoder.blocks.0.norm1.bias", "image_encoder.blocks.0.attn.rel_pos_h", "image_encoder.blocks.0.attn.rel_pos_w", "image_encoder.blocks.0.attn.qkv.weight", "image_encoder.blocks.0.attn.qkv.bias", "image_encoder.blocks.0.attn.proj.weight", "image_encoder.blocks.0.attn.proj.bias", "image_encoder.blocks.0.norm2.weight", "image_encoder.blocks.0.norm2.bias", "image_encoder.blocks.0.mlp.lin1.weight", "image_encoder.blocks.0.mlp.lin1.bias", "image_encoder.blocks.0.mlp.lin2.weight", "image_encoder.blocks.0.mlp.lin2.bias", "image_encoder.blocks.1.norm1.weight", "image_encoder.blocks.1.norm1.bias", "image_encoder.blocks.1.attn.rel_pos_h", "image_encoder.blocks.1.attn.rel_pos_w", "image_encoder.blocks.1.attn.qkv.weight", "image_encoder.blocks.1.attn.qkv.bias", "image_encoder.blocks.1.attn.proj.weight", "image_encoder.blocks.1.attn.proj.bias", "image_encoder.blocks.1.norm2.weight", "image_encoder.blocks.1.norm2.bias", "image_encoder.blocks.1.mlp.lin1.weight", "image_encoder.blocks.1.mlp.lin1.bias", "image_encoder.blocks.1.mlp.lin2.weight", "image_encoder.blocks.1.mlp.lin2.bias", "image_encoder.blocks.2.norm1.weight", "image_encoder.blocks.2.norm1.bias", "image_encoder.blocks.2.attn.rel_pos_h", "image_encoder.blocks.2.attn.rel_pos_w", "image_encoder.blocks.2.attn.qkv.weight", "image_encoder.blocks.2.attn.qkv.bias", "image_encoder.blocks.2.attn.proj.weight", "image_encoder.blocks.2.attn.proj.bias", "image_encoder.blocks.2.norm2.weight", "image_encoder.blocks.2.norm2.bias", "image_encoder.blocks.2.mlp.lin1.weight", "image_encoder.blocks.2.mlp.lin1.bias", "image_encoder.blocks.2.mlp.lin2.weight", "image_encoder.blocks.2.mlp.lin2.bias", "image_encoder.blocks.3.norm1.weight", "image_encoder.blocks.3.norm1.bias", "image_encoder.blocks.3.attn.rel_pos_h", "image_encoder.blocks.3.attn.rel_pos_w", "image_encoder.blocks.3.attn.qkv.weight", "image_encoder.blocks.3.attn.qkv.bias", "image_encoder.blocks.3.attn.proj.weight", "image_encoder.blocks.3.attn.proj.bias", "image_encoder.blocks.3.norm2.weight", "image_encoder.blocks.3.norm2.bias", "image_encoder.blocks.3.mlp.lin1.weight", "image_encoder.blocks.3.mlp.lin1.bias", "image_encoder.blocks.3.mlp.lin2.weight", "image_encoder.blocks.3.mlp.lin2.bias", "image_encoder.blocks.4.norm1.weight", "image_encoder.blocks.4.norm1.bias", "image_encoder.blocks.4.attn.rel_pos_h", "image_encoder.blocks.4.attn.rel_pos_w", "image_encoder.blocks.4.attn.qkv.weight", "image_encoder.blocks.4.attn.qkv.bias", "image_encoder.blocks.4.attn.proj.weight", "image_encoder.blocks.4.attn.proj.bias", "image_encoder.blocks.4.norm2.weight", "image_encoder.blocks.4.norm2.bias", "image_encoder.blocks.4.mlp.lin1.weight", "image_encoder.blocks.4.mlp.lin1.bias", "image_encoder.blocks.4.mlp.lin2.weight", "image_encoder.blocks.4.mlp.lin2.bias", "image_encoder.blocks.5.norm1.weight", "image_encoder.blocks.5.norm1.bias", "image_encoder.blocks.5.attn.rel_pos_h", "image_encoder.blocks.5.attn.rel_pos_w", "image_encoder.blocks.5.attn.qkv.weight", "image_encoder.blocks.5.attn.qkv.bias", "image_encoder.blocks.5.attn.proj.weight", "image_encoder.blocks.5.attn.proj.bias", "image_encoder.blocks.5.norm2.weight", "image_encoder.blocks.5.norm2.bias", "image_encoder.blocks.5.mlp.lin1.weight", "image_encoder.blocks.5.mlp.lin1.bias", "image_encoder.blocks.5.mlp.lin2.weight", "image_encoder.blocks.5.mlp.lin2.bias", "image_encoder.blocks.6.norm1.weight", "image_encoder.blocks.6.norm1.bias", "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", "image_encoder.blocks.6.norm2.bias", "image_encoder.blocks.6.mlp.lin1.weight", "image_encoder.blocks.6.mlp.lin1.bias", "image_encoder.blocks.6.mlp.lin2.weight", "image_encoder.blocks.6.mlp.lin2.bias", "image_encoder.blocks.7.norm1.weight", "image_encoder.blocks.7.norm1.bias", "image_encoder.blocks.7.attn.rel_pos_h", "image_encoder.blocks.7.attn.rel_pos_w", "image_encoder.blocks.7.attn.qkv.weight", "image_encoder.blocks.7.attn.qkv.bias", "image_encoder.blocks.7.attn.proj.weight", "image_encoder.blocks.7.attn.proj.bias", "image_encoder.blocks.7.norm2.weight", "image_encoder.blocks.7.norm2.bias", "image_encoder.blocks.7.mlp.lin1.weight", "image_encoder.blocks.7.mlp.lin1.bias", "image_encoder.blocks.7.mlp.lin2.weight", "image_encoder.blocks.7.mlp.lin2.bias", "image_encoder.blocks.8.norm1.weight", "image_encoder.blocks.8.norm1.bias", "image_encoder.blocks.8.attn.rel_pos_h", "image_encoder.blocks.8.attn.rel_pos_w", "image_encoder.blocks.8.attn.qkv.weight", "image_encoder.blocks.8.attn.qkv.bias", "image_encoder.blocks.8.attn.proj.weight", "image_encoder.blocks.8.attn.proj.bias", "image_encoder.blocks.8.norm2.weight", "image_encoder.blocks.8.norm2.bias", "image_encoder.blocks.8.mlp.lin1.weight", "image_encoder.blocks.8.mlp.lin1.bias", "image_encoder.blocks.8.mlp.lin2.weight", "image_encoder.blocks.8.mlp.lin2.bias", "image_encoder.blocks.9.norm1.weight", "image_encoder.blocks.9.norm1.bias", "image_encoder.blocks.9.attn.rel_pos_h", "image_encoder.blocks.9.attn.rel_pos_w", "image_encoder.blocks.9.attn.qkv.weight", "image_encoder.blocks.9.attn.qkv.bias", "image_encoder.blocks.9.attn.proj.weight", "image_encoder.blocks.9.attn.proj.bias", "image_encoder.blocks.9.norm2.weight", "image_encoder.blocks.9.norm2.bias", "image_encoder.blocks.9.mlp.lin1.weight", "image_encoder.blocks.9.mlp.lin1.bias", "image_encoder.blocks.9.mlp.lin2.weight", "image_encoder.blocks.9.mlp.lin2.bias", "image_encoder.blocks.10.norm1.weight", "image_encoder.blocks.10.norm1.bias", "image_encoder.blocks.10.attn.rel_pos_h", "image_encoder.blocks.10.attn.rel_pos_w", "image_encoder.blocks.10.attn.qkv.weight", "image_encoder.blocks.10.attn.qkv.bias", "image_encoder.blocks.10.attn.proj.weight", "image_encoder.blocks.10.attn.proj.bias", "image_encoder.blocks.10.norm2.weight", "image_encoder.blocks.10.norm2.bias", "image_encoder.blocks.10.mlp.lin1.weight", "image_encoder.blocks.10.mlp.lin1.bias", "image_encoder.blocks.10.mlp.lin2.weight", "image_encoder.blocks.10.mlp.lin2.bias", "image_encoder.blocks.11.norm1.weight", "image_encoder.blocks.11.norm1.bias", "image_encoder.blocks.11.attn.rel_pos_h", "image_encoder.blocks.11.attn.rel_pos_w", "image_encoder.blocks.11.attn.qkv.weight", "image_encoder.blocks.11.attn.qkv.bias", "image_encoder.blocks.11.attn.proj.weight", "image_encoder.blocks.11.attn.proj.bias", "image_encoder.blocks.11.norm2.weight", "image_encoder.blocks.11.norm2.bias", "image_encoder.blocks.11.mlp.lin1.weight", "image_encoder.blocks.11.mlp.lin1.bias", "image_encoder.blocks.11.mlp.lin2.weight", "image_encoder.blocks.11.mlp.lin2.bias", "image_encoder.neck.0.weight", "image_encoder.neck.1.weight", "image_encoder.neck.1.bias", "image_encoder.neck.2.weight", "image_encoder.neck.3.weight", "image_encoder.neck.3.bias", "prompt_encoder.pe_layer.positional_encoding_gaussian_matrix", "prompt_encoder.point_embeddings.0.weight", "prompt_encoder.point_embeddings.1.weight", "prompt_encoder.point_embeddings.2.weight", "prompt_encoder.point_embeddings.3.weight", "prompt_encoder.not_a_point_embed.weight", "prompt_encoder.mask_downscaling.0.weight", "prompt_encoder.mask_downscaling.0.bias", "prompt_encoder.mask_downscaling.1.weight", "prompt_encoder.mask_downscaling.1.bias", "prompt_encoder.mask_downscaling.3.weight", "prompt_encoder.mask_downscaling.3.bias", "prompt_encoder.mask_downscaling.4.weight", "prompt_encoder.mask_downscaling.4.bias", "prompt_encoder.mask_downscaling.6.weight", "prompt_encoder.mask_downscaling.6.bias", "prompt_encoder.no_mask_embed.weight", "mask_decoder.transformer.layers.0.self_attn.q_proj.weight", "mask_decoder.transformer.layers.0.self_attn.q_proj.bias", "mask_decoder.transformer.layers.0.self_attn.k_proj.weight", "mask_decoder.transformer.layers.0.self_attn.k_proj.bias", "mask_decoder.transformer.layers.0.self_attn.v_proj.weight", "mask_decoder.transformer.layers.0.self_attn.v_proj.bias", "mask_decoder.transformer.layers.0.self_attn.out_proj.weight", "mask_decoder.transformer.layers.0.self_attn.out_proj.bias", "mask_decoder.transformer.layers.0.norm1.weight", "mask_decoder.transformer.layers.0.norm1.bias", "mask_decoder.transformer.layers.0.cross_attn_token_to_image.q_proj.weight", "mask_decoder.transformer.layers.0.cross_attn_token_to_image.q_proj.bias", "mask_decoder.transformer.layers.0.cross_attn_token_to_image.k_proj.weight", "mask_decoder.transformer.layers.0.cross_attn_token_to_image.k_proj.bias", "mask_decoder.transformer.layers.0.cross_attn_token_to_image.v_proj.weight", "mask_decoder.transformer.layers.0.cross_attn_token_to_image.v_proj.bias", "mask_decoder.transformer.layers.0.cross_attn_token_to_image.out_proj.weight", "mask_decoder.transformer.layers.0.cross_attn_token_to_image.out_proj.bias", "mask_decoder.transformer.layers.0.norm2.weight", "mask_decoder.transformer.layers.0.norm2.bias", "mask_decoder.transformer.layers.0.mlp.lin1.weight", "mask_decoder.transformer.layers.0.mlp.lin1.bias", "mask_decoder.transformer.layers.0.mlp.lin2.weight", "mask_decoder.transformer.layers.0.mlp.lin2.bias", "mask_decoder.transformer.layers.0.norm3.weight", "mask_decoder.transformer.layers.0.norm3.bias", "mask_decoder.transformer.layers.0.norm4.weight", "mask_decoder.transformer.layers.0.norm4.bias", "mask_decoder.transformer.layers.0.cross_attn_image_to_token.q_proj.weight", "mask_decoder.transformer.layers.0.cross_attn_image_to_token.q_proj.bias", "mask_decoder.transformer.layers.0.cross_attn_image_to_token.k_proj.weight", "mask_decoder.transformer.layers.0.cross_attn_image_to_token.k_proj.bias", "mask_decoder.transformer.layers.0.cross_attn_image_to_token.v_proj.weight", "mask_decoder.transformer.layers.0.cross_attn_image_to_token.v_proj.bias", "mask_decoder.transformer.layers.0.cross_attn_image_to_token.out_proj.weight", "mask_decoder.transformer.layers.0.cross_attn_image_to_token.out_proj.bias", "mask_decoder.transformer.layers.1.self_attn.q_proj.weight", "mask_decoder.transformer.layers.1.self_attn.q_proj.bias", "mask_decoder.transformer.layers.1.self_attn.k_proj.weight", "mask_decoder.transformer.layers.1.self_attn.k_proj.bias", "mask_decoder.transformer.layers.1.self_attn.v_proj.weight", "mask_decoder.transformer.layers.1.self_attn.v_proj.bias", "mask_decoder.transformer.layers.1.self_attn.out_proj.weight", "mask_decoder.transformer.layers.1.self_attn.out_proj.bias", "mask_decoder.transformer.layers.1.norm1.weight", "mask_decoder.transformer.layers.1.norm1.bias", "mask_decoder.transformer.layers.1.cross_attn_token_to_image.q_proj.weight", "mask_decoder.transformer.layers.1.cross_attn_token_to_image.q_proj.bias", "mask_decoder.transformer.layers.1.cross_attn_token_to_image.k_proj.weight", "mask_decoder.transformer.layers.1.cross_attn_token_to_image.k_proj.bias", "mask_decoder.transformer.layers.1.cross_attn_token_to_image.v_proj.weight", "mask_decoder.transformer.layers.1.cross_attn_token_to_image.v_proj.bias", "mask_decoder.transformer.layers.1.cross_attn_token_to_image.out_proj.weight", "mask_decoder.transformer.layers.1.cross_attn_token_to_image.out_proj.bias", "mask_decoder.transformer.layers.1.norm2.weight", "mask_decoder.transformer.layers.1.norm2.bias", "mask_decoder.transformer.layers.1.mlp.lin1.weight", "mask_decoder.transformer.layers.1.mlp.lin1.bias", "mask_decoder.transformer.layers.1.mlp.lin2.weight", "mask_decoder.transformer.layers.1.mlp.lin2.bias", "mask_decoder.transformer.layers.1.norm3.weight", "mask_decoder.transformer.layers.1.norm3.bias", "mask_decoder.transformer.layers.1.norm4.weight", "mask_decoder.transformer.layers.1.norm4.bias", "mask_decoder.transformer.layers.1.cross_attn_image_to_token.q_proj.weight", "mask_decoder.transformer.layers.1.cross_attn_image_to_token.q_proj.bias", "mask_decoder.transformer.layers.1.cross_attn_image_to_token.k_proj.weight", "mask_decoder.transformer.layers.1.cross_attn_image_to_token.k_proj.bias", "mask_decoder.transformer.layers.1.cross_attn_image_to_token.v_proj.weight", "mask_decoder.transformer.layers.1.cross_attn_image_to_token.v_proj.bias", "mask_decoder.transformer.layers.1.cross_attn_image_to_token.out_proj.weight", "mask_decoder.transformer.layers.1.cross_attn_image_to_token.out_proj.bias", "mask_decoder.transformer.final_attn_token_to_image.q_proj.weight", "mask_decoder.transformer.final_attn_token_to_image.q_proj.bias", "mask_decoder.transformer.final_attn_token_to_image.k_proj.weight", "mask_decoder.transformer.final_attn_token_to_image.k_proj.bias", "mask_decoder.transformer.final_attn_token_to_image.v_proj.weight", "mask_decoder.transformer.final_attn_token_to_image.v_proj.bias", "mask_decoder.transformer.final_attn_token_to_image.out_proj.weight", "mask_decoder.transformer.final_attn_token_to_image.out_proj.bias", "mask_decoder.transformer.norm_final_attn.weight", "mask_decoder.transformer.norm_final_attn.bias", "mask_decoder.iou_token.weight", "mask_decoder.mask_tokens.weight", "mask_decoder.output_upscaling.0.weight", "mask_decoder.output_upscaling.0.bias", "mask_decoder.output_upscaling.1.weight", "mask_decoder.output_upscaling.1.bias", "mask_decoder.output_upscaling.3.weight", "mask_decoder.output_upscaling.3.bias", "mask_decoder.output_hypernetworks_mlps.0.layers.0.weight", "mask_decoder.output_hypernetworks_mlps.0.layers.0.bias", "mask_decoder.output_hypernetworks_mlps.0.layers.1.weight", "mask_decoder.output_hypernetworks_mlps.0.layers.1.bias", "mask_decoder.output_hypernetworks_mlps.0.layers.2.weight", "mask_decoder.output_hypernetworks_mlps.0.layers.2.bias", "mask_decoder.output_hypernetworks_mlps.1.layers.0.weight", "mask_decoder.output_hypernetworks_mlps.1.layers.0.bias", "mask_decoder.output_hypernetworks_mlps.1.layers.1.weight", "mask_decoder.output_hypernetworks_mlps.1.layers.1.bias", "mask_decoder.output_hypernetworks_mlps.1.layers.2.weight", "mask_decoder.output_hypernetworks_mlps.1.layers.2.bias", "mask_decoder.output_hypernetworks_mlps.2.layers.0.weight", "mask_decoder.output_hypernetworks_mlps.2.layers.0.bias", "mask_decoder.output_hypernetworks_mlps.2.layers.1.weight", "mask_decoder.output_hypernetworks_mlps.2.layers.1.bias", "mask_decoder.output_hypernetworks_mlps.2.layers.2.weight", "mask_decoder.output_hypernetworks_mlps.2.layers.2.bias", "mask_decoder.output_hypernetworks_mlps.3.layers.0.weight", "mask_decoder.output_hypernetworks_mlps.3.layers.0.bias", "mask_decoder.output_hypernetworks_mlps.3.layers.1.weight", "mask_decoder.output_hypernetworks_mlps.3.layers.1.bias", "mask_decoder.output_hypernetworks_mlps.3.layers.2.weight", "mask_decoder.output_hypernetworks_mlps.3.layers.2.bias", "mask_decoder.iou_prediction_head.layers.0.weight", "mask_decoder.iou_prediction_head.layers.0.bias", "mask_decoder.iou_prediction_head.layers.1.weight", "mask_decoder.iou_prediction_head.layers.1.bias", "mask_decoder.iou_prediction_head.layers.2.weight", "mask_decoder.iou_prediction_head.layers.2.bias".
Unexpected key(s) in state_dict: "model".
Process finished with exit code 1
扫一扫
5万+
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
