RuntimeError: Error(s) in loading state_dict for VisionTransformer

[zimoradi76]

hello thanks for implementation sharing I have an error while trying to train your model.

I used Seg-T-Mask/16 as backbone. and this is my command for training: python -m segm.train --log-dir seg_tiny_mask --dataset ade20k --backbone vit_tiny_patch16_384 --decoder mask_transformer this is my error:

python -m segm.train --log-dir seg_tiny_mask --dataset ade20k --backbone vit_tiny_patch16_384 --decoder mask_transformer /home/moradi/code/segmenter-master/segm/train.py:72: FutureWarning: You are using torch.load with weights_only=False (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for weights_only will be flipped to True. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via torch.serialization.add_safe_globals. We recommend you start setting weights_only=True for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature. model = torch.load('/home/moradi/code/segmenter-master/vit_base_patch8_384.pth', map_location='cpu') Starting process with rank 0... Process 0 is connected. All processes are connected. Use normalization: {'mean': (127.5, 127.5, 127.5), 'std': (127.5, 127.5, 127.5)} root_dir is here: /home/moradi/data/ADEChallengeData2016 2024-10-11 18:48:27,253 - mmseg - INFO - Loaded 20210 images Use normalization: {'mean': (127.5, 127.5, 127.5), 'std': (127.5, 127.5, 127.5)} root_dir is here: /home/moradi/data/ADEChallengeData2016 2024-10-11 18:48:27,308 - mmseg - INFO - Loaded 2000 images /home/moradi/code/segmenter-master/segm/model/factory.py:84: FutureWarning: You are using torch.load with weights_only=False (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for weights_only will be flipped to True. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via torch.serialization.add_safe_globals. We recommend you start setting weights_only=True for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature. state_dict = torch.load(local_path, map_location='cuda') rank0: Traceback (most recent call last): rank0: File "/opt/anaconda3/envs/Project1/lib/python3.9/runpy.py", line 197, in _run_module_as_main rank0: return _run_code(code, main_globals, None, rank0: File "/opt/anaconda3/envs/Project1/lib/python3.9/runpy.py", line 87, in _run_code rank0: exec(code, run_globals) rank0: File "/home/moradi/code/segmenter-master/segm/train.py", line 307, in

rank0: File "/opt/anaconda3/envs/Project1/lib/python3.9/site-packages/click/core.py", line 1157, in call rank0: return self.main(args, kwargs) rank0: File "/opt/anaconda3/envs/Project1/lib/python3.9/site-packages/click/core.py", line 1078, in main rank0: rv = self.invoke(ctx) rank0: File "/opt/anaconda3/envs/Project1/lib/python3.9/site-packages/click/core.py", line 1434, in invoke rank0: return ctx.invoke(self.callback, ctx.params) rank0: File "/opt/anaconda3/envs/Project1/lib/python3.9/site-packages/click/core.py", line 783, in invoke rank0: return __callback(args, **kwargs) rank0: File "/home/moradi/code/segmenter-master/segm/train.py", line 180, in main rank0: model = create_segmenter(net_kwargs) rank0: File "/home/moradi/code/segmenter-master/segm/model/factory.py", line 116, in create_segmenter rank0: encoder = create_vit(model_cfg) rank0: File "/home/moradi/code/segmenter-master/segm/model/factory.py", line 77, in create_vit rank0: load_custom_pretrained_2(model, default_cfg) rank0: File "/home/moradi/code/segmenter-master/segm/model/factory.py", line 86, in load_custom_pretrained_2 rank0: model.load_state_dict(filtered_dict, strict=True) rank0: File "/opt/anaconda3/envs/Project1/lib/python3.9/site-packages/torch/nn/modules/module.py", line 2215, in load_state_dict rank0: raise RuntimeError('Error(s) in loading state_dict for {}:\n\t{}'.format( rank0: RuntimeError: Error(s) in loading state_dict for VisionTransformer: rank0: Missing key(s) in state_dict: "cls_token", "pos_embed", "patch_embed.proj.weight", "patch_embed.proj.bias", "blocks.0.norm1.weight", "blocks.0.norm1.bias", "blocks.0.norm2.weight", "blocks.0.norm2.bias", "blocks.0.attn.qkv.weight", "blocks.0.attn.qkv.bias", "blocks.0.attn.proj.weight", "blocks.0.attn.proj.bias", "blocks.0.mlp.fc1.weight", "blocks.0.mlp.fc1.bias", "blocks.0.mlp.fc2.weight", "blocks.0.mlp.fc2.bias", "blocks.1.norm1.weight", "blocks.1.norm1.bias", "blocks.1.norm2.weight", "blocks.1.norm2.bias", "blocks.1.attn.qkv.weight", "blocks.1.attn.qkv.bias", "blocks.1.attn.proj.weight", "blocks.1.attn.proj.bias", "blocks.1.mlp.fc1.weight", "blocks.1.mlp.fc1.bias", "blocks.1.mlp.fc2.weight", "blocks.1.mlp.fc2.bias", "blocks.2.norm1.weight", "blocks.2.norm1.bias", "blocks.2.norm2.weight", "blocks.2.norm2.bias", "blocks.2.attn.qkv.weight", "blocks.2.attn.qkv.bias", "blocks.2.attn.proj.weight", "blocks.2.attn.proj.bias", "blocks.2.mlp.fc1.weight", "blocks.2.mlp.fc1.bias", "blocks.2.mlp.fc2.weight", "blocks.2.mlp.fc2.bias", "blocks.3.norm1.weight", "blocks.3.norm1.bias", "blocks.3.norm2.weight", "blocks.3.norm2.bias", "blocks.3.attn.qkv.weight", "blocks.3.attn.qkv.bias", "blocks.3.attn.proj.weight", "blocks.3.attn.proj.bias", "blocks.3.mlp.fc1.weight", "blocks.3.mlp.fc1.bias", "blocks.3.mlp.fc2.weight", "blocks.3.mlp.fc2.bias", "blocks.4.norm1.weight", "blocks.4.norm1.bias", "blocks.4.norm2.weight", "blocks.4.norm2.bias", "blocks.4.attn.qkv.weight", "blocks.4.attn.qkv.bias", "blocks.4.attn.proj.weight", "blocks.4.attn.proj.bias", "blocks.4.mlp.fc1.weight", "blocks.4.mlp.fc1.bias", "blocks.4.mlp.fc2.weight", "blocks.4.mlp.fc2.bias", "blocks.5.norm1.weight", "blocks.5.norm1.bias", "blocks.5.norm2.weight", "blocks.5.norm2.bias", "blocks.5.attn.qkv.weight", "blocks.5.attn.qkv.bias", "blocks.5.attn.proj.weight", "blocks.5.attn.proj.bias", "blocks.5.mlp.fc1.weight", "blocks.5.mlp.fc1.bias", "blocks.5.mlp.fc2.weight", "blocks.5.mlp.fc2.bias", "blocks.6.norm1.weight", "blocks.6.norm1.bias", "blocks.6.norm2.weight", "blocks.6.norm2.bias", "blocks.6.attn.qkv.weight", "blocks.6.attn.qkv.bias", "blocks.6.attn.proj.weight", "blocks.6.attn.proj.bias", "blocks.6.mlp.fc1.weight", "blocks.6.mlp.fc1.bias", "blocks.6.mlp.fc2.weight", "blocks.6.mlp.fc2.bias", "blocks.7.norm1.weight", "blocks.7.norm1.bias", "blocks.7.norm2.weight", "blocks.7.norm2.bias", "blocks.7.attn.qkv.weight", "blocks.7.attn.qkv.bias", "blocks.7.attn.proj.weight", "blocks.7.attn.proj.bias", "blocks.7.mlp.fc1.weight", "blocks.7.mlp.fc1.bias", "blocks.7.mlp.fc2.weight", "blocks.7.mlp.fc2.bias", "blocks.8.norm1.weight", "blocks.8.norm1.bias", "blocks.8.norm2.weight", "blocks.8.norm2.bias", "blocks.8.attn.qkv.weight", "blocks.8.attn.qkv.bias", "blocks.8.attn.proj.weight", "blocks.8.attn.proj.bias", "blocks.8.mlp.fc1.weight", "blocks.8.mlp.fc1.bias", "blocks.8.mlp.fc2.weight", "blocks.8.mlp.fc2.bias", "blocks.9.norm1.weight", "blocks.9.norm1.bias", "blocks.9.norm2.weight", "blocks.9.norm2.bias", "blocks.9.attn.qkv.weight", "blocks.9.attn.qkv.bias", "blocks.9.attn.proj.weight", "blocks.9.attn.proj.bias", "blocks.9.mlp.fc1.weight", "blocks.9.mlp.fc1.bias", "blocks.9.mlp.fc2.weight", "blocks.9.mlp.fc2.bias", "blocks.10.norm1.weight", "blocks.10.norm1.bias", "blocks.10.norm2.weight", "blocks.10.norm2.bias", "blocks.10.attn.qkv.weight", "blocks.10.attn.qkv.bias", "blocks.10.attn.proj.weight", "blocks.10.attn.proj.bias", "blocks.10.mlp.fc1.weight", "blocks.10.mlp.fc1.bias", "blocks.10.mlp.fc2.weight", "blocks.10.mlp.fc2.bias", "blocks.11.norm1.weight", "blocks.11.norm1.bias", "blocks.11.norm2.weight", "blocks.11.norm2.bias", "blocks.11.attn.qkv.weight", "blocks.11.attn.qkv.bias", "blocks.11.attn.proj.weight", "blocks.11.attn.proj.bias", "blocks.11.mlp.fc1.weight", "blocks.11.mlp.fc1.bias", "blocks.11.mlp.fc2.weight", "blocks.11.mlp.fc2.bias", "norm.weight", "norm.bias", "head.weight", "head.bias". rank0: Unexpected key(s) in state_dict: "encoder.cls_token", "encoder.pos_embed", "encoder.patch_embed.proj.weight", "encoder.patch_embed.proj.bias", "encoder.blocks.0.norm1.weight", "encoder.blocks.0.norm1.bias", "encoder.blocks.0.norm2.weight", "encoder.blocks.0.norm2.bias", "encoder.blocks.0.attn.qkv.weight", "encoder.blocks.0.attn.qkv.bias", "encoder.blocks.0.attn.proj.weight", "encoder.blocks.0.attn.proj.bias", "encoder.blocks.0.mlp.fc1.weight", "encoder.blocks.0.mlp.fc1.bias", "encoder.blocks.0.mlp.fc2.weight", "encoder.blocks.0.mlp.fc2.bias", "encoder.blocks.1.norm1.weight", "encoder.blocks.1.norm1.bias", "encoder.blocks.1.norm2.weight", "encoder.blocks.1.norm2.bias", "encoder.blocks.1.attn.qkv.weight", "encoder.blocks.1.attn.qkv.bias", "encoder.blocks.1.attn.proj.weight", "encoder.blocks.1.attn.proj.bias", "encoder.blocks.1.mlp.fc1.weight", "encoder.blocks.1.mlp.fc1.bias", "encoder.blocks.1.mlp.fc2.weight", "encoder.blocks.1.mlp.fc2.bias", "encoder.blocks.2.norm1.weight", "encoder.blocks.2.norm1.bias", "encoder.blocks.2.norm2.weight", "encoder.blocks.2.norm2.bias", "encoder.blocks.2.attn.qkv.weight", "encoder.blocks.2.attn.qkv.bias", "encoder.blocks.2.attn.proj.weight", "encoder.blocks.2.attn.proj.bias", "encoder.blocks.2.mlp.fc1.weight", "encoder.blocks.2.mlp.fc1.bias", "encoder.blocks.2.mlp.fc2.weight", "encoder.blocks.2.mlp.fc2.bias", "encoder.blocks.3.norm1.weight", "encoder.blocks.3.norm1.bias", "encoder.blocks.3.norm2.weight", "encoder.blocks.3.norm2.bias", "encoder.blocks.3.attn.qkv.weight", "encoder.blocks.3.attn.qkv.bias", "encoder.blocks.3.attn.proj.weight", "encoder.blocks.3.attn.proj.bias", "encoder.blocks.3.mlp.fc1.weight", "encoder.blocks.3.mlp.fc1.bias", "encoder.blocks.3.mlp.fc2.weight", "encoder.blocks.3.mlp.fc2.bias", "encoder.blocks.4.norm1.weight", "encoder.blocks.4.norm1.bias", "encoder.blocks.4.norm2.weight", "encoder.blocks.4.norm2.bias", "encoder.blocks.4.attn.qkv.weight", "encoder.blocks.4.attn.qkv.bias", "encoder.blocks.4.attn.proj.weight", "encoder.blocks.4.attn.proj.bias", "encoder.blocks.4.mlp.fc1.weight", "encoder.blocks.4.mlp.fc1.bias", "encoder.blocks.4.mlp.fc2.weight", "encoder.blocks.4.mlp.fc2.bias", "encoder.blocks.5.norm1.weight", "encoder.blocks.5.norm1.bias", "encoder.blocks.5.norm2.weight", "encoder.blocks.5.norm2.bias", "encoder.blocks.5.attn.qkv.weight", "encoder.blocks.5.attn.qkv.bias", "encoder.blocks.5.attn.proj.weight", "encoder.blocks.5.attn.proj.bias", "encoder.blocks.5.mlp.fc1.weight", "encoder.blocks.5.mlp.fc1.bias", "encoder.blocks.5.mlp.fc2.weight", "encoder.blocks.5.mlp.fc2.bias", "encoder.blocks.6.norm1.weight", "encoder.blocks.6.norm1.bias", "encoder.blocks.6.norm2.weight", "encoder.blocks.6.norm2.bias", "encoder.blocks.6.attn.qkv.weight", "encoder.blocks.6.attn.qkv.bias", "encoder.blocks.6.attn.proj.weight", "encoder.blocks.6.attn.proj.bias", "encoder.blocks.6.mlp.fc1.weight", "encoder.blocks.6.mlp.fc1.bias", "encoder.blocks.6.mlp.fc2.weight", "encoder.blocks.6.mlp.fc2.bias", "encoder.blocks.7.norm1.weight", "encoder.blocks.7.norm1.bias", "encoder.blocks.7.norm2.weight", "encoder.blocks.7.norm2.bias", "encoder.blocks.7.attn.qkv.weight", "encoder.blocks.7.attn.qkv.bias", "encoder.blocks.7.attn.proj.weight", "encoder.blocks.7.attn.proj.bias", "encoder.blocks.7.mlp.fc1.weight", "encoder.blocks.7.mlp.fc1.bias", "encoder.blocks.7.mlp.fc2.weight", "encoder.blocks.7.mlp.fc2.bias", "encoder.blocks.8.norm1.weight", "encoder.blocks.8.norm1.bias", "encoder.blocks.8.norm2.weight", "encoder.blocks.8.norm2.bias", "encoder.blocks.8.attn.qkv.weight", "encoder.blocks.8.attn.qkv.bias", "encoder.blocks.8.attn.proj.weight", "encoder.blocks.8.attn.proj.bias", "encoder.blocks.8.mlp.fc1.weight", "encoder.blocks.8.mlp.fc1.bias", "encoder.blocks.8.mlp.fc2.weight", "encoder.blocks.8.mlp.fc2.bias", "encoder.blocks.9.norm1.weight", "encoder.blocks.9.norm1.bias", "encoder.blocks.9.norm2.weight", "encoder.blocks.9.norm2.bias", "encoder.blocks.9.attn.qkv.weight", "encoder.blocks.9.attn.qkv.bias", "encoder.blocks.9.attn.proj.weight", "encoder.blocks.9.attn.proj.bias", "encoder.blocks.9.mlp.fc1.weight", "encoder.blocks.9.mlp.fc1.bias", "encoder.blocks.9.mlp.fc2.weight", "encoder.blocks.9.mlp.fc2.bias", "encoder.blocks.10.norm1.weight", "encoder.blocks.10.norm1.bias", "encoder.blocks.10.norm2.weight", "encoder.blocks.10.norm2.bias", "encoder.blocks.10.attn.qkv.weight", "encoder.blocks.10.attn.qkv.bias", "encoder.blocks.10.attn.proj.weight", "encoder.blocks.10.attn.proj.bias", "encoder.blocks.10.mlp.fc1.weight", "encoder.blocks.10.mlp.fc1.bias", "encoder.blocks.10.mlp.fc2.weight", "encoder.blocks.10.mlp.fc2.bias", "encoder.blocks.11.norm1.weight", "encoder.blocks.11.norm1.bias", "encoder.blocks.11.norm2.weight", "encoder.blocks.11.norm2.bias", "encoder.blocks.11.attn.qkv.weight", "encoder.blocks.11.attn.qkv.bias", "encoder.blocks.11.attn.proj.weight", "encoder.blocks.11.attn.proj.bias", "encoder.blocks.11.mlp.fc1.weight", "encoder.blocks.11.mlp.fc1.bias", "encoder.blocks.11.mlp.fc2.weight", "encoder.blocks.11.mlp.fc2.bias", "encoder.norm.weight", "encoder.norm.bias", "encoder.head.weight", "encoder.head.bias", "decoder.cls_emb", "decoder.proj_patch", "decoder.proj_classes", "decoder.blocks.0.norm1.weight", "decoder.blocks.0.norm1.bias", "decoder.blocks.0.norm2.weight", "decoder.blocks.0.norm2.bias", "decoder.blocks.0.attn.qkv.weight", "decoder.blocks.0.attn.qkv.bias", "decoder.blocks.0.attn.proj.weight", "decoder.blocks.0.attn.proj.bias", "decoder.blocks.0.mlp.fc1.weight", "decoder.blocks.0.mlp.fc1.bias", "decoder.blocks.0.mlp.fc2.weight", "decoder.blocks.0.mlp.fc2.bias", "decoder.blocks.1.norm1.weight", "decoder.blocks.1.norm1.bias", "decoder.blocks.1.norm2.weight", "decoder.blocks.1.norm2.bias", "decoder.blocks.1.attn.qkv.weight", "decoder.blocks.1.attn.qkv.bias", "decoder.blocks.1.attn.proj.weight", "decoder.blocks.1.attn.proj.bias", "decoder.blocks.1.mlp.fc1.weight", "decoder.blocks.1.mlp.fc1.bias", "decoder.blocks.1.mlp.fc2.weight", "decoder.blocks.1.mlp.fc2.bias", "decoder.proj_dec.weight", "decoder.proj_dec.bias", "decoder.decoder_norm.weight", "decoder.decoder_norm.bias", "decoder.mask_norm.weight", "decoder.mask_norm.bias".