77 lines
2.9 KiB
Python
77 lines
2.9 KiB
Python
import paddle
|
|
import numpy as np
|
|
import yaml
|
|
from sklearn.metrics import accuracy_score, precision_recall_fscore_support
|
|
from paddlenlp.transformers import ErnieTokenizer
|
|
from paddle.io import DataLoader
|
|
from paddlenlp.data import DataCollatorWithPadding
|
|
import json
|
|
import functools
|
|
from paddlenlp.datasets import load_dataset
|
|
|
|
# 加载配置
|
|
with open("data.yaml", "r", encoding="utf-8") as f:
|
|
config = yaml.safe_load(f)
|
|
|
|
# 加载模型和 tokenizer
|
|
model = paddle.jit.load("trained_model_static") # 加载保存的静态图模型
|
|
tokenizer = ErnieTokenizer.from_pretrained("E:/workingSpace/PycharmProjects/Intention/models/ernie-3.0-tiny-base-v2-zh")
|
|
|
|
|
|
# 读取数据集的函数
|
|
def read_local_dataset(path, label2id=None, is_test=True):
|
|
with open(path, "r", encoding="utf-8") as f:
|
|
data = json.load(f) # 读取 JSON 数据
|
|
for item in data:
|
|
if "text" in item:
|
|
yield {"text": item["text"], "label": label2id.get(item["label"], -1)} # 如果 label 不存在，标记为 -1
|
|
|
|
# 生成 label2id 和 id2label
|
|
label_id = {label: idx for idx, label in enumerate(config["labels"])}
|
|
id_label = {idx: label for label, idx in label_id.items()}
|
|
|
|
# 数据预处理函数
|
|
def preprocess_function(examples, tokenizer, max_length, is_test=False):
|
|
result = tokenizer(examples["text"], max_length=max_length, truncation=True, padding='max_length')
|
|
if not is_test:
|
|
result["labels"] = np.array([examples["label"]], dtype="int64")
|
|
return result
|
|
|
|
# 加载数据集
|
|
test_ds = load_dataset(read_local_dataset, path=config["val"], label2id=label_id, lazy=False)
|
|
# 转换数据集
|
|
trans_func = functools.partial(preprocess_function, tokenizer=tokenizer, max_length=256)
|
|
test_ds = test_ds.map(trans_func)
|
|
|
|
# 使用 DataCollatorWithPadding
|
|
data_collator = DataCollatorWithPadding(tokenizer)
|
|
test_dataloader = DataLoader(test_ds, batch_size=16, shuffle=False, collate_fn=data_collator)
|
|
|
|
# 评估模型
|
|
model.eval() # 切换到评估模式
|
|
all_preds = []
|
|
all_labels = []
|
|
|
|
# 遍历数据集进行推理
|
|
for batch in test_dataloader:
|
|
input_ids = batch["input_ids"] # 使用模型输入的 input_ids
|
|
attention_mask = batch["attention_mask"] # 使用 attention_mask
|
|
labels = batch["labels"] # 获取真实标签（根据预处理函数传递）
|
|
# 获取模型输出
|
|
logits = model(input_ids, attention_mask=attention_mask) # 传递 input_ids 和 attention_mask
|
|
pred_labels = np.argmax(logits.numpy(), axis=1) # 选择概率最大的标签
|
|
|
|
# 保存预测值和真实标签
|
|
all_preds.extend(pred_labels)
|
|
all_labels.extend(labels.numpy())
|
|
|
|
# 计算评估指标
|
|
accuracy = accuracy_score(all_labels, all_preds)
|
|
precision, recall, f1, _ = precision_recall_fscore_support(all_labels, all_preds, average='weighted')
|
|
|
|
# 输出性能评估结果
|
|
print(f"Accuracy: {accuracy:.4f}")
|
|
print(f"Precision: {precision:.4f}")
|
|
print(f"Recall: {recall:.4f}")
|
|
print(f"F1 Score: {f1:.4f}")
|