如何从HuggingFace的文本分类管道中获取模型的logits?

huangapple go评论63阅读模式
英文:

How to get the logits of the model with a text classification pipeline from HuggingFace?

问题

You can obtain the logits from the distilbert-base-uncased-finetuned-sst-2-english model using the classifier pipeline by modifying your code as follows:

selected_model = "distilbert-base-uncased-finetuned-sst-2-english"
tokenizer = AutoTokenizer.from_pretrained(selected_model)
model = AutoModelForSequenceClassification.from_pretrained(selected_model, num_labels=2)
classifier = pipeline('sentiment-analysis', model=model, tokenizer=tokenizer)

# Input text
text = "Your input sentence here"

# Tokenize the text
inputs = tokenizer(text, return_tensors="pt")

# Get the logits
with torch.no_grad():
    logits = model(**inputs).logits

print(logits)

This code first tokenizes your input text using the tokenizer, then passes it through the model to obtain the logits. You can replace "Your input sentence here" with the text you want to analyze, and it will return the logits for that input text.

英文:

I need to use pipeline in order to get the tokenization and inference from the distilbert-base-uncased-finetuned-sst-2-english model over my dataset.

My data is a list of sentences, for recreation purposes we can assume it is:

texts = ["this is the first sentence", "of my data.", "In fact, thats not true,", "but we are going to assume it", "is"]

Before using pipeline, I was getting the logits from the model outputs like this:

with torch.no_grad():
     logits = model(**tokenized_test).logits

Now I have to use pipeline, so this is the way I'm getting the model's output:

 selected_model = "distilbert-base-uncased-finetuned-sst-2-english"
 tokenizer = AutoTokenizer.from_pretrained(selected_model)
 model = AutoModelForSequenceClassification.from_pretrained(selected_model, num_labels=2)
 classifier = pipeline('sentiment-analysis', model=model, tokenizer=tokenizer)
 print(classifier(text))

which gives me:

[{'label': 'POSITIVE', 'score': 0.9746173024177551}, {'label': 'NEGATIVE', 'score': 0.5020197629928589}, {'label': 'NEGATIVE', 'score': 0.9995120763778687}, {'label': 'NEGATIVE', 'score': 0.9802979826927185}, {'label': 'POSITIVE', 'score': 0.9274746775627136}]

And I cant get the 'logits' field anymore.

Is there a way to get the logits instead of the label and score? Would a custom pipeline be the best and/or easiest way to do it?

答案1

得分: 4

When you use the default pipeline, the postprocess function will usually take the softmax, e.g.

from transformers import AutoTokenizer, AutoModelForSequenceClassification

tokenizer = AutoTokenizer.from_pretrained('distilbert-base-uncased-finetuned-sst-2-english')
model = AutoModelForSequenceClassification.from_pretrained('distilbert-base-uncased-finetuned-sst-2-english')

text = ['hello this is a test',
 'that transforms a list of sentences',
 'into a list of list of sentences',
 'in order to emulate, in this case, two batches of the same length',
 'to be tokenized by the hf tokenizer for the defined model']

classifier(text, batch_size=2, truncation="only_first")

[out]:

[{'label': 'NEGATIVE', 'score': 0.9379090666770935},
 {'label': 'POSITIVE', 'score': 0.9990271329879761},
 {'label': 'NEGATIVE', 'score': 0.9726701378822327},
 {'label': 'NEGATIVE', 'score': 0.9965035915374756},
 {'label': 'NEGATIVE', 'score': 0.9913086891174316}]

So what you want is to overload the postprocess logic by inheriting from the pipeline.

To check which pipeline the classifier inherits do this:

classifier = pipeline('sentiment-analysis', model=model, tokenizer=tokenizer)
type(classifier)

[out]:

transformers.pipelines.text_classification.TextClassificationPipeline

Now that you know the parent class of the task pipeline you want to use, now you can do this and still enjoy the perks of the precoded batching from TextClassificationPipeline:

from transformers import TextClassificationPipeline

class MarioThePlumber(TextClassificationPipeline):
    def postprocess(self, model_outputs):
        best_class = model_outputs["logits"]
        return best_class

pipe = MarioThePlumber(model=model, tokenizer=tokenizer)

pipe(text, batch_size=2, truncation="only_first")

[out]:

[tensor([[ 1.5094, -1.2056]]),
 tensor([[-3.4114,  3.5229]]),
 tensor([[ 1.8835, -1.6886]]),
 tensor([[ 3.0780, -2.5745]]),
 tensor([[ 2.5383, -2.1984]])]
英文:

When you use the default pipeline, the postprocess function will usually take the softmax, e.g.

from transformers import AutoTokenizer, AutoModelForSequenceClassification

tokenizer = AutoTokenizer.from_pretrained('distilbert-base-uncased-finetuned-sst-2-english')
model = AutoModelForSequenceClassification.from_pretrained('distilbert-base-uncased-finetuned-sst-2-english')


text = ['hello this is a test',
 'that transforms a list of sentences',
 'into a list of list of sentences',
 'in order to emulate, in this case, two batches of the same lenght',
 'to be tokenized by the hf tokenizer for the defined model']

classifier(text, batch_size=2, truncation="only_first")

[out]:

[{'label': 'NEGATIVE', 'score': 0.9379090666770935},
 {'label': 'POSITIVE', 'score': 0.9990271329879761},
 {'label': 'NEGATIVE', 'score': 0.9726701378822327},
 {'label': 'NEGATIVE', 'score': 0.9965035915374756},
 {'label': 'NEGATIVE', 'score': 0.9913086891174316}]

So what you want is to overload the postprocess logic by inheriting from the pipeline.

To check which pipeline the classifier inherits do this:

classifier = pipeline('sentiment-analysis', model=model, tokenizer=tokenizer)
type(classifier)

[out]:

transformers.pipelines.text_classification.TextClassificationPipeline

Now that you know the parent class of the task pipeline you want to use, now you can do this and still enjoy the perks of the precoded batching from TextClassificationPipeline:

from transformers import TextClassificationPipeline

class MarioThePlumber(TextClassificationPipeline):
    def postprocess(self, model_outputs):
        best_class = model_outputs["logits"]
        return best_class

pipe = MarioThePlumber(model=model, tokenizer=tokenizer)

pipe(text, batch_size=2, truncation="only_first")

[out]:

[tensor([[ 1.5094, -1.2056]]),
 tensor([[-3.4114,  3.5229]]),
 tensor([[ 1.8835, -1.6886]]),
 tensor([[ 3.0780, -2.5745]]),
 tensor([[ 2.5383, -2.1984]])]

huangapple
  • 本文由 发表于 2023年6月9日 01:26:56
  • 转载请务必保留本文链接:https://go.coder-hub.com/76434311.html
匿名

发表评论

匿名网友

:?: :razz: :sad: :evil: :!: :smile: :oops: :grin: :eek: :shock: :???: :cool: :lol: :mad: :twisted: :roll: :wink: :idea: :arrow: :neutral: :cry: :mrgreen:

确定