feat(ocr,det,slide): 重构项目结构
- 优化 规范化模型目录 - 重构 Ocr,Detector,Slide 拆分规范化
This commit is contained in:
@@ -12,6 +12,8 @@ base64 = "0.22.1"
|
||||
imageproc = { version = "0.26.2", default-features = true }
|
||||
serde = { version = "1.0.228", features = ["derive"] }
|
||||
serde_json = "1.0.150"
|
||||
ndarray="0.16.1"
|
||||
|
||||
|
||||
[features]
|
||||
default = []
|
||||
|
||||
@@ -1,24 +1,33 @@
|
||||
use crate::utils::cv_ops;
|
||||
use crate::utils::cv_ops::{abs_diff, min_max_loc, ndarray_to_luma8, rgb_to_gray};
|
||||
use crate::utils::image_io::image_to_ndarray;
|
||||
use anyhow::{Context, Result, anyhow};
|
||||
use image::{DynamicImage, GenericImageView};
|
||||
use image::{ImageBuffer, Luma};
|
||||
use anyhow::{Result, anyhow};
|
||||
use image::DynamicImage;
|
||||
use image::Luma;
|
||||
use imageproc::contrast::{ThresholdType, threshold};
|
||||
use imageproc::distance_transform::Norm;
|
||||
use imageproc::edges::canny;
|
||||
use imageproc::morphology::{close, open};
|
||||
use imageproc::region_labelling::{Connectivity, connected_components};
|
||||
use imageproc::template_matching::{MatchTemplateMethod, match_template};
|
||||
use std::cmp::{max, min};
|
||||
use tract_onnx::prelude::tract_ndarray::{Array2, Array3, ArrayView2, ArrayView3, Axis, s};
|
||||
|
||||
use std::fmt;
|
||||
use tract_onnx::prelude::tract_ndarray::{ArrayView2, ArrayView3};
|
||||
#[derive(Debug)]
|
||||
pub struct SlideResult {
|
||||
pub target: [i32; 2],
|
||||
pub target_x: i32,
|
||||
pub target_y: i32,
|
||||
pub confidence: f64,
|
||||
}
|
||||
impl fmt::Display for SlideResult {
|
||||
fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
|
||||
writeln!(f, "滑块匹配测试结果:")?;
|
||||
writeln!(f, "检测坐标: [x: {}, y: {}]", self.target_x, self.target_y)?;
|
||||
// 注意:这里保留 4 位小数,如果想让外部控制,也可以直接写 {:.4}
|
||||
write!(f, "置信度: {:.4}", self.confidence)?;
|
||||
Ok(())
|
||||
}
|
||||
}
|
||||
|
||||
pub struct Slider;
|
||||
|
||||
@@ -58,23 +67,8 @@ impl Slider {
|
||||
target: ArrayView3<u8>,
|
||||
background: ArrayView3<u8>,
|
||||
) -> Result<SlideResult> {
|
||||
// let (h, w, _) = target.dim();
|
||||
|
||||
// 1. 计算图像差异并灰度化 (对应 cv2.absdiff + cv2.cvtColor)
|
||||
// 使用 OpenCV 标准权重公式:0.299R + 0.587G + 0.114B
|
||||
// let mut diff_buffer = ImageBuffer::new(w as u32, h as u32);
|
||||
// for y in 0..h {
|
||||
// for x in 0..w {
|
||||
// let r_diff = (target[[y, x, 0]] as i16 - background[[y, x, 0]] as i16).abs() as f32;
|
||||
// let g_diff = (target[[y, x, 1]] as i16 - background[[y, x, 1]] as i16).abs() as f32;
|
||||
// let b_diff = (target[[y, x, 2]] as i16 - background[[y, x, 2]] as i16).abs() as f32;
|
||||
//
|
||||
// let gray_diff = (0.299 * r_diff + 0.587 * g_diff + 0.114 * b_diff) as u8;
|
||||
// diff_buffer.put_pixel(x as u32, y as u32, Luma([gray_diff]));
|
||||
// }
|
||||
// }
|
||||
// 1. 计算差异数组 (复用 cv2::absdiff)
|
||||
|
||||
let (th, tw, tc) = target.dim();
|
||||
let (bh, bw, bc) = background.dim();
|
||||
|
||||
@@ -193,9 +187,6 @@ impl Slider {
|
||||
background: ArrayView2<u8>,
|
||||
) -> Result<SlideResult> {
|
||||
// 1. 将 ndarray 转换为 imageproc 需要的 ImageBuffer (无拷贝或轻量转换)
|
||||
|
||||
// let (bh, bw) = background.dim();
|
||||
|
||||
// 转换逻辑 (假设你已经有方法转回 ImageBuffer)
|
||||
let t_buf = ndarray_to_luma8(target);
|
||||
let b_buf = ndarray_to_luma8(background);
|
||||
|
||||
170
src/lib.rs
170
src/lib.rs
@@ -3,175 +3,7 @@ mod error;
|
||||
pub mod models;
|
||||
pub mod utils;
|
||||
|
||||
|
||||
pub use crate::algo::{SlideResult, Slider};
|
||||
pub use crate::models::det::{DetBuilder, DetSession, DetectionResult, Detector};
|
||||
pub use crate::models::ocr::{Ocr, OcrBuilder, OcrResult, OcrSession};
|
||||
use models::loader::ModelSession;
|
||||
pub use models::ocr::model_metadata::ModelMetadata;
|
||||
|
||||
// pub enum ModelSpec {
|
||||
// /// 默认 OCR (使用内置路径)
|
||||
// OcrModel,
|
||||
// DetModel,
|
||||
// /// 自定义 OCR (路径由用户提供)
|
||||
// CustomOcrModel {
|
||||
// path: String,
|
||||
// model_metadata: ModelMetadata,
|
||||
// },
|
||||
// }
|
||||
// impl ModelSpec {
|
||||
// // 将默认路径定义为内部关联常量
|
||||
// const DEFAULT_OCR_PATH: &'static str = "models/common_sml2h3_f32.onnx";
|
||||
// const DEFAULT_DET_PATH: &'static str = "models/common_det.onnx";
|
||||
// }
|
||||
// pub enum Runtime {
|
||||
// Ocr(Ocr),
|
||||
// Det(Det),
|
||||
// }
|
||||
// impl Runtime {
|
||||
// // 统一获取描述的方法
|
||||
// pub fn desc(&self) -> String {
|
||||
// match self {
|
||||
// Runtime::Ocr(s) => s.desc(), // 调用 Ocr 结构体的方法
|
||||
// Runtime::Det(s) => s.desc(), // 调用 Det 结构体的方法
|
||||
// }
|
||||
// }
|
||||
// }
|
||||
// pub struct DdddOcrBuilder {
|
||||
// mode: ModelSpec,
|
||||
// }
|
||||
//
|
||||
// impl DdddOcrBuilder {
|
||||
// pub fn new() -> Self {
|
||||
// Self {
|
||||
// mode: ModelSpec::OcrModel,
|
||||
// }
|
||||
// }
|
||||
//
|
||||
// /// 切换为检测模式
|
||||
// pub fn det(mut self) -> Self {
|
||||
// self.mode = ModelSpec::DetModel;
|
||||
// self
|
||||
// }
|
||||
//
|
||||
// /// 设置自定义 OCR 路径
|
||||
// pub fn custom_ocr(mut self, path: String, model_metadata: ModelMetadata) -> Self {
|
||||
// // 直接重写枚举,替换掉之前的 Ocr 或 Det
|
||||
// self.mode = ModelSpec::CustomOcrModel {
|
||||
// path,
|
||||
// model_metadata,
|
||||
// };
|
||||
// self
|
||||
// }
|
||||
//
|
||||
// /// 核心初始化逻辑
|
||||
// pub fn build(self) -> Result<DdddOcr> {
|
||||
// let runtime = match self.mode {
|
||||
// ModelSpec::OcrModel => Runtime::Ocr(Ocr::new(
|
||||
// ModelSpec::DEFAULT_OCR_PATH.into(),
|
||||
// ModelMetadata::from_builtin_beta(),
|
||||
// )?),
|
||||
// ModelSpec::DetModel => Runtime::Det(Det::new(ModelSpec::DEFAULT_DET_PATH.into())?),
|
||||
// ModelSpec::CustomOcrModel {
|
||||
// path,
|
||||
// model_metadata,
|
||||
// } => Runtime::Ocr(Ocr::new(path, model_metadata)?),
|
||||
// };
|
||||
//
|
||||
// Ok(DdddOcr { runtime })
|
||||
// }
|
||||
// }
|
||||
//
|
||||
// pub struct DdddOcr {
|
||||
// runtime: Runtime,
|
||||
// }
|
||||
//
|
||||
// impl Display for DdddOcr {
|
||||
// fn fmt(&self, f: &mut Formatter<'_>) -> std::fmt::Result {
|
||||
// write!(f, "DdddOcr(ocr: {})", self.runtime.desc())
|
||||
// }
|
||||
// }
|
||||
//
|
||||
// impl DdddOcr {
|
||||
// pub fn classification(&self, img: &DynamicImage) -> Result<String> {
|
||||
// match &self.runtime {
|
||||
// // Runtime::Ocr(s) => s.predict(img).run(),
|
||||
// // Runtime::Ocr(s) => s.predictor().probability(false).predict(img),
|
||||
// // Runtime::Ocr(s) => {
|
||||
// // let predictor = s.predictor();
|
||||
// // let restricted = predictor.charset_restrict(&CharRestrict::Lowercase);
|
||||
// // let a = restricted.valid_tokens();
|
||||
// // println!("{:?}", a);
|
||||
// // Ok("".to_string())
|
||||
// // }
|
||||
// Runtime::Ocr(s) => {
|
||||
// let res = s.predictor().probability(true).predict(img)?;
|
||||
// println!("{}", res);
|
||||
// Ok(res.to_string())
|
||||
// }
|
||||
// // Runtime::Ocr(s) => s.predictor().charset_restrict(&CharRestrict::Digit).predict(img),
|
||||
// // Runtime::Ocr(s) => s.predictor().color_filter(&ColorPreset::Custom(vec![
|
||||
// // // 错误:下界 (82, 221, 14) 没问题
|
||||
// // // 但上界的 H 通道写成了 240,超过了 180 的法定上限!
|
||||
// // HsvRange::new((82, 221, 14), (240, 203, 82)),
|
||||
// // ])).predict(img),
|
||||
// Runtime::Det(_) => Err(anyhow::anyhow!("当前模型是检测模型,无法执行 OCR")),
|
||||
// }
|
||||
// }
|
||||
// pub fn detection(&self, img: &DynamicImage) -> Result<Vec<DetectionResult>> {
|
||||
// match &self.runtime {
|
||||
// Runtime::Det(s) => s.predict(img),
|
||||
// Runtime::Ocr(_) => Err(anyhow::anyhow!("当前模型是 OCR 模型,无法执行检测")),
|
||||
// }
|
||||
// }
|
||||
// }
|
||||
|
||||
// struct Classification {}
|
||||
// #[derive(Debug)]
|
||||
// struct ClassificationBuilder {
|
||||
// img: DynamicImage,
|
||||
// png_fix: bool,
|
||||
// color_filter_colors: Option<Vec<ColorRange>>,
|
||||
// color_filter_custom_ranges: Option<Vec<ColorRange>>,
|
||||
// }
|
||||
// impl ClassificationBuilder {
|
||||
// pub fn new(img: DynamicImage) -> Self {
|
||||
// ClassificationBuilder {
|
||||
// img,
|
||||
// png_fix: false,
|
||||
// color_filter_colors: None,
|
||||
// color_filter_custom_ranges: None,
|
||||
// }
|
||||
// }
|
||||
// pub fn png_fix(mut self, value: bool) -> Self {
|
||||
// self.png_fix = value;
|
||||
// self
|
||||
// }
|
||||
// pub fn color_filter_colors(mut self, value: Vec<ColorRange>) -> Self {
|
||||
// self.color_filter_colors = Some(value);
|
||||
// self
|
||||
// }
|
||||
// pub fn color_filter_custom_ranges(mut self, value: Vec<ColorRange>) -> Self {
|
||||
// self.color_filter_custom_ranges = Some(value);
|
||||
// self
|
||||
// }
|
||||
// pub fn build(self) -> Classification {
|
||||
// Classification {}
|
||||
// }
|
||||
// }
|
||||
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
#[test]
|
||||
fn test_ctc_decode_indices() {
|
||||
// 模拟一个 DdddOcr 实例(如果 decode 不依赖 ocr,可以设为相关函数)
|
||||
// 这里假设你的 decode_ctc 是公开或内部可访问的
|
||||
let input = vec![1, 1, 0, 1, 2, 2, 0, 2];
|
||||
// 逻辑:[1, 1] -> 1, [0] -> 跳过, [1] -> 1, [2, 2] -> 2, [0] -> 跳过, [2] -> 2
|
||||
// 预期结果索引应该是 [1, 1, 2, 2] 对应的字符
|
||||
// 具体的断言取决于你的 CHARSET_BETA
|
||||
// let result = dddd.ctc_decode_indices(&input);
|
||||
// assert_eq!(result, "AABB");
|
||||
}
|
||||
}
|
||||
pub use models::ocr::metadata::ModelMetadata;
|
||||
|
||||
@@ -1,15 +1,10 @@
|
||||
use crate::models::ocr::model_metadata::ModelMetadata;
|
||||
use crate::models::loader::{ModelLoader, ModelSession, ModelType};
|
||||
use anyhow::{Context, Result, anyhow};
|
||||
use image::{DynamicImage, GenericImageView, imageops::FilterType};
|
||||
use std::path::Path;
|
||||
use tract_onnx::prelude::tract_ndarray::{Array2, Array3, Array4, Axis, prelude::*, s};
|
||||
use tract_onnx::prelude::{Graph, RunnableModel, Tensor, TypedFact, TypedOp, tvec};
|
||||
use anyhow::{Context, Result};
|
||||
use image::{imageops::FilterType, DynamicImage, GenericImageView};
|
||||
use std::fmt;
|
||||
use tract_onnx::prelude::tract_ndarray::{prelude::*, s, Array2, Array3, Array4, Axis};
|
||||
use tract_onnx::prelude::{Tensor};
|
||||
|
||||
const DEFAULT_DET_PATH: &'static str = "common_det.onnx";
|
||||
|
||||
// 预设的提示信息常量
|
||||
use crate::error::MODEL_DOWNLOAD_HELP;
|
||||
use crate::models::det::session::DetSession;
|
||||
|
||||
#[derive(Debug, Clone, Copy)]
|
||||
@@ -22,15 +17,23 @@ pub struct DetectionResult {
|
||||
pub class_id: u32,
|
||||
}
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
impl fmt::Display for DetectionResult {
|
||||
fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
|
||||
// 结构体只管自己这一行怎么显示,不用管外部的索引 [i]
|
||||
write!(
|
||||
f,
|
||||
"x1={}, y1={}, x2={}, y2={}, 分数={:.4}, 类别ID={}",
|
||||
self.x1, self.y1, self.x2, self.y2, self.score, self.class_id
|
||||
)
|
||||
}
|
||||
}
|
||||
|
||||
#[derive(Debug)]
|
||||
pub struct Detector<'a> {
|
||||
pub(crate) session: &'a DetSession,
|
||||
#[allow(dead_code)]
|
||||
pub(crate) use_gpu: bool,
|
||||
#[allow(dead_code)]
|
||||
pub(crate) device_id: u8,
|
||||
}
|
||||
|
||||
|
||||
@@ -1,17 +1,10 @@
|
||||
use anyhow::{anyhow, Context};
|
||||
use image::DynamicImage;
|
||||
use anyhow::Context;
|
||||
use std::io::Cursor;
|
||||
use tract_onnx::onnx;
|
||||
use tract_onnx::prelude::*;
|
||||
// 关键点:直接使用 tract 重导出的 ndarray
|
||||
use crate::utils::image_io::png_rgba_white_preprocess;
|
||||
use crate::utils::image_processor::{convert_to_grayscale, resize_image};
|
||||
use std::collections::HashMap;
|
||||
use std::io::Cursor;
|
||||
use tract_onnx::prelude::tract_ndarray::s;
|
||||
use crate::ModelMetadata;
|
||||
|
||||
/// OCR 模型:包含路径和字符集
|
||||
const DEFAULT_OCR_PATH: &'static str = "common_sml2h3_f32.onnx";
|
||||
|
||||
pub enum ModelType {
|
||||
Ocr,
|
||||
Det,
|
||||
@@ -53,60 +46,3 @@ impl ModelLoader {
|
||||
Ok(Self { session })
|
||||
}
|
||||
}
|
||||
// impl ModelLoader {
|
||||
// pub fn find_model_path(env_var: &str, default_filename: &str) -> Option<std::path::PathBuf> {
|
||||
// // 1. 策略一:优先尝试读取环境变量
|
||||
// if let Ok(env_path) = std::env::var(env_var) {
|
||||
// let path = std::path::PathBuf::from(env_path);
|
||||
// if path.exists() {
|
||||
// return Some(path);
|
||||
// }
|
||||
// }
|
||||
// // 2. 策略二:尝试在当前工作目录寻找
|
||||
// if let Ok(mut path) = std::env::current_dir() {
|
||||
// path.push(default_filename);
|
||||
// if path.exists() {
|
||||
// return Some(path);
|
||||
// }
|
||||
// }
|
||||
//
|
||||
// // 3. 策略三:尝试在当前可执行文件同级目录寻找
|
||||
// if let Ok(mut exe_path) = std::env::current_exe() {
|
||||
// exe_path.pop(); // 弹出可执行文件名,拿到所在的父目录
|
||||
// exe_path.push(default_filename);
|
||||
// if exe_path.exists() {
|
||||
// return Some(exe_path);
|
||||
// }
|
||||
// }
|
||||
// // 4. 所有本地探测策略均落空
|
||||
// None
|
||||
// }
|
||||
// }
|
||||
|
||||
|
||||
|
||||
// pub fn new_default() -> anyhow::Result<Self> {
|
||||
// let metadata = ModelMetadata::from_builtin_beta(); // 绑定自带的 BETA 字符集
|
||||
//
|
||||
// // 1. 策略一:优先尝试读取环境变量
|
||||
// if let Some(path) = ModelLoader::find_model_path("DDDD_OCR_MODEL", DEFAULT_OCR_PATH) {
|
||||
// return Self::new(path, metadata);
|
||||
// }
|
||||
//
|
||||
// // 4. 策略四:开启了 embed-models 特征时的编译期死穴保底
|
||||
// // 如果开启了 feature 但根目录下没有该模型,编译时会在此处直接中断失败
|
||||
//
|
||||
// #[cfg(feature = "embed-models")]
|
||||
// {
|
||||
// let model_bytes = include_bytes!("../models/common_sml2h3_f32.onnx");
|
||||
// // 注意:这里需要你的 InternalOcr 扩展一个 from_bytes 的方法
|
||||
// return Self::model_from_bytes(model_bytes, metadata);
|
||||
//
|
||||
// }
|
||||
//
|
||||
// // 5. 所有策略落空,抛出保姆级错误
|
||||
// #[cfg(not(feature = "embed-models"))]
|
||||
// {
|
||||
// Err(anyhow!(MODEL_DOWNLOAD_HELP))
|
||||
// }
|
||||
// }
|
||||
@@ -1,7 +1,8 @@
|
||||
use crate::models::ocr::charset::TokenFilter;
|
||||
use crate::models::ocr::executor::Ocr;
|
||||
use crate::models::ocr::session::OcrSession;
|
||||
use crate::models::ocr::color_filter::ColorFilter;
|
||||
use crate::models::ocr::token_filter::TokenFilter;
|
||||
|
||||
pub struct OcrBuilder {
|
||||
/// 是否修复PNG格式问题
|
||||
png_fix: bool,
|
||||
|
||||
@@ -1,25 +1,24 @@
|
||||
use std::str::FromStr;
|
||||
use crate::utils::cv_ops::rgb_to_opencv_hsv;
|
||||
use anyhow::anyhow;
|
||||
use image::{DynamicImage, ImageBuffer, Rgb};
|
||||
use crate::utils::cv_ops::rgb_to_opencv_hsv;
|
||||
|
||||
#[derive(Debug, Clone, Copy, PartialEq, Eq, PartialOrd, Ord)]
|
||||
pub struct HsvRange {
|
||||
pub lower: (u8, u8, u8), // (H, S, V)
|
||||
pub upper: (u8, u8, u8), // (H, S, V)
|
||||
}
|
||||
|
||||
use std::str::FromStr;
|
||||
|
||||
/// 核心区间判定辅助函数
|
||||
#[inline(always)]
|
||||
fn is_pixel_matched(ranges: &[HsvRange], h: u8, s: u8, v: u8) -> bool {
|
||||
ranges.iter().any(|range| {
|
||||
h >= range.lower.0 && h <= range.upper.0 &&
|
||||
s >= range.lower.1 && s <= range.upper.1 &&
|
||||
v >= range.lower.2 && v <= range.upper.2
|
||||
h >= range.lower.0
|
||||
&& h <= range.upper.0
|
||||
&& s >= range.lower.1
|
||||
&& s <= range.upper.1
|
||||
&& v >= range.lower.2
|
||||
&& v <= range.upper.2
|
||||
})
|
||||
}
|
||||
pub fn filter_image(image: &DynamicImage, hsv_ranges: &[HsvRange]) -> anyhow::Result<DynamicImage> {
|
||||
pub fn apply_to_image(
|
||||
image: &DynamicImage,
|
||||
hsv_ranges: &[HsvRange],
|
||||
) -> anyhow::Result<DynamicImage> {
|
||||
// 1. 统一转换为连续内存的 RGB8 缓冲区 (对应 Python 的 Image 到 RGB/BGR 数组转换)
|
||||
let rgb_img = image.to_rgb8();
|
||||
let (width, height) = rgb_img.dimensions();
|
||||
@@ -50,6 +49,13 @@ pub fn filter_image(image: &DynamicImage, hsv_ranges: &[HsvRange]) -> anyhow::Re
|
||||
|
||||
Ok(DynamicImage::ImageRgb8(filtered_buffer))
|
||||
}
|
||||
|
||||
#[derive(Debug, Clone, Copy, PartialEq, Eq, PartialOrd, Ord)]
|
||||
pub struct HsvRange {
|
||||
pub lower: (u8, u8, u8), // (H, S, V)
|
||||
pub upper: (u8, u8, u8), // (H, S, V)
|
||||
}
|
||||
|
||||
impl HsvRange {
|
||||
pub const fn new(lower: (u8, u8, u8), upper: (u8, u8, u8)) -> Self {
|
||||
Self { lower, upper }
|
||||
@@ -65,7 +71,8 @@ impl HsvRange {
|
||||
}
|
||||
|
||||
// 2. 校验下界不能大于上界
|
||||
if self.lower.0 > self.upper.0 || self.lower.1 > self.upper.1 || self.lower.2 > self.upper.2 {
|
||||
if self.lower.0 > self.upper.0 || self.lower.1 > self.upper.1 || self.lower.2 > self.upper.2
|
||||
{
|
||||
return Err("HSV范围下界不能大于上界".to_string());
|
||||
}
|
||||
|
||||
@@ -87,25 +94,58 @@ pub enum ColorPreset {
|
||||
Custom(Vec<HsvRange>),
|
||||
}
|
||||
|
||||
impl ColorPreset {
|
||||
impl ColorPreset {
|
||||
/// 纯裸数据定义,没有任何结构体包装,干净利落
|
||||
/// 返回值:(范围数量, 范围数组)
|
||||
/// 完美的零成本抽象:利用常量提升将数据直接打入只读数据段 (.rodata)
|
||||
pub fn matches(&self) -> &[HsvRange] {
|
||||
match self {
|
||||
ColorPreset::Red => &[
|
||||
HsvRange { lower: (0, 50, 50), upper: (10, 255, 255) },
|
||||
HsvRange { lower: (170, 50, 50), upper: (180, 255, 255) },
|
||||
HsvRange {
|
||||
lower: (0, 50, 50),
|
||||
upper: (10, 255, 255),
|
||||
},
|
||||
HsvRange {
|
||||
lower: (170, 50, 50),
|
||||
upper: (180, 255, 255),
|
||||
},
|
||||
],
|
||||
ColorPreset::Blue => &[HsvRange { lower: (100, 50, 50), upper: (130, 255, 255) }],
|
||||
ColorPreset::Green => &[HsvRange { lower: (40, 50, 50), upper: (80, 255, 255) }],
|
||||
ColorPreset::Yellow => &[HsvRange { lower: (20, 50, 50), upper: (40, 255, 255) }],
|
||||
ColorPreset::Orange => &[HsvRange { lower: (10, 50, 50), upper: (20, 255, 255) }],
|
||||
ColorPreset::Purple => &[HsvRange { lower: (130, 50, 50), upper: (170, 255, 255) }],
|
||||
ColorPreset::Cyan => &[HsvRange { lower: (80, 50, 50), upper: (100, 255, 255) }],
|
||||
ColorPreset::Black => &[HsvRange { lower: (0, 0, 0), upper: (180, 255, 50) }],
|
||||
ColorPreset::White => &[HsvRange { lower: (0, 0, 200), upper: (180, 30, 255) }],
|
||||
ColorPreset::Gray => &[HsvRange { lower: (0, 0, 50), upper: (180, 30, 200) }],
|
||||
ColorPreset::Blue => &[HsvRange {
|
||||
lower: (100, 50, 50),
|
||||
upper: (130, 255, 255),
|
||||
}],
|
||||
ColorPreset::Green => &[HsvRange {
|
||||
lower: (40, 50, 50),
|
||||
upper: (80, 255, 255),
|
||||
}],
|
||||
ColorPreset::Yellow => &[HsvRange {
|
||||
lower: (20, 50, 50),
|
||||
upper: (40, 255, 255),
|
||||
}],
|
||||
ColorPreset::Orange => &[HsvRange {
|
||||
lower: (10, 50, 50),
|
||||
upper: (20, 255, 255),
|
||||
}],
|
||||
ColorPreset::Purple => &[HsvRange {
|
||||
lower: (130, 50, 50),
|
||||
upper: (170, 255, 255),
|
||||
}],
|
||||
ColorPreset::Cyan => &[HsvRange {
|
||||
lower: (80, 50, 50),
|
||||
upper: (100, 255, 255),
|
||||
}],
|
||||
ColorPreset::Black => &[HsvRange {
|
||||
lower: (0, 0, 0),
|
||||
upper: (180, 255, 50),
|
||||
}],
|
||||
ColorPreset::White => &[HsvRange {
|
||||
lower: (0, 0, 200),
|
||||
upper: (180, 30, 255),
|
||||
}],
|
||||
ColorPreset::Gray => &[HsvRange {
|
||||
lower: (0, 0, 50),
|
||||
upper: (180, 30, 200),
|
||||
}],
|
||||
ColorPreset::Custom(ranges) => ranges,
|
||||
}
|
||||
}
|
||||
@@ -204,7 +244,6 @@ impl ColorFilter for ColorPreset {
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
/// 多路颜色“或”逻辑组合子(并集网络)
|
||||
pub struct MultiOrColorRestrict<'a> {
|
||||
pub filters: Vec<&'a dyn ColorFilter>,
|
||||
@@ -246,4 +285,3 @@ macro_rules! color_any_of {
|
||||
}
|
||||
};
|
||||
}
|
||||
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
use crate::models::ocr::model_metadata::Resize;
|
||||
use crate::models::ocr::metadata::Resize;
|
||||
|
||||
use crate::models::ocr::session::OcrSession;
|
||||
use crate::models::ocr::color_filter::{HsvRange, filter_image};
|
||||
use crate::models::ocr::color_filter::{HsvRange, apply_to_image};
|
||||
use crate::utils::image_io::png_rgba_white_preprocess;
|
||||
use crate::utils::image_processor::{convert_to_grayscale, resize_image};
|
||||
use anyhow::Result;
|
||||
@@ -141,7 +141,7 @@ impl<'a> Ocr<'a> {
|
||||
}
|
||||
Ok(Some(ranges)) => {
|
||||
// 只有真正需要过滤时,才在内部提取像素并生成清洗后的 Owned 新图
|
||||
let filtered_img = filter_image(image, ranges)?;
|
||||
let filtered_img = apply_to_image(image, ranges)?;
|
||||
Cow::Owned(filtered_img)
|
||||
}
|
||||
};
|
||||
|
||||
@@ -1,11 +1,72 @@
|
||||
use crate::models::ocr::charset::{CHARSET_BETA, CHARSET_OLD, Charset};
|
||||
use anyhow::{Result, anyhow};
|
||||
use anyhow::{anyhow, Result};
|
||||
use serde::Deserialize;
|
||||
use std::borrow::Cow;
|
||||
use std::collections::{HashMap, HashSet};
|
||||
use std::fs::File;
|
||||
use std::io::Read;
|
||||
use std::path::Path;
|
||||
use std::collections::HashMap;
|
||||
|
||||
// ==========================================
|
||||
// 3. 字符集核心结构体 (重命名为 Charset)
|
||||
// ==========================================
|
||||
#[derive(Debug, Clone)]
|
||||
pub struct Charset {
|
||||
// 使用 Cow 统一静态切片和动态读取的 Vec<String>,内部实现真正的零拷贝
|
||||
pub tokens: Vec<Cow<'static, str>>,
|
||||
// 反向查找表,保证字符转索引为 O(1)
|
||||
pub char_to_idx: HashMap<Cow<'static, str>, usize>,
|
||||
// 当前处于激活状态的有效索引缓存 (用于 CTC 解码前的过滤加速)
|
||||
// pub valid_indices: HashSet<usize>,
|
||||
}
|
||||
|
||||
impl Charset {
|
||||
// 内部底层统一收拢构造
|
||||
pub fn new(tokens: Vec<Cow<'static, str>>) -> Self {
|
||||
let mut char_to_idx = HashMap::with_capacity(tokens.len());
|
||||
for (idx, token) in tokens.iter().enumerate() {
|
||||
char_to_idx.entry(token.clone()).or_insert(idx);
|
||||
// 如果字符集有重复,保留第一个遇到的索引 (符合 Python .index 逻辑)
|
||||
// char_to_idx.entry(token.to_string()).or_insert(idx);
|
||||
}
|
||||
|
||||
Self {
|
||||
tokens,
|
||||
char_to_idx,
|
||||
}
|
||||
}
|
||||
|
||||
// --- 业务策略方法 ---
|
||||
|
||||
/// 将字符转为索引,不存在返回 -1 (保持与原 Python 库行为一致)
|
||||
pub fn char_to_index(&self, char_str: &str) -> i32 {
|
||||
if let Some(&idx) = self.char_to_idx.get(char_str) {
|
||||
idx as i32
|
||||
} else {
|
||||
-1
|
||||
}
|
||||
}
|
||||
|
||||
/// 将索引转为字符引用,零拷贝。若越界返回 None
|
||||
pub fn index_to_char_ref(&self, index: usize) -> Option<&str> {
|
||||
self.tokens.get(index).map(|cow| cow.as_ref())
|
||||
}
|
||||
|
||||
pub fn is_valid_char(&self, char_str: &str) -> bool {
|
||||
self.char_to_idx.get(char_str).is_some()
|
||||
}
|
||||
pub fn size(&self) -> usize {
|
||||
self.tokens.len()
|
||||
}
|
||||
}
|
||||
|
||||
// ==========================================
|
||||
// 4. 标准 Display 接口实现 (对应 __str__)
|
||||
// ==========================================
|
||||
impl std::fmt::Display for Charset {
|
||||
fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
|
||||
write!(f, "Charset [Total Size: {}", self.size(),)
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
|
||||
// =====================================================================
|
||||
// 1. 辅助定义的枚举与结构体
|
||||
// =====================================================================
|
||||
@@ -74,28 +135,6 @@ pub struct ModelMetadata {
|
||||
|
||||
impl ModelMetadata {
|
||||
// --- 优雅的工厂模式构造器 ---
|
||||
/// 从预设的旧版字符集创建
|
||||
pub fn from_builtin_old() -> Self {
|
||||
Self::from_static_slice(
|
||||
CHARSET_OLD,
|
||||
false,
|
||||
Resize::DynamicWidth(64),
|
||||
1,
|
||||
Normalization::ZeroToOne,
|
||||
)
|
||||
}
|
||||
|
||||
/// 从预设的 Beta 版字符集创建
|
||||
pub fn from_builtin_beta() -> Self {
|
||||
Self::from_static_slice(
|
||||
CHARSET_BETA,
|
||||
false,
|
||||
Resize::DynamicWidth(64),
|
||||
1,
|
||||
Normalization::MinusOneToOne,
|
||||
)
|
||||
}
|
||||
|
||||
/// 通用的静态切片转换构造器
|
||||
pub fn from_static_slice(
|
||||
slice: &[&'static str],
|
||||
@@ -158,54 +197,4 @@ impl ModelMetadata {
|
||||
.map_err(|e| anyhow!("JSON 字节流不是合法的 UTF-8 编码: {}", e))?;
|
||||
Self::from_json_str(json_str)
|
||||
}
|
||||
|
||||
/// 从外部外部 JSON 文件动态加载字符集(在后续优化中移除)
|
||||
pub fn from_json_file<P: AsRef<Path>>(path: P) -> Result<Self> {
|
||||
let path = path.as_ref();
|
||||
if !path.exists() {
|
||||
return Err(anyhow!("模型元数据配置文件不存在: {:?}", path));
|
||||
}
|
||||
|
||||
let mut file = File::open(path)?;
|
||||
let mut content = String::new();
|
||||
file.read_to_string(&mut content)?;
|
||||
|
||||
let dto: ModelMetadataDto = serde_json::from_str(&content)
|
||||
.map_err(|e| anyhow!("JSON 反序列化失败,请检查字段是否完整: {}", e))?;
|
||||
|
||||
// 1. 将 DTO 的字符串数组转化为强类型的 Charset
|
||||
let tokens: Vec<Cow<'static, str>> =
|
||||
dto.charset.into_iter().map(|s| Cow::Owned(s)).collect();
|
||||
let charset = Charset::new(tokens);
|
||||
|
||||
// 2. 解析 resize 策略(重现 Python 的复杂条件判断)
|
||||
if dto.resize.len() != 2 {
|
||||
return Err(anyhow!(
|
||||
"'resize (or image)' 字段必须是包含两个元素的数组,例如 [-1, 64]"
|
||||
));
|
||||
}
|
||||
let r0 = dto.resize[0];
|
||||
let r1 = dto.resize[1];
|
||||
|
||||
let resize = if r0 == -1 {
|
||||
if dto.word {
|
||||
// 如果 word 为 true,且包含 -1,Python 里是 resize 为 (r1, r1) 的正方形
|
||||
Resize::Square(r1 as u32)
|
||||
} else {
|
||||
// 如果 word 为 false,且包含 -1,Python 里是高度固定为 r1,宽度按原图比例缩放
|
||||
Resize::DynamicWidth(r1 as u32)
|
||||
}
|
||||
} else {
|
||||
// 正常的固定宽高
|
||||
Resize::Fixed(r0 as u32, r1 as u32)
|
||||
};
|
||||
|
||||
Ok(Self {
|
||||
charset,
|
||||
word: dto.word,
|
||||
resize,
|
||||
channel: dto.channel,
|
||||
normalization: dto.normalization,
|
||||
})
|
||||
}
|
||||
}
|
||||
@@ -1,9 +1,9 @@
|
||||
mod builder;
|
||||
mod executor;
|
||||
mod session;
|
||||
pub mod charset;
|
||||
pub mod model_metadata;
|
||||
pub mod metadata;
|
||||
pub mod color_filter;
|
||||
mod token_filter;
|
||||
|
||||
pub use builder::OcrBuilder;
|
||||
pub use executor::{Ocr, OcrResult};
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
use crate::models::ocr::model_metadata::ModelMetadata;
|
||||
use crate::models::ocr::metadata::ModelMetadata;
|
||||
use crate::models::loader::{ModelLoader, ModelSession, ModelType};
|
||||
use anyhow::Context;
|
||||
use anyhow::Result;
|
||||
|
||||
146
src/models/ocr/token_filter.rs
Normal file
146
src/models/ocr/token_filter.rs
Normal file
@@ -0,0 +1,146 @@
|
||||
use std::borrow::Cow;
|
||||
|
||||
/// 字符集范围限制枚举
|
||||
pub struct ValidationCtx<'a> {
|
||||
pub text: &'a str, // 当前 Token 的文本内容
|
||||
pub token_id: usize, // 当前 Token 的 ID 索引
|
||||
}
|
||||
|
||||
/// 统一的约束接口
|
||||
pub trait TokenFilter {
|
||||
fn matches(&self, ctx: &ValidationCtx) -> bool;
|
||||
/// 预估容量提示,帮助精准开辟 Vec 内存
|
||||
fn estimated_capacity(&self) -> usize {
|
||||
128
|
||||
}
|
||||
/// 【新引入的架构级核心方法】
|
||||
/// 统一接管全量字符集的密集遍历、CTC Blank放行、去重、排序及空交集退化兜底
|
||||
fn apply_to_charset(&self, tokens: &[Cow<str>]) -> Option<Vec<usize>> {
|
||||
let mut has_any_match = false;
|
||||
let estimated_capacity = self.estimated_capacity();
|
||||
|
||||
// 1. 精准开辟内存,完美利用容量提示,避免动态乱涨
|
||||
let mut temp_indices = Vec::with_capacity(estimated_capacity.max(16));
|
||||
|
||||
// 2. 高性能原地单次流式迭代
|
||||
for (idx, token) in tokens.iter().enumerate() {
|
||||
let token_str = token.as_ref();
|
||||
|
||||
// 规则 A: CTC Blank 空字符串或 0 号索引无条件放行
|
||||
if token_str.is_empty() || idx == 0 {
|
||||
temp_indices.push(idx);
|
||||
continue; // 关键:直接跳过,防止后续 matches 匹配成功导致重复 push 产生 Bug
|
||||
}
|
||||
|
||||
// 规则 B: 组装无拷贝上下文
|
||||
let ctx = ValidationCtx {
|
||||
text: token_str,
|
||||
token_id: idx,
|
||||
};
|
||||
|
||||
// 规则 C: 路由到各自具体实现的特异性匹配中(如 Digit 判定、TopN 判定、组合子判定等)
|
||||
if self.matches(&ctx) {
|
||||
temp_indices.push(idx);
|
||||
has_any_match = true;
|
||||
}
|
||||
}
|
||||
|
||||
// 3. 终极防御:如果整个模型字符集除了 Blank,一个都没对上,直接退化为 None(全量识别)
|
||||
if !has_any_match {
|
||||
println!("警告:当前限制策略与模型字符集完全没有交集!已自动恢复全量识别。");
|
||||
None
|
||||
} else {
|
||||
// 4. 排序并去重,为 Ocr 引擎后续进行极其高频的『二分查找』筑起绝对安全的底层保障
|
||||
temp_indices.sort_unstable();
|
||||
temp_indices.dedup();
|
||||
Some(temp_indices)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
#[derive(Debug, Clone, PartialEq, Eq)]
|
||||
pub enum CharRestrict {
|
||||
Digit,
|
||||
Lowercase,
|
||||
Uppercase,
|
||||
CustomList(Vec<String>),
|
||||
}
|
||||
|
||||
impl TokenFilter for CharRestrict {
|
||||
fn matches(&self, ctx: &ValidationCtx) -> bool {
|
||||
match self {
|
||||
Self::Digit => ctx.text.len() == 1 && ctx.text.as_bytes()[0].is_ascii_digit(),
|
||||
Self::Lowercase => ctx.text.len() == 1 && ctx.text.as_bytes()[0].is_ascii_lowercase(),
|
||||
Self::Uppercase => ctx.text.len() == 1 && ctx.text.as_bytes()[0].is_ascii_uppercase(),
|
||||
Self::CustomList(vec) => vec.iter().any(|t| t == ctx.text),
|
||||
}
|
||||
}
|
||||
fn estimated_capacity(&self) -> usize {
|
||||
match self {
|
||||
Self::Digit => 16,
|
||||
Self::Lowercase | Self::Uppercase => 32,
|
||||
Self::CustomList(vec) => vec.len() + 1,
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
#[derive(Debug, Clone, PartialEq, Eq)]
|
||||
pub enum IdRestrict {
|
||||
TopN(usize),
|
||||
IdRange(std::ops::Range<usize>),
|
||||
IdList(Vec<usize>),
|
||||
}
|
||||
|
||||
impl TokenFilter for IdRestrict {
|
||||
fn matches(&self, ctx: &ValidationCtx) -> bool {
|
||||
match self {
|
||||
Self::TopN(n) => ctx.token_id < *n,
|
||||
Self::IdRange(range) => range.contains(&ctx.token_id),
|
||||
Self::IdList(vec) => vec.contains(&ctx.token_id),
|
||||
}
|
||||
}
|
||||
fn estimated_capacity(&self) -> usize {
|
||||
match self {
|
||||
Self::TopN(n) => *n + 1,
|
||||
// 2. IdRange:标准标准库 Range 的长度
|
||||
// 注意:因为范围可能是 1000..2000,它的 len() 返回的是 usize
|
||||
Self::IdRange(range) => range.len() + 1,
|
||||
// 3. IdList:Vec 里的元素个数
|
||||
Self::IdList(vec) => vec.len() + 1,
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/// 多路“或”逻辑组合子(支持 N 个规则无缝并集)
|
||||
pub struct MultiOrRestrict<'a> {
|
||||
pub filters: Vec<&'a dyn TokenFilter>,
|
||||
}
|
||||
|
||||
impl<'a> TokenFilter for MultiOrRestrict<'a> {
|
||||
fn matches(&self, ctx: &ValidationCtx) -> bool {
|
||||
// 核心高阶函数:只要有一个过滤器命中,该 Token 即可放行
|
||||
self.filters.iter().any(|f| f.matches(ctx))
|
||||
}
|
||||
|
||||
fn estimated_capacity(&self) -> usize {
|
||||
// 将所有过滤器的预估容量累加,作为最终容量参考
|
||||
self.filters.iter().map(|f| f.estimated_capacity()).sum()
|
||||
}
|
||||
}
|
||||
// =====================================================================
|
||||
// 声明式宏:替代 `+` 运算符,解决组合扩展痛苦
|
||||
// =====================================================================
|
||||
#[macro_export]
|
||||
macro_rules! any_of {
|
||||
// 场景 A:如果用户只传了一个规则,免去构建 Vec 的开销,直接返回其引用
|
||||
($only:expr) => {
|
||||
&$only as &dyn $crate::TokenFilter
|
||||
};
|
||||
|
||||
// 场景 B:如果用户传入了多个规则,自动织成一张静态组合网
|
||||
($($filter:expr),+ $(,)?) => {
|
||||
&$crate::MultiOrRestrict {
|
||||
filters: vec![ $( &$filter as &dyn $crate::TokenFilter ),+ ]
|
||||
}
|
||||
};
|
||||
}
|
||||
@@ -1,5 +1,7 @@
|
||||
use image::{DynamicImage, GrayImage, imageops::FilterType};
|
||||
use anyhow::Result;
|
||||
use image::{DynamicImage, GrayImage, imageops::FilterType, Rgb, ImageBuffer};
|
||||
use anyhow::{anyhow, Result};
|
||||
use crate::models::ocr::color_filter::HsvRange;
|
||||
use crate::utils::cv_ops::rgb_to_opencv_hsv;
|
||||
|
||||
/// 对应 Python 的 convert_to_grayscale
|
||||
/// 将图像转换为灰度图 (L模式)
|
||||
@@ -34,4 +36,5 @@ pub fn resize_image(
|
||||
// target_height,
|
||||
// FilterType::Lanczos3
|
||||
// )
|
||||
// }
|
||||
// }
|
||||
|
||||
|
||||
@@ -1,3 +1,10 @@
|
||||
use std::borrow::Cow;
|
||||
use std::fs::File;
|
||||
use std::path::Path;
|
||||
use anyhow::anyhow;
|
||||
use ddddocr_rs::models::ocr::metadata::Charset;
|
||||
use ddddocr_rs::models::ocr::metadata::{Normalization, Resize};
|
||||
|
||||
pub const CHARSET_BETA: &[&str] = &[
|
||||
"", "笤", "谴", "膀", "荔", "佰", "电", "臁", "矍", "同", "奇", "芄", "吠", "6", "曛", "荇",
|
||||
"砥", "蹅", "晃", "厄", "殣", "c", "辱", "钋", "杻", "價", "眙", "鴿", "⒄", "裙", "训", "涛",
|
||||
@@ -517,212 +524,77 @@ pub const CHARSET_BETA: &[&str] = &[
|
||||
|
||||
pub const CHARSET_OLD: &[&str] = &["", "笤", "谴", "膀", "荔"];
|
||||
|
||||
use std::borrow::Cow;
|
||||
use std::collections::{HashMap, HashSet};
|
||||
|
||||
/// 字符集范围限制枚举
|
||||
pub struct ValidationCtx<'a> {
|
||||
pub text: &'a str, // 当前 Token 的文本内容
|
||||
pub token_id: usize, // 当前 Token 的 ID 索引
|
||||
}
|
||||
|
||||
/// 统一的约束接口
|
||||
pub trait TokenFilter {
|
||||
fn matches(&self, ctx: &ValidationCtx) -> bool;
|
||||
/// 预估容量提示,帮助精准开辟 Vec 内存
|
||||
fn estimated_capacity(&self) -> usize {
|
||||
128
|
||||
}
|
||||
/// 【新引入的架构级核心方法】
|
||||
/// 统一接管全量字符集的密集遍历、CTC Blank放行、去重、排序及空交集退化兜底
|
||||
fn apply_to_charset(&self, tokens: &[Cow<str>]) -> Option<Vec<usize>> {
|
||||
let mut has_any_match = false;
|
||||
let estimated_capacity = self.estimated_capacity();
|
||||
|
||||
// 1. 精准开辟内存,完美利用容量提示,避免动态乱涨
|
||||
let mut temp_indices = Vec::with_capacity(estimated_capacity.max(16));
|
||||
// pub fn from_builtin_old() -> Self {
|
||||
// Self::from_static_slice(
|
||||
// CHARSET_OLD,
|
||||
// false,
|
||||
// Resize::DynamicWidth(64),
|
||||
// 1,
|
||||
// Normalization::ZeroToOne,
|
||||
// )
|
||||
// }
|
||||
//
|
||||
// /// 从预设的 Beta 版字符集创建
|
||||
// pub fn from_builtin_beta() -> Self {
|
||||
// Self::from_static_slice(
|
||||
// CHARSET_BETA,
|
||||
// false,
|
||||
// Resize::DynamicWidth(64),
|
||||
// 1,
|
||||
// Normalization::MinusOneToOne,
|
||||
// )
|
||||
// }
|
||||
|
||||
// 2. 高性能原地单次流式迭代
|
||||
for (idx, token) in tokens.iter().enumerate() {
|
||||
let token_str = token.as_ref();
|
||||
|
||||
// 规则 A: CTC Blank 空字符串或 0 号索引无条件放行
|
||||
if token_str.is_empty() || idx == 0 {
|
||||
temp_indices.push(idx);
|
||||
continue; // 关键:直接跳过,防止后续 matches 匹配成功导致重复 push 产生 Bug
|
||||
}
|
||||
|
||||
// 规则 B: 组装无拷贝上下文
|
||||
let ctx = ValidationCtx {
|
||||
text: token_str,
|
||||
token_id: idx,
|
||||
};
|
||||
|
||||
// 规则 C: 路由到各自具体实现的特异性匹配中(如 Digit 判定、TopN 判定、组合子判定等)
|
||||
if self.matches(&ctx) {
|
||||
temp_indices.push(idx);
|
||||
has_any_match = true;
|
||||
}
|
||||
}
|
||||
|
||||
// 3. 终极防御:如果整个模型字符集除了 Blank,一个都没对上,直接退化为 None(全量识别)
|
||||
if !has_any_match {
|
||||
println!("警告:当前限制策略与模型字符集完全没有交集!已自动恢复全量识别。");
|
||||
None
|
||||
} else {
|
||||
// 4. 排序并去重,为 Ocr 引擎后续进行极其高频的『二分查找』筑起绝对安全的底层保障
|
||||
temp_indices.sort_unstable();
|
||||
temp_indices.dedup();
|
||||
Some(temp_indices)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
#[derive(Debug, Clone, PartialEq, Eq)]
|
||||
pub enum CharRestrict {
|
||||
Digit,
|
||||
Lowercase,
|
||||
Uppercase,
|
||||
CustomList(Vec<String>),
|
||||
}
|
||||
|
||||
impl TokenFilter for CharRestrict {
|
||||
fn matches(&self, ctx: &ValidationCtx) -> bool {
|
||||
match self {
|
||||
Self::Digit => ctx.text.len() == 1 && ctx.text.as_bytes()[0].is_ascii_digit(),
|
||||
Self::Lowercase => ctx.text.len() == 1 && ctx.text.as_bytes()[0].is_ascii_lowercase(),
|
||||
Self::Uppercase => ctx.text.len() == 1 && ctx.text.as_bytes()[0].is_ascii_uppercase(),
|
||||
Self::CustomList(vec) => vec.iter().any(|t| t == ctx.text),
|
||||
}
|
||||
}
|
||||
fn estimated_capacity(&self) -> usize {
|
||||
match self {
|
||||
Self::Digit => 16,
|
||||
Self::Lowercase | Self::Uppercase => 32,
|
||||
Self::CustomList(vec) => vec.len() + 1,
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
#[derive(Debug, Clone, PartialEq, Eq)]
|
||||
pub enum IdRestrict {
|
||||
TopN(usize),
|
||||
IdRange(std::ops::Range<usize>),
|
||||
IdList(Vec<usize>),
|
||||
}
|
||||
|
||||
impl TokenFilter for IdRestrict {
|
||||
fn matches(&self, ctx: &ValidationCtx) -> bool {
|
||||
match self {
|
||||
Self::TopN(n) => ctx.token_id < *n,
|
||||
Self::IdRange(range) => range.contains(&ctx.token_id),
|
||||
Self::IdList(vec) => vec.contains(&ctx.token_id),
|
||||
}
|
||||
}
|
||||
fn estimated_capacity(&self) -> usize {
|
||||
match self {
|
||||
Self::TopN(n) => *n + 1,
|
||||
// 2. IdRange:标准标准库 Range 的长度
|
||||
// 注意:因为范围可能是 1000..2000,它的 len() 返回的是 usize
|
||||
Self::IdRange(range) => range.len() + 1,
|
||||
// 3. IdList:Vec 里的元素个数
|
||||
Self::IdList(vec) => vec.len() + 1,
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/// 多路“或”逻辑组合子(支持 N 个规则无缝并集)
|
||||
pub struct MultiOrRestrict<'a> {
|
||||
pub filters: Vec<&'a dyn TokenFilter>,
|
||||
}
|
||||
|
||||
impl<'a> TokenFilter for MultiOrRestrict<'a> {
|
||||
fn matches(&self, ctx: &ValidationCtx) -> bool {
|
||||
// 核心高阶函数:只要有一个过滤器命中,该 Token 即可放行
|
||||
self.filters.iter().any(|f| f.matches(ctx))
|
||||
}
|
||||
|
||||
fn estimated_capacity(&self) -> usize {
|
||||
// 将所有过滤器的预估容量累加,作为最终容量参考
|
||||
self.filters.iter().map(|f| f.estimated_capacity()).sum()
|
||||
}
|
||||
}
|
||||
// =====================================================================
|
||||
// 声明式宏:替代 `+` 运算符,解决组合扩展痛苦
|
||||
// =====================================================================
|
||||
#[macro_export]
|
||||
macro_rules! any_of {
|
||||
// 场景 A:如果用户只传了一个规则,免去构建 Vec 的开销,直接返回其引用
|
||||
($only:expr) => {
|
||||
&$only as &dyn $crate::TokenFilter
|
||||
};
|
||||
|
||||
// 场景 B:如果用户传入了多个规则,自动织成一张静态组合网
|
||||
($($filter:expr),+ $(,)?) => {
|
||||
&$crate::MultiOrRestrict {
|
||||
filters: vec![ $( &$filter as &dyn $crate::TokenFilter ),+ ]
|
||||
}
|
||||
};
|
||||
}
|
||||
|
||||
// ==========================================
|
||||
// 3. 字符集核心结构体 (重命名为 Charset)
|
||||
// ==========================================
|
||||
#[derive(Debug, Clone)]
|
||||
pub struct Charset {
|
||||
// 使用 Cow 统一静态切片和动态读取的 Vec<String>,内部实现真正的零拷贝
|
||||
pub tokens: Vec<Cow<'static, str>>,
|
||||
// 反向查找表,保证字符转索引为 O(1)
|
||||
pub char_to_idx: HashMap<Cow<'static, str>, usize>,
|
||||
// 当前处于激活状态的有效索引缓存 (用于 CTC 解码前的过滤加速)
|
||||
// pub valid_indices: HashSet<usize>,
|
||||
}
|
||||
|
||||
impl Charset {
|
||||
// 内部底层统一收拢构造
|
||||
pub fn new(tokens: Vec<Cow<'static, str>>) -> Self {
|
||||
let mut char_to_idx = HashMap::with_capacity(tokens.len());
|
||||
for (idx, token) in tokens.iter().enumerate() {
|
||||
char_to_idx.entry(token.clone()).or_insert(idx);
|
||||
// 如果字符集有重复,保留第一个遇到的索引 (符合 Python .index 逻辑)
|
||||
// char_to_idx.entry(token.to_string()).or_insert(idx);
|
||||
}
|
||||
|
||||
Self {
|
||||
tokens,
|
||||
char_to_idx,
|
||||
}
|
||||
}
|
||||
|
||||
// --- 业务策略方法 ---
|
||||
|
||||
/// 将字符转为索引,不存在返回 -1 (保持与原 Python 库行为一致)
|
||||
pub fn char_to_index(&self, char_str: &str) -> i32 {
|
||||
if let Some(&idx) = self.char_to_idx.get(char_str) {
|
||||
idx as i32
|
||||
} else {
|
||||
-1
|
||||
}
|
||||
}
|
||||
|
||||
/// 将索引转为字符引用,零拷贝。若越界返回 None
|
||||
pub fn index_to_char_ref(&self, index: usize) -> Option<&str> {
|
||||
self.tokens.get(index).map(|cow| cow.as_ref())
|
||||
}
|
||||
|
||||
pub fn is_valid_char(&self, char_str: &str) -> bool {
|
||||
self.char_to_idx.get(char_str).is_some()
|
||||
}
|
||||
pub fn size(&self) -> usize {
|
||||
self.tokens.len()
|
||||
}
|
||||
}
|
||||
|
||||
// ==========================================
|
||||
// 4. 标准 Display 接口实现 (对应 __str__)
|
||||
// ==========================================
|
||||
impl std::fmt::Display for Charset {
|
||||
fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
|
||||
write!(f, "Charset [Total Size: {}", self.size(),)
|
||||
}
|
||||
}
|
||||
// /// 从外部外部 JSON 文件动态加载字符集(在后续优化中移除)
|
||||
// pub fn from_json_file<P: AsRef<Path>>(path: P) -> anyhow::Result<Self> {
|
||||
// let path = path.as_ref();
|
||||
// if !path.exists() {
|
||||
// return Err(anyhow!("模型元数据配置文件不存在: {:?}", path));
|
||||
// }
|
||||
//
|
||||
// let mut file = File::open(path)?;
|
||||
// let mut content = String::new();
|
||||
// file.read_to_string(&mut content)?;
|
||||
//
|
||||
// let dto: ModelMetadataDto = serde_json::from_str(&content)
|
||||
// .map_err(|e| anyhow!("JSON 反序列化失败,请检查字段是否完整: {}", e))?;
|
||||
//
|
||||
// // 1. 将 DTO 的字符串数组转化为强类型的 Charset
|
||||
// let tokens: Vec<Cow<'static, str>> =
|
||||
// dto.charset.into_iter().map(|s| Cow::Owned(s)).collect();
|
||||
// let charset = Charset::new(tokens);
|
||||
//
|
||||
// // 2. 解析 resize 策略(重现 Python 的复杂条件判断)
|
||||
// if dto.resize.len() != 2 {
|
||||
// return Err(anyhow!(
|
||||
// "'resize (or image)' 字段必须是包含两个元素的数组,例如 [-1, 64]"
|
||||
// ));
|
||||
// }
|
||||
// let r0 = dto.resize[0];
|
||||
// let r1 = dto.resize[1];
|
||||
//
|
||||
// let resize = if r0 == -1 {
|
||||
// if dto.word {
|
||||
// // 如果 word 为 true,且包含 -1,Python 里是 resize 为 (r1, r1) 的正方形
|
||||
// Resize::Square(r1 as u32)
|
||||
// } else {
|
||||
// // 如果 word 为 false,且包含 -1,Python 里是高度固定为 r1,宽度按原图比例缩放
|
||||
// Resize::DynamicWidth(r1 as u32)
|
||||
// }
|
||||
// } else {
|
||||
// // 正常的固定宽高
|
||||
// Resize::Fixed(r0 as u32, r1 as u32)
|
||||
// };
|
||||
//
|
||||
// Ok(Self {
|
||||
// charset,
|
||||
// word: dto.word,
|
||||
// resize,
|
||||
// channel: dto.channel,
|
||||
// normalization: dto.normalization,
|
||||
// })
|
||||
// }
|
||||
@@ -1,8 +1,11 @@
|
||||
use ddddocr_rs::{Ocr, Slider, Detector, ModelMetadata, OcrSession, DetBuilder, DetSession}; // 假设你的包名是这个
|
||||
use ddddocr_rs::models::det::DetectionResult;
|
||||
use ddddocr_rs::{DetBuilder, DetSession, Detector, ModelMetadata, Ocr, OcrSession, Slider}; // 假设你的包名是这个
|
||||
use image::{DynamicImage, Rgb};
|
||||
use std::fs;
|
||||
use std::path::Path;
|
||||
use ddddocr_rs::models::det::DetectionResult;
|
||||
mod char_slice;
|
||||
use char_slice::CHARSET_BETA;
|
||||
use ddddocr_rs::models::ocr::metadata::{Normalization, Resize};
|
||||
|
||||
fn load_image<P: AsRef<Path>>(path: P) -> anyhow::Result<image::DynamicImage> {
|
||||
// 1. 先将泛型转为具体的 &Path 引用
|
||||
@@ -16,8 +19,8 @@ fn load_image<P: AsRef<Path>>(path: P) -> anyhow::Result<image::DynamicImage> {
|
||||
}
|
||||
/// 将检测结果绘制在图像上并保存
|
||||
fn save_debug_image(
|
||||
dynamic_img: &DynamicImage, // 【优化点 1】直接传入解码好的引用,拒绝重复解码
|
||||
bboxes: &[DetectionResult], // 【修改点 1】类型改为自定义结构体切片
|
||||
dynamic_img: &DynamicImage, // 【优化点 1】直接传入解码好的引用,拒绝重复解码
|
||||
bboxes: &[DetectionResult], // 【修改点 1】类型改为自定义结构体切片
|
||||
output_path: &str,
|
||||
) -> anyhow::Result<()> {
|
||||
// 删除了原本的 let dynamic_img = image::load_from_memory(image_bytes)?;
|
||||
@@ -60,17 +63,29 @@ fn save_debug_image(
|
||||
Ok(())
|
||||
}
|
||||
|
||||
|
||||
#[test]
|
||||
fn test_full_classification() {
|
||||
// 1. 初始化模型
|
||||
let ocr = OcrSession::new("D:\\CNWei\\CNW\\Rust\\ddddocr-rs\\models\\common_sml2h3_f32.onnx",ModelMetadata::from_builtin_beta()).expect("模型加载失败");
|
||||
let ocr = OcrSession::new(
|
||||
"D:\\CNWei\\CNW\\Rust\\ddddocr-rs\\models\\common_sml2h3_f32.onnx",
|
||||
ModelMetadata::from_static_slice(
|
||||
CHARSET_BETA,
|
||||
false,
|
||||
Resize::DynamicWidth(64),
|
||||
1,
|
||||
Normalization::MinusOneToOne,
|
||||
),
|
||||
)
|
||||
.expect("模型加载失败");
|
||||
|
||||
// 2. 加载测试图片
|
||||
let img = image::open("samples/code2.png").expect("测试图片不存在");
|
||||
|
||||
// 3. 执行识别
|
||||
let result = Ocr::new(&ocr).predict(&img).expect("识别过程出错").into_text();
|
||||
let result = Ocr::new(&ocr)
|
||||
.predict(&img)
|
||||
.expect("识别过程出错")
|
||||
.into_text();
|
||||
|
||||
println!("识别结果: {}", result);
|
||||
assert!(!result.is_empty());
|
||||
@@ -101,10 +116,7 @@ fn test_det_load() -> anyhow::Result<()> {
|
||||
|
||||
for (i, bbox) in bboxes.iter().enumerate() {
|
||||
// 【修改点 3】将原来的 bbox[0].. 索引访问改为结构体字段访问
|
||||
println!(
|
||||
"目标 [{}]: x1={}, y1={}, x2={}, y2={}, 分数={:.4}, 类别ID={}",
|
||||
i, bbox.x1, bbox.y1, bbox.x2, bbox.y2, bbox.score, bbox.class_id
|
||||
);
|
||||
println!("目标 [{}]: {}", i, bbox);
|
||||
}
|
||||
}
|
||||
Ok(())
|
||||
@@ -129,9 +141,7 @@ fn test_real_slide_match() {
|
||||
|
||||
// 3. 打印结果
|
||||
println!("-------------------------------------------");
|
||||
println!("滑块匹配测试结果:");
|
||||
println!("检测坐标: [x: {}, y: {}]", result.target_x, result.target_y);
|
||||
println!("置信度: {:.4}", result.confidence);
|
||||
println!("{}", result);
|
||||
println!("耗时: {:?}", duration);
|
||||
println!("-------------------------------------------");
|
||||
|
||||
|
||||
Reference in New Issue
Block a user