search

yangheng95 / PyABSA

Sentiment Analysis, Text Classification, Text Augmentation, Text Adversarial defense, etc.;
https://pyabsa.readthedocs.io
MIT License
923 stars 159 forks source link

Raised error when run continue train from a trained model #148

Closed brightgems closed 2 years ago

brightgems commented 2 years ago

Enviroment: pyabsa v1.8.39

below is error message:


       size mismatch for dense.weight: copying a param with shape torch.Size([4, 768]) from checkpoint, the shape in currentmodel is torch.Size([3, 768]).
        size mismatch for dense.bias: copying a param with shape torch.Size([4]) from checkpoint, the shape in current model is torch.Size([3]).
brightgems commented 2 years ago

I guess it caused by difference in label# of pre-train model. so it can close now.