问题
请帮助理解以下问题的原因,以及如何在预训练模型的基础上从拥抱面构建Keras模型进行微调。
目标
在Huggingface的TFDistilBertForSequenceClassification之上创建用于DistilBERT微调的自定义模型。
将形状输入到模型
根据标记器输出的形状,我假设它是(2, None, 256)
,因为[input_ids, attention_mask]
将进入模型。
令牌化器的输出。
from transformers import DistilBertTokenizerFast
tokenizer = DistilBertTokenizerFast.from_pretrained('distilbert-base-uncased')
max_sequence_length = 256
tokens = tokenizer(
" ".join(["token"] * max_sequence_length),
truncation=True,
padding=True,
max_length=max_sequence_length,
return_tensors="tf"
)
print(tokens)
---
{
'input_ids': <tf.Tensor: shape=(1, 256), dtype=int32, numpy=array([[ 101, 19204, 19204, 19204, 19204, 19204, 19204, 19204, 19204, ...]], dtype=int32)>,
'attention_mask': <tf.Tensor: shape=(1, 256), dtype=int32, numpy=array([[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...]], dtype=int32)>
}
预训练模型
model = TFDistilBertForSequenceClassification.from_pretrained('distilbert-base-uncased')
for layer in model.layers:
if layer.name == "distilbert":
layer.trainable = False
model.summary()
---
Model: "tf_distil_bert_for_sequence_classification_4"
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
distilbert (TFDistilBertMain multiple 66362880
_________________________________________________________________
pre_classifier (Dense) multiple 590592
_________________________________________________________________
classifier (Dense) multiple 1538
_________________________________________________________________
dropout_99 (Dropout) multiple 0
=================================================================
Total params: 66,955,010
Trainable params: 592,130
Non-trainable params: 66,362,880
自定义模型
使用Sequential在预训练模型的顶部添加了Keras Dense层。
seq = Sequential([
model,
Dense(
name="output_softmax",
units=2,
activation="softmax"
)
])
seq.compile(
loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True),
optimizer=tf.keras.optimizers.Adam()
)
问题
基本的Layer类表示build方法创建权重。
build(self,input_shape(:此方法可用于使用add_weight((创建取决于输入形状的权重call((将通过调用build((自动构建层(如果尚未构建(。
运行该方法,但得到错误。
seq.build(input_shape=(2, None, max_sequence_length))
---
...
ValueError: You cannot build your model by calling `build` if your layers do not support float-type inputs. Instead, in order to instantiate and build your model, `call` your model on real tensor data (of the correct type).
根据错误消息,将标记器输出提供给模型,然后得到另一个错误。
seq(tokens)
---
TypeError: Failed to convert 'TFSequenceClassifierOutput(loss=None, logits=TensorShape([1, 2]), hidden_states=None, attentions=None)' to a shape: ''logits''could not be converted to a dimension. A shape should either be single dimension (e.g. 10), or an iterable of dimensions (e.g. [1, 10, None]).
环境
python --version
---
Python 3.7.10
print(tf.__version__)
---
2.5.0
print(transformers.__version__)
---
4.8.2
在不使用Sequential或构建方法的情况下,您尝试过Keras Functional API吗-(我尝试过并使用过其他预先训练过的模型(s.a:-(一个pesuedo代码(
def custom():
x=Input(shape=(256,))
y=Input(shape=(256,))
out=distilbertlayer([x,y])
out=Dense(2,activation='softmax')(out)
mod=tf.keras.models.Model([x,y],out)
return mod
custommodel=custom()
在这里,在给定的信息中。我认为这个错误是由于传递给自定义密集层的输出类型错误。作为一个建议,您可以尝试将不同的输出从distilbertlayer传递到自定义密集层,如
out=distilbertlayer([x,y])
out=Dense(2,activation='softmax')(out[:,0])
然而,首先应该理解distilbertlayer的输出格式。