这个问题与How can I check a confusion_matrix after fine-tuning with custom datasets?相同，在Data Science Stack Exchange上。

背景

我想检查一个confusion_matrix，包括precision，recall和f1-score，如下所示，经过自定义数据集的微调。
微调过程和任务是序列分类与IMDb评论上的自定义数据集微调教程拥抱脸。
使用Trainer完成微调后，在这种情况下如何检查confusion_matrix？
confusion_matrix的图像，包括precision、recall和f1-score original site：仅作为输出图像示例

predictions = np.argmax(trainer.test(test_x), axis=1)

# Confusion matrix and classification report.
print(classification_report(test_y, predictions))

            precision    recall  f1-score   support

          0       0.75      0.79      0.77      1000
          1       0.81      0.87      0.84      1000
          2       0.63      0.61      0.62      1000
          3       0.55      0.47      0.50      1000
          4       0.66      0.66      0.66      1000
          5       0.62      0.64      0.63      1000
          6       0.74      0.83      0.78      1000
          7       0.80      0.74      0.77      1000
          8       0.85      0.81      0.83      1000
          9       0.79      0.80      0.80      1000

avg / total       0.72      0.72      0.72     10000

代码

from transformers import DistilBertForSequenceClassification, Trainer, TrainingArguments

training_args = TrainingArguments(
    output_dir='./results',          # output directory
    num_train_epochs=3,              # total number of training epochs
    per_device_train_batch_size=16,  # batch size per device during training
    per_device_eval_batch_size=64,   # batch size for evaluation
    warmup_steps=500,                # number of warmup steps for learning rate scheduler
    weight_decay=0.01,               # strength of weight decay
    logging_dir='./logs',            # directory for storing logs
    logging_steps=10,
)

model = DistilBertForSequenceClassification.from_pretrained("distilbert-base-uncased")

trainer = Trainer(
    model=model,                         # the instantiated 🤗 Transformers model to be trained
    args=training_args,                  # training arguments, defined above
    train_dataset=train_dataset,         # training dataset
    eval_dataset=val_dataset             # evaluation dataset
)

trainer.train()

到目前为止我所做的

数据集准备序列分类与IMDb评论，我微调与教练。

from pathlib import Path

def read_imdb_split(split_dir):
    split_dir = Path(split_dir)
    texts = []
    labels = []
    for label_dir in ["pos", "neg"]:
        for text_file in (split_dir/label_dir).iterdir():
            texts.append(text_file.read_text())
            labels.append(0 if label_dir is "neg" else 1)

    return texts, labels

train_texts, train_labels = read_imdb_split('aclImdb/train')
test_texts, test_labels = read_imdb_split('aclImdb/test')

from sklearn.model_selection import train_test_split
train_texts, val_texts, train_labels, val_labels = train_test_split(train_texts, train_labels, test_size=.2)

from transformers import DistilBertTokenizerFast
tokenizer = DistilBertTokenizerFast.from_pretrained('distilbert-base-uncased')

train_encodings = tokenizer(train_texts, truncation=True, padding=True)
val_encodings = tokenizer(val_texts, truncation=True, padding=True)
test_encodings = tokenizer(test_texts, truncation=True, padding=True)

import torch

class IMDbDataset(torch.utils.data.Dataset):
    def __init__(self, encodings, labels):
        self.encodings = encodings
        self.labels = labels

    def __getitem__(self, idx):
        item = {key: torch.tensor(val[idx]) for key, val in self.encodings.items()}
        item['labels'] = torch.tensor(self.labels[idx])
        return item

    def __len__(self):
        return len(self.labels)

train_dataset = IMDbDataset(train_encodings, train_labels)
val_dataset = IMDbDataset(val_encodings, val_labels)
test_dataset = IMDbDataset(test_encodings, test_labels)