the pretrained model state_dict did not match

[hubutui]

I download the pretrained model, and run

python test.py --dataset Synapse --cfg configs/swin_tiny_patch4_window7_224_lite.yaml --is_saveni --volume_path your DATA_DIR --output_dir your OUT_DIR --max_epoch 150 --base_lr 0.05 --img_size 224 --batch_size 24

and there are mismatch keys:

    msg = net.load_state_dict(torch.load(snapshot)["model"])
  File "/usr/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1482, in load_state_dict
    raise RuntimeError('Error(s) in loading state_dict for {}:\n\t{}'.format(
RuntimeError: Error(s) in loading state_dict for SwinUnet:
    Missing key(s) in state_dict: "swin_unet.patch_embed.proj.weight", "swin_unet.patch_embed.proj.bias", "swin_unet.patch_embed.norm.weight", "swin_unet.patch_embed.norm.bias", "swin_unet.layers.0.blocks.0.norm1.weight", "swin_unet.layers.0.blocks.0.norm1.bias", "swin_unet.layers.0.blocks.0.attn.relative_position_bias_table", "swin_unet.layers.0.blocks.0.attn.relative_position_index", "swin_unet.layers.0.blocks.0.attn.qkv.weight", "swin_unet.layers.0.blocks.0.attn.qkv.bias", "swin_unet.layers.0.blocks.0.attn.proj.weight", "swin_unet.layers.0.blocks.0.attn.proj.bias", "swin_unet.layers.0.blocks.0.norm2.weight", "swin_unet.layers.0.blocks.0.norm2.bias", "swin_unet.layers.0.blocks.0.mlp.fc1.weight", "swin_unet.layers.0.blocks.0.mlp.fc1.bias", "swin_unet.layers.0.blocks.0.mlp.fc2.weight", "swin_unet.layers.0.blocks.0.mlp.fc2.bias", "swin_unet.layers.0.blocks.1.attn_mask", "swin_unet.layers.0.blocks.1.norm1.weight", "swin_unet.layers.0.blocks.1.norm1.bias", "swin_unet.layers.0.blocks.1.attn.relative_position_bias_table", "swin_unet.layers.0.blocks.1.attn.relative_position_index", "swin_unet.layers.0.blocks.1.attn.qkv.weight", "swin_unet.layers.0.blocks.1.attn.qkv.bias", "swin_unet.layers.0.blocks.1.attn.proj.weight", "swin_unet.layers.0.blocks.1.attn.proj.bias", "swin_unet.layers.0.blocks.1.norm2.weight", "swin_unet.layers.0.blocks.1.norm2.bias", "swin_unet.layers.0.blocks.1.mlp.fc1.weight", "swin_unet.layers.0.blocks.1.mlp.fc1.bias", "swin_unet.layers.0.blocks.1.mlp.fc2.weight", "swin_unet.layers.0.blocks.1.mlp.fc2.bias", "swin_unet.layers.0.downsample.reduction.weight", "swin_unet.layers.0.downsample.norm.weight", "swin_unet.layers.0.downsample.norm.bias", "swin_unet.layers.1.blocks.0.norm1.weight", "swin_unet.layers.1.blocks.0.norm1.bias", "swin_unet.layers.1.blocks.0.attn.relative_position_bias_table", "swin_unet.layers.1.blocks.0.attn.relative_position_index", "swin_unet.layers.1.blocks.0.attn.qkv.weight", "swin_unet.layers.1.blocks.0.attn.qkv.bias", "swin_unet.layers.1.blocks.0.attn.proj.weight", "swin_unet.layers.1.blocks.0.attn.proj.bias", "swin_unet.layers.1.blocks.0.norm2.weight", "swin_unet.layers.1.blocks.0.norm2.bias", "swin_unet.layers.1.blocks.0.mlp.fc1.weight", "swin_unet.layers.1.blocks.0.mlp.fc1.bias", "swin_unet.layers.1.blocks.0.mlp.fc2.weight", "swin_unet.layers.1.blocks.0.mlp.fc2.bias", "swin_unet.layers.1.blocks.1.attn_mask", "swin_unet.layers.1.blocks.1.norm1.weight", "swin_unet.layers.1.blocks.1.norm1.bias", "swin_unet.layers.1.blocks.1.attn.relative_position_bias_table", "swin_unet.layers.1.blocks.1.attn.relative_position_index", "swin_unet.layers.1.blocks.1.attn.qkv.weight", "swin_unet.layers.1.blocks.1.attn.qkv.bias", "swin_unet.layers.1.blocks.1.attn.proj.weight", "swin_unet.layers.1.blocks.1.attn.proj.bias", "swin_unet.layers.1.blocks.1.norm2.weight", "swin_unet.layers.1.blocks.1.norm2.bias", "swin_unet.layers.1.blocks.1.mlp.fc1.weight", "swin_unet.layers.1.blocks.1.mlp.fc1.bias", "swin_unet.layers.1.blocks.1.mlp.fc2.weight", "swin_unet.layers.1.blocks.1.mlp.fc2.bias", "swin_unet.layers.1.downsample.reduction.weight", "swin_unet.layers.1.downsample.norm.weight", "swin_unet.layers.1.downsample.norm.bias", "swin_unet.layers.2.blocks.0.norm1.weight", "swin_unet.layers.2.blocks.0.norm1.bias", "swin_unet.layers.2.blocks.0.attn.relative_position_bias_table", "swin_unet.layers.2.blocks.0.attn.relative_position_index", "swin_unet.layers.2.blocks.0.attn.qkv.weight", "swin_unet.layers.2.blocks.0.attn.qkv.bias", "swin_unet.layers.2.blocks.0.attn.proj.weight", "swin_unet.layers.2.blocks.0.attn.proj.bias", "swin_unet.layers.2.blocks.0.norm2.weight", "swin_unet.layers.2.blocks.0.norm2.bias", "swin_unet.layers.2.blocks.0.mlp.fc1.weight", "swin_unet.layers.2.blocks.0.mlp.fc1.bias", "swin_unet.layers.2.blocks.0.mlp.fc2.weight", "swin_unet.layers.2.blocks.0.mlp.fc2.bias", "swin_unet.layers.2.blocks.1.attn_mask", "swin_unet.layers.2.blocks.1.norm1.weight", "swin_unet.layers.2.blocks.1.norm1.bias", "swin_unet.layers.2.blocks.1.attn.relative_position_bias_table", "swin_unet.layers.2.blocks.1.attn.relative_position_index", "swin_unet.layers.2.blocks.1.attn.qkv.weight", "swin_unet.layers.2.blocks.1.attn.qkv.bias", "swin_unet.layers.2.blocks.1.attn.proj.weight", "swin_unet.layers.2.blocks.1.attn.proj.bias", "swin_unet.layers.2.blocks.1.norm2.weight", "swin_unet.layers.2.blocks.1.norm2.bias", "swin_unet.layers.2.blocks.1.mlp.fc1.weight", "swin_unet.layers.2.blocks.1.mlp.fc1.bias", "swin_unet.layers.2.blocks.1.mlp.fc2.weight", "swin_unet.layers.2.blocks.1.mlp.fc2.bias", "swin_unet.layers.2.downsample.reduction.weight", "swin_unet.layers.2.downsample.norm.weight", "swin_unet.layers.2.downsample.norm.bias", "swin_unet.layers.3.blocks.0.norm1.weight", "swin_unet.layers.3.blocks.0.norm1.bias", "swin_unet.layers.3.blocks.0.attn.relative_position_bias_table", "swin_unet.layers.3.blocks.0.attn.relative_position_index", "swin_unet.layers.3.blocks.0.attn.qkv.weight", "swin_unet.layers.3.blocks.0.attn.qkv.bias", "swin_unet.layers.3.blocks.0.attn.proj.weight", "swin_unet.layers.3.blocks.0.attn.proj.bias", "swin_unet.layers.3.blocks.0.norm2.weight", "swin_unet.layers.3.blocks.0.norm2.bias", "swin_unet.layers.3.blocks.0.mlp.fc1.weight", "swin_unet.layers.3.blocks.0.mlp.fc1.bias", "swin_unet.layers.3.blocks.0.mlp.fc2.weight", "swin_unet.layers.3.blocks.0.mlp.fc2.bias", "swin_unet.layers.3.blocks.1.norm1.weight", "swin_unet.layers.3.blocks.1.norm1.bias", "swin_unet.layers.3.blocks.1.attn.relative_position_bias_table", "swin_unet.layers.3.blocks.1.attn.relative_position_index", "swin_unet.layers.3.blocks.1.attn.qkv.weight", "swin_unet.layers.3.blocks.1.attn.qkv.bias", "swin_unet.layers.3.blocks.1.attn.proj.weight", "swin_unet.layers.3.blocks.1.attn.proj.bias", "swin_unet.layers.3.blocks.1.norm2.weight", "swin_unet.layers.3.blocks.1.norm2.bias", "swin_unet.layers.3.blocks.1.mlp.fc1.weight", "swin_unet.layers.3.blocks.1.mlp.fc1.bias", "swin_unet.layers.3.blocks.1.mlp.fc2.weight", "swin_unet.layers.3.blocks.1.mlp.fc2.bias", "swin_unet.layers_up.0.expand.weight", "swin_unet.layers_up.0.norm.weight", "swin_unet.layers_up.0.norm.bias", "swin_unet.layers_up.1.blocks.0.norm1.weight", "swin_unet.layers_up.1.blocks.0.norm1.bias", "swin_unet.layers_up.1.blocks.0.attn.relative_position_bias_table", "swin_unet.layers_up.1.blocks.0.attn.relative_position_index", "swin_unet.layers_up.1.blocks.0.attn.qkv.weight", "swin_unet.layers_up.1.blocks.0.attn.qkv.bias", "swin_unet.layers_up.1.blocks.0.attn.proj.weight", "swin_unet.layers_up.1.blocks.0.attn.proj.bias", "swin_unet.layers_up.1.blocks.0.norm2.weight", "swin_unet.layers_up.1.blocks.0.norm2.bias", "swin_unet.layers_up.1.blocks.0.mlp.fc1.weight", "swin_unet.layers_up.1.blocks.0.mlp.fc1.bias", "swin_unet.layers_up.1.blocks.0.mlp.fc2.weight", "swin_unet.layers_up.1.blocks.0.mlp.fc2.bias", "swin_unet.layers_up.1.blocks.1.attn_mask", "swin_unet.layers_up.1.blocks.1.norm1.weight", "swin_unet.layers_up.1.blocks.1.norm1.bias", "swin_unet.layers_up.1.blocks.1.attn.relative_position_bias_table", "swin_unet.layers_up.1.blocks.1.attn.relative_position_index", "swin_unet.layers_up.1.blocks.1.attn.qkv.weight", "swin_unet.layers_up.1.blocks.1.attn.qkv.bias", "swin_unet.layers_up.1.blocks.1.attn.proj.weight", "swin_unet.layers_up.1.blocks.1.attn.proj.bias", "swin_unet.layers_up.1.blocks.1.norm2.weight", "swin_unet.layers_up.1.blocks.1.norm2.bias", "swin_unet.layers_up.1.blocks.1.mlp.fc1.weight", "swin_unet.layers_up.1.blocks.1.mlp.fc1.bias", "swin_unet.layers_up.1.blocks.1.mlp.fc2.weight", "swin_unet.layers_up.1.blocks.1.mlp.fc2.bias", "swin_unet.layers_up.1.upsample.expand.weight", "swin_unet.layers_up.1.upsample.norm.weight", "swin_unet.layers_up.1.upsample.norm.bias", "swin_unet.layers_up.2.blocks.0.norm1.weight", "swin_unet.layers_up.2.blocks.0.norm1.bias", "swin_unet.layers_up.2.blocks.0.attn.relative_position_bias_table", "swin_unet.layers_up.2.blocks.0.attn.relative_position_index", "swin_unet.layers_up.2.blocks.0.attn.qkv.weight", "swin_unet.layers_up.2.blocks.0.attn.qkv.bias", "swin_unet.layers_up.2.blocks.0.attn.proj.weight", "swin_unet.layers_up.2.blocks.0.attn.proj.bias", "swin_unet.layers_up.2.blocks.0.norm2.weight", "swin_unet.layers_up.2.blocks.0.norm2.bias", "swin_unet.layers_up.2.blocks.0.mlp.fc1.weight", "swin_unet.layers_up.2.blocks.0.mlp.fc1.bias", "swin_unet.layers_up.2.blocks.0.mlp.fc2.weight", "swin_unet.layers_up.2.blocks.0.mlp.fc2.bias", "swin_unet.layers_up.2.blocks.1.attn_mask", "swin_unet.layers_up.2.blocks.1.norm1.weight", "swin_unet.layers_up.2.blocks.1.norm1.bias", "swin_unet.layers_up.2.blocks.1.attn.relative_position_bias_table", "swin_unet.layers_up.2.blocks.1.attn.relative_position_index", "swin_unet.layers_up.2.blocks.1.attn.qkv.weight", "swin_unet.layers_up.2.blocks.1.attn.qkv.bias", "swin_unet.layers_up.2.blocks.1.attn.proj.weight", "swin_unet.layers_up.2.blocks.1.attn.proj.bias", "swin_unet.layers_up.2.blocks.1.norm2.weight", "swin_unet.layers_up.2.blocks.1.norm2.bias", "swin_unet.layers_up.2.blocks.1.mlp.fc1.weight", "swin_unet.layers_up.2.blocks.1.mlp.fc1.bias", "swin_unet.layers_up.2.blocks.1.mlp.fc2.weight", "swin_unet.layers_up.2.blocks.1.mlp.fc2.bias", "swin_unet.layers_up.2.upsample.expand.weight", "swin_unet.layers_up.2.upsample.norm.weight", "swin_unet.layers_up.2.upsample.norm.bias", "swin_unet.layers_up.3.blocks.0.norm1.weight", "swin_unet.layers_up.3.blocks.0.norm1.bias", "swin_unet.layers_up.3.blocks.0.attn.relative_position_bias_table", "swin_unet.layers_up.3.blocks.0.attn.relative_position_index", "swin_unet.layers_up.3.blocks.0.attn.qkv.weight", "swin_unet.layers_up.3.blocks.0.attn.qkv.bias", "swin_unet.layers_up.3.blocks.0.attn.proj.weight", "swin_unet.layers_up.3.blocks.0.attn.proj.bias", "swin_unet.layers_up.3.blocks.0.norm2.weight", "swin_unet.layers_up.3.blocks.0.norm2.bias", "swin_unet.layers_up.3.blocks.0.mlp.fc1.weight", "swin_unet.layers_up.3.blocks.0.mlp.fc1.bias", "swin_unet.layers_up.3.blocks.0.mlp.fc2.weight", "swin_unet.layers_up.3.blocks.0.mlp.fc2.bias", "swin_unet.layers_up.3.blocks.1.attn_mask", "swin_unet.layers_up.3.blocks.1.norm1.weight", "swin_unet.layers_up.3.blocks.1.norm1.bias", "swin_unet.layers_up.3.blocks.1.attn.relative_position_bias_table", "swin_unet.layers_up.3.blocks.1.attn.relative_position_index", "swin_unet.layers_up.3.blocks.1.attn.qkv.weight", "swin_unet.layers_up.3.blocks.1.attn.qkv.bias", "swin_unet.layers_up.3.blocks.1.attn.proj.weight", "swin_unet.layers_up.3.blocks.1.attn.proj.bias", "swin_unet.layers_up.3.blocks.1.norm2.weight", "swin_unet.layers_up.3.blocks.1.norm2.bias", "swin_unet.layers_up.3.blocks.1.mlp.fc1.weight", "swin_unet.layers_up.3.blocks.1.mlp.fc1.bias", "swin_unet.layers_up.3.blocks.1.mlp.fc2.weight", "swin_unet.layers_up.3.blocks.1.mlp.fc2.bias", "swin_unet.concat_back_dim.1.weight", "swin_unet.concat_back_dim.1.bias", "swin_unet.concat_back_dim.2.weight", "swin_unet.concat_back_dim.2.bias", "swin_unet.concat_back_dim.3.weight", "swin_unet.concat_back_dim.3.bias", "swin_unet.norm.weight", "swin_unet.norm.bias", "swin_unet.norm_up.weight", "swin_unet.norm_up.bias", "swin_unet.up.expand.weight", "swin_unet.up.norm.weight", "swin_unet.up.norm.bias", "swin_unet.output.weight". 
    Unexpected key(s) in state_dict: "patch_embed.proj.weight", "patch_embed.proj.bias", "patch_embed.norm.weight", "patch_embed.norm.bias", "layers.0.blocks.0.norm1.weight", "layers.0.blocks.0.norm1.bias", "layers.0.blocks.0.attn.qkv.weight", "layers.0.blocks.0.attn.qkv.bias", "layers.0.blocks.0.attn.proj.weight", "layers.0.blocks.0.attn.proj.bias", "layers.0.blocks.0.norm2.weight", "layers.0.blocks.0.norm2.bias", "layers.0.blocks.0.mlp.fc1.weight", "layers.0.blocks.0.mlp.fc1.bias", "layers.0.blocks.0.mlp.fc2.weight", "layers.0.blocks.0.mlp.fc2.bias", "layers.0.blocks.1.norm1.weight", "layers.0.blocks.1.norm1.bias", "layers.0.blocks.1.attn.qkv.weight", "layers.0.blocks.1.attn.qkv.bias", "layers.0.blocks.1.attn.proj.weight", "layers.0.blocks.1.attn.proj.bias", "layers.0.blocks.1.norm2.weight", "layers.0.blocks.1.norm2.bias", "layers.0.blocks.1.mlp.fc1.weight", "layers.0.blocks.1.mlp.fc1.bias", "layers.0.blocks.1.mlp.fc2.weight", "layers.0.blocks.1.mlp.fc2.bias", "layers.0.downsample.norm.weight", "layers.0.downsample.norm.bias", "layers.1.blocks.0.norm1.weight", "layers.1.blocks.0.norm1.bias", "layers.1.blocks.0.attn.qkv.weight", "layers.1.blocks.0.attn.qkv.bias", "layers.1.blocks.0.attn.proj.weight", "layers.1.blocks.0.attn.proj.bias", "layers.1.blocks.0.norm2.weight", "layers.1.blocks.0.norm2.bias", "layers.1.blocks.0.mlp.fc1.weight", "layers.1.blocks.0.mlp.fc1.bias", "layers.1.blocks.0.mlp.fc2.weight", "layers.1.blocks.0.mlp.fc2.bias", "layers.1.blocks.1.norm1.weight", "layers.1.blocks.1.norm1.bias", "layers.1.blocks.1.attn.qkv.weight", "layers.1.blocks.1.attn.qkv.bias", "layers.1.blocks.1.attn.proj.weight", "layers.1.blocks.1.attn.proj.bias", "layers.1.blocks.1.norm2.weight", "layers.1.blocks.1.norm2.bias", "layers.1.blocks.1.mlp.fc1.weight", "layers.1.blocks.1.mlp.fc1.bias", "layers.1.blocks.1.mlp.fc2.weight", "layers.1.blocks.1.mlp.fc2.bias", "layers.1.downsample.norm.weight", "layers.1.downsample.norm.bias", "layers.2.blocks.0.norm1.weight", "layers.2.blocks.0.norm1.bias", "layers.2.blocks.0.attn.qkv.weight", "layers.2.blocks.0.attn.qkv.bias", "layers.2.blocks.0.attn.proj.weight", "layers.2.blocks.0.attn.proj.bias", "layers.2.blocks.0.norm2.weight", "layers.2.blocks.0.norm2.bias", "layers.2.blocks.0.mlp.fc1.weight", "layers.2.blocks.0.mlp.fc1.bias", "layers.2.blocks.0.mlp.fc2.weight", "layers.2.blocks.0.mlp.fc2.bias", "layers.2.blocks.1.norm1.weight", "layers.2.blocks.1.norm1.bias", "layers.2.blocks.1.attn.qkv.weight", "layers.2.blocks.1.attn.qkv.bias", "layers.2.blocks.1.attn.proj.weight", "layers.2.blocks.1.attn.proj.bias", "layers.2.blocks.1.norm2.weight", "layers.2.blocks.1.norm2.bias", "layers.2.blocks.1.mlp.fc1.weight", "layers.2.blocks.1.mlp.fc1.bias", "layers.2.blocks.1.mlp.fc2.weight", "layers.2.blocks.1.mlp.fc2.bias", "layers.2.blocks.2.norm1.weight", "layers.2.blocks.2.norm1.bias", "layers.2.blocks.2.attn.qkv.weight", "layers.2.blocks.2.attn.qkv.bias", "layers.2.blocks.2.attn.proj.weight", "layers.2.blocks.2.attn.proj.bias", "layers.2.blocks.2.norm2.weight", "layers.2.blocks.2.norm2.bias", "layers.2.blocks.2.mlp.fc1.weight", "layers.2.blocks.2.mlp.fc1.bias", "layers.2.blocks.2.mlp.fc2.weight", "layers.2.blocks.2.mlp.fc2.bias", "layers.2.blocks.3.norm1.weight", "layers.2.blocks.3.norm1.bias", "layers.2.blocks.3.attn.qkv.weight", "layers.2.blocks.3.attn.qkv.bias", "layers.2.blocks.3.attn.proj.weight", "layers.2.blocks.3.attn.proj.bias", "layers.2.blocks.3.norm2.weight", "layers.2.blocks.3.norm2.bias", "layers.2.blocks.3.mlp.fc1.weight", "layers.2.blocks.3.mlp.fc1.bias", "layers.2.blocks.3.mlp.fc2.weight", "layers.2.blocks.3.mlp.fc2.bias", "layers.2.blocks.4.norm1.weight", "layers.2.blocks.4.norm1.bias", "layers.2.blocks.4.attn.qkv.weight", "layers.2.blocks.4.attn.qkv.bias", "layers.2.blocks.4.attn.proj.weight", "layers.2.blocks.4.attn.proj.bias", "layers.2.blocks.4.norm2.weight", "layers.2.blocks.4.norm2.bias", "layers.2.blocks.4.mlp.fc1.weight", "layers.2.blocks.4.mlp.fc1.bias", "layers.2.blocks.4.mlp.fc2.weight", "layers.2.blocks.4.mlp.fc2.bias", "layers.2.blocks.5.norm1.weight", "layers.2.blocks.5.norm1.bias", "layers.2.blocks.5.attn.qkv.weight", "layers.2.blocks.5.attn.qkv.bias", "layers.2.blocks.5.attn.proj.weight", "layers.2.blocks.5.attn.proj.bias", "layers.2.blocks.5.norm2.weight", "layers.2.blocks.5.norm2.bias", "layers.2.blocks.5.mlp.fc1.weight", "layers.2.blocks.5.mlp.fc1.bias", "layers.2.blocks.5.mlp.fc2.weight", "layers.2.blocks.5.mlp.fc2.bias", "layers.2.downsample.norm.weight", "layers.2.downsample.norm.bias", "layers.3.blocks.0.norm1.weight", "layers.3.blocks.0.norm1.bias", "layers.3.blocks.0.attn.qkv.weight", "layers.3.blocks.0.attn.qkv.bias", "layers.3.blocks.0.attn.proj.weight", "layers.3.blocks.0.attn.proj.bias", "layers.3.blocks.0.norm2.weight", "layers.3.blocks.0.norm2.bias", "layers.3.blocks.0.mlp.fc1.weight", "layers.3.blocks.0.mlp.fc1.bias", "layers.3.blocks.0.mlp.fc2.weight", "layers.3.blocks.0.mlp.fc2.bias", "layers.3.blocks.1.norm1.weight", "layers.3.blocks.1.norm1.bias", "layers.3.blocks.1.attn.qkv.weight", "layers.3.blocks.1.attn.qkv.bias", "layers.3.blocks.1.attn.proj.weight", "layers.3.blocks.1.attn.proj.bias", "layers.3.blocks.1.norm2.weight", "layers.3.blocks.1.norm2.bias", "layers.3.blocks.1.mlp.fc1.weight", "layers.3.blocks.1.mlp.fc1.bias", "layers.3.blocks.1.mlp.fc2.weight", "layers.3.blocks.1.mlp.fc2.bias", "norm.weight", "norm.bias", "head.weight", "head.bias", "layers.0.blocks.0.attn.relative_position_index", "layers.0.blocks.1.attn.relative_position_index", "layers.1.blocks.0.attn.relative_position_index", "layers.1.blocks.1.attn.relative_position_index", "layers.2.blocks.0.attn.relative_position_index", "layers.2.blocks.1.attn.relative_position_index", "layers.2.blocks.2.attn.relative_position_index", "layers.2.blocks.3.attn.relative_position_index", "layers.2.blocks.4.attn.relative_position_index", "layers.2.blocks.5.attn.relative_position_index", "layers.3.blocks.0.attn.relative_position_index", "layers.3.blocks.1.attn.relative_position_index", "layers.0.blocks.1.attn_mask", "layers.1.blocks.1.attn_mask", "layers.2.blocks.1.attn_mask", "layers.2.blocks.3.attn_mask", "layers.2.blocks.5.attn_mask", "layers.0.blocks.0.attn.relative_position_bias_table", "layers.0.blocks.1.attn.relative_position_bias_table", "layers.1.blocks.0.attn.relative_position_bias_table", "layers.1.blocks.1.attn.relative_position_bias_table", "layers.2.blocks.0.attn.relative_position_bias_table", "layers.2.blocks.1.attn.relative_position_bias_table", "layers.2.blocks.2.attn.relative_position_bias_table", "layers.2.blocks.3.attn.relative_position_bias_table", "layers.2.blocks.4.attn.relative_position_bias_table", "layers.2.blocks.5.attn.relative_position_bias_table", "layers.3.blocks.0.attn.relative_position_bias_table", "layers.3.blocks.1.attn.relative_position_bias_table", "layers.0.downsample.reduction.weight", "layers.1.downsample.reduction.weight", "layers.2.downsample.reduction.weight". 

[wangru1026]

snapshot是不是存储路径错误？

[JiafengtTang]

hi, do you have settled this bug?

[plo97]

I encountered a similar error.