如何使用 Huggingface BERT 模型为二元分类器 CNN 提供数据？

Question

我有点困惑如何使用 huggingface transformers 输出来训练一个简单的语言二元分类器模型来预测阿尔伯特·爱因斯坦是否说过一句话。

from transformers import AutoTokenizer, AutoModel

tokenizer = AutoTokenizer.from_pretrained("bert-base-uncased")
model = AutoModel.from_pretrained("bert-base-uncased")

inputs = ["Hello World", "Hello There", "Bye Bye", "Two things are infinite: the universe and human stupidity; and I'm not sure about the universe."]
for input in inputs:
  inputs = tokenizer(input, return_tensors="pt")
  outputs = model(**inputs)
  print(outputs[0].shape, input, len(input))

输出：

Some weights of the model checkpoint at bert-base-uncased were not used when initializing BertModel: ['cls.predictions.transform.LayerNorm.weight', 'cls.predictions.bias', 'cls.seq_relationship.bias', 'cls.seq_relationship.weight', 'cls.predictions.transform.LayerNorm.bias', 'cls.predictions.transform.dense.weight', 'cls.predictions.decoder.weight', 'cls.predictions.transform.dense.bias']
- This IS expected if you are initializing BertModel from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).
- This IS NOT expected if you are initializing BertModel from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).
torch.Size([1, 4, 768]) Hello World 11
torch.Size([1, 4, 768]) Hello There 11
torch.Size([1, 4, 768]) Bye Bye 7
torch.Size([1, 23, 768]) Two things are infinite: the universe and human stupidity; and I'm not sure about the universe. 95

如您所见，输出的尺寸随输入的长度而变化。现在假设我想训练一个二元分类器来预测爱因斯坦是否说过输入句子，并且网络的输入将是 BERT transformer 的预测。

如何在 pytorch 中编写一个采用张量 [1, None, 768] 的 CNN 模型？似乎第二维随着输入的长度而变化。

Answer 1

在 pytorch 中，您不需要为 CNN 设置固定的 input dim。唯一的要求是您的kernel_size 不得小于input_size。

一般来说，在 Transformer 模型之上放置分类器（序列分类器）的最佳方式是添加一个池化层 + FC层。您可以使用全局池化、平均池化或最大池化或自适应池化，然后使用全连接层。

请注意，您还可以使用 AutoModelForSequenceClassification 为您完成所有工作。

#An example with a simple average pooling
from transformers import AutoTokenizer, AutoModel
import torch

NUM_CLASSES = 1
MAX_LEN = 30

    
    
tokenizer = AutoTokenizer.from_pretrained("bert-base-uncased")
model = AutoModel.from_pretrained("bert-base-uncased")
model.classifier = torch.nn.Linear(model.pooler.dense.in_features, NUM_CLASSES)


inputs_str = ["Hello World", "Hello There", "Bye Bye", "Two things are infinite: the universe and human stupidity; and I'm not sure about the universe."]

inputs = tokenizer(inputs_str, padding="max_length", return_tensors="pt", max_length=MAX_LEN)

outputs, _ = model(**inputs)
outputs = torch.mean(outputs, dim=1)
outputs = model.classifier(outputs)
print(outputs.shape) #=> (4,1)