muberraozmen / simplymlc Goto Github PK

Halo, muberraozmen:
Its a good work! I have been train a model. But when i want to predict on new dataset,i found a problem about load model, How can i fix it? Tks very much!
@muberraozmen
import builder

model = builder.Model(num_features=512,num_labels=9,dim_feedforward=1024)
model.load_model(path + "best_model_professsion.model")

RuntimeError Traceback (most recent call last)
in
----> 1 model.load_model(path + "best_model_professsion.model")

C:\Jupyternotebook\antiy\phone_figure\simplyMLC-master\builder.py in load_model(self, model_dir)
74
75 def load_model(self, model_dir):
---> 76 self.model.load_state_dict(torch.load(model_dir))
77
78 @staticmethod

C:\Anaconda3\lib\site-packages\torch\nn\modules\module.py in load_state_dict(self, state_dict, strict)
1481 if len(error_msgs) > 0:
1482 raise RuntimeError('Error(s) in loading state_dict for {}:\n\t{}'.format(
-> 1483 self.class.name, "\n\t".join(error_msgs)))
1484 return _IncompatibleKeys(missing_keys, unexpected_keys)
1485

RuntimeError: Error(s) in loading state_dict for TransformerMLC:
Missing key(s) in state_dict: "encoder.layers.2.self_attn.in_proj_weight", "encoder.layers.2.self_attn.in_proj_bias", "encoder.layers.2.self_attn.out_proj.weight", "encoder.layers.2.self_attn.out_proj.bias", "encoder.layers.2.linear1.weight", "encoder.layers.2.linear1.bias", "encoder.layers.2.linear2.weight", "encoder.layers.2.linear2.bias", "encoder.layers.2.norm1.weight", "encoder.layers.2.norm1.bias", "encoder.layers.2.norm2.weight", "encoder.layers.2.norm2.bias", "encoder.layers.3.self_attn.in_proj_weight", "encoder.layers.3.self_attn.in_proj_bias", "encoder.layers.3.self_attn.out_proj.weight", "encoder.layers.3.self_attn.out_proj.bias", "encoder.layers.3.linear1.weight", "encoder.layers.3.linear1.bias", "encoder.layers.3.linear2.weight", "encoder.layers.3.linear2.bias", "encoder.layers.3.norm1.weight", "encoder.layers.3.norm1.bias", "encoder.layers.3.norm2.weight", "encoder.layers.3.norm2.bias", "encoder.layers.4.self_attn.in_proj_weight", "encoder.layers.4.self_attn.in_proj_bias", "encoder.layers.4.self_attn.out_proj.weight", "encoder.layers.4.self_attn.out_proj.bias", "encoder.layers.4.linear1.weight", "encoder.layers.4.linear1.bias", "encoder.layers.4.linear2.weight", "encoder.layers.4.linear2.bias", "encoder.layers.4.norm1.weight", "encoder.layers.4.norm1.bias", "encoder.layers.4.norm2.weight", "encoder.layers.4.norm2.bias", "encoder.layers.5.self_attn.in_proj_weight", "encoder.layers.5.self_attn.in_proj_bias", "encoder.layers.5.self_attn.out_proj.weight", "encoder.layers.5.self_attn.out_proj.bias", "encoder.layers.5.linear1.weight", "encoder.layers.5.linear1.bias", "encoder.layers.5.linear2.weight", "encoder.layers.5.linear2.bias", "encoder.layers.5.norm1.weight", "encoder.layers.5.norm1.bias", "encoder.layers.5.norm2.weight", "encoder.layers.5.norm2.bias", "decoder.layers.2.multihead_attn.in_proj_weight", "decoder.layers.2.multihead_attn.in_proj_bias", "decoder.layers.2.multihead_attn.out_proj.weight", "decoder.layers.2.multihead_attn.out_proj.bias", "decoder.layers.2.linear1.weight", "decoder.layers.2.linear1.bias", "decoder.layers.2.linear2.weight", "decoder.layers.2.linear2.bias", "decoder.layers.2.norm1.weight", "decoder.layers.2.norm1.bias", "decoder.layers.2.norm2.weight", "decoder.layers.2.norm2.bias", "decoder.layers.3.multihead_attn.in_proj_weight", "decoder.layers.3.multihead_attn.in_proj_bias", "decoder.layers.3.multihead_attn.out_proj.weight", "decoder.layers.3.multihead_attn.out_proj.bias", "decoder.layers.3.linear1.weight", "decoder.layers.3.linear1.bias", "decoder.layers.3.linear2.weight", "decoder.layers.3.linear2.bias", "decoder.layers.3.norm1.weight", "decoder.layers.3.norm1.bias", "decoder.layers.3.norm2.weight", "decoder.layers.3.norm2.bias", "decoder.layers.4.multihead_attn.in_proj_weight", "decoder.layers.4.multihead_attn.in_proj_bias", "decoder.layers.4.multihead_attn.out_proj.weight", "decoder.layers.4.multihead_attn.out_proj.bias", "decoder.layers.4.linear1.weight", "decoder.layers.4.linear1.bias", "decoder.layers.4.linear2.weight", "decoder.layers.4.linear2.bias", "decoder.layers.4.norm1.weight", "decoder.layers.4.norm1.bias", "decoder.layers.4.norm2.weight", "decoder.layers.4.norm2.bias", "decoder.layers.5.multihead_attn.in_proj_weight", "decoder.layers.5.multihead_attn.in_proj_bias", "decoder.layers.5.multihead_attn.out_proj.weight", "decoder.layers.5.multihead_attn.out_proj.bias", "decoder.layers.5.linear1.weight", "decoder.layers.5.linear1.bias", "decoder.layers.5.linear2.weight", "decoder.layers.5.linear2.bias", "decoder.layers.5.norm1.weight", "decoder.layers.5.norm1.bias", "decoder.layers.5.norm2.weight", "decoder.layers.5.norm2.bias".
size mismatch for input_emb.weight: copying a param with shape torch.Size([11314, 512]) from checkpoint, the shape in current model is torch.Size([512, 512]).