Pytorch Bert 中文分类 运行代码时候遇到的问题

问题1 bert = AutoModel.from_pretrained('bert-base-chinese')

报错信息如下： 

RuntimeError: Error(s) in loading state_dict for BertModel:
    size mismatch for bert.embeddings.word_embeddings.weight: copying a param with shape torch.Size([21128, 768]) from checkpoint, the shape in current model is torch.Size([119547, 768]).

后来发现因为以前用的模型版本和token啥的不是一套，所以需要重新下载。

下载地址： bert-base-chinese at main (huggingface.co)

问题2  compute_class_weight('balanced', np.unique(y_train), y_train)

报错  compute_class_weight() takes 1 positional argument but 3 were given

解决方案： compute_class_weight('balanced', classes=np.unique(y_train), y=y_train)

问题3 for batch in tqdm(trainloader):

AttributeError: 'tqdm_notebook' object has no attribute 'disp'

解决方案： pip install ipywidgets