发票分类器

这是一个收据/发票分类器模型，基于 MobileNet V3。其目的是检查输入图像是否为有效的发票或收据。

使用以下数据集进行训练：

• https://huggingface.co/datasets/dajor85570/invoices-and-receipts_ocr_v1
• https://huggingface.co/datasets/pouya-haghi/imagenet-subset

使用方法

要使用该模型，首先安装一些必要的依赖项：

pip install huggingface_hub onnxruntime pillow numpy

然后运行以下代码：

import json, time, numpy as np
from pathlib import Path
from PIL import Image, ImageOps
import onnxruntime as ort
from huggingface_hub import hf_hub_download

REPO_ID = "huytd189/invoice-classifier"
MODEL_FN = "model.onnx"
LABELS_FN = "class_mapping.json"
IMG = "demo.jpg"
IMG_SIZE = 192

# 拉取文件
model_path = hf_hub_download(REPO_ID, MODEL_FN)
labels_path = hf_hub_download(REPO_ID, LABELS_FN)

# 标签
labels = {"0":"invalid","1":"valid"}
if Path(labels_path).exists():
    labels = json.loads(Path(labels_path).read_text())

# 会话
sess = ort.InferenceSession(model_path, providers=["CPUExecutionProvider"])
in_name, out_name = sess.get_inputs()[0].name, sess.get_outputs()[0].name

# 预处理图像输入
img = ImageOps.exif_transpose(Image.open(IMG)).convert("RGB").resize((IMG_SIZE, IMG_SIZE))
x = (np.asarray(img, np.float32) / 255.0)
x = np.transpose(x, (2,0,1))[None, ...]

# 运行
t0 = time.time()
(logits,) = sess.run([out_name], {in_name: x})
probs = np.exp(logits - logits.max()) / np.exp(logits - logits.max()).sum(-1, keepdims=True)
idx = int(probs.argmax())
print(f"pred={labels.get(str(idx), f'class{idx}')}, probs={probs[0].round(4).tolist()}, {1000*(time.time()-t0):.1f}ms")

演示