- Removed trailing whitespace and ensured files end with a single newline in cleanup_unused_files.py. - Added fix_trailing_whitespace.py to batch remove trailing whitespace from Python files. - Updated install_dependencies.py to improve dependency installation prompts. - Cleaned up pick_coords.py by removing unnecessary whitespace and improving code readability. - Enhanced region_selector.py by disabling specific pylint checks for better compatibility with third-party libraries. - Improved WPS流程图生成工具.py by cleaning up whitespace and enhancing readability. - Updated __init__.py in typings to remove unnecessary lines. - Modified app.js to adjust default configuration values and clean up unused code.
101 lines
3.1 KiB
Python
101 lines
3.1 KiB
Python
#!/usr/bin/env python3
|
||
# -*- coding: utf-8 -*-
|
||
"""
|
||
测试OCR多线程优化效果
|
||
"""
|
||
|
||
import os
|
||
import sys
|
||
import time
|
||
from concurrent.futures import ThreadPoolExecutor
|
||
from operations.screenshot_service import get_optimal_workers
|
||
|
||
def test_ocr_multithread_config():
|
||
"""测试OCR多线程配置"""
|
||
print("=" * 70)
|
||
print("OCR多线程配置检查")
|
||
print("=" * 70)
|
||
print()
|
||
|
||
# 1. CPU信息
|
||
cpu_count = os.cpu_count() or 4
|
||
print(f"1. CPU信息")
|
||
print("-" * 70)
|
||
print(f" CPU核心数: {cpu_count}")
|
||
print()
|
||
|
||
# 2. OMP线程数配置
|
||
print("2. OMP线程数配置(底层库多线程)")
|
||
print("-" * 70)
|
||
omp_threads = os.environ.get("OMP_NUM_THREADS", "未设置")
|
||
print(f" OMP_NUM_THREADS: {omp_threads}")
|
||
|
||
# 计算推荐的OMP线程数
|
||
optimal_omp_threads = min(4, max(2, cpu_count // 3))
|
||
print(f" 推荐值: {optimal_omp_threads} (根据CPU核心数动态计算)")
|
||
print()
|
||
|
||
# 3. 线程池大小配置
|
||
print("3. 线程池大小配置(任务级多线程)")
|
||
print("-" * 70)
|
||
optimal_workers = get_optimal_workers()
|
||
print(f" 推荐线程池大小: {optimal_workers} (根据CPU核心数动态计算)")
|
||
print(f" 说明: 用于并行执行多个OCR任务")
|
||
print()
|
||
|
||
# 4. 优化说明
|
||
print("4. 优化说明")
|
||
print("-" * 70)
|
||
print(" 优化前:")
|
||
print(" - OMP_NUM_THREADS=1 (限制底层库只能使用1个线程)")
|
||
print(" - 线程池大小固定为6 (未充分利用多核CPU)")
|
||
print()
|
||
print(" 优化后:")
|
||
print(f" - OMP_NUM_THREADS={optimal_omp_threads} (允许底层库使用多线程)")
|
||
print(f" - 线程池大小={optimal_workers} (根据CPU核心数动态调整)")
|
||
print()
|
||
print(" 预期效果:")
|
||
print(" - 底层库(PaddleOCR/EasyOCR)可以并行处理图像")
|
||
print(" - 多个OCR任务可以并行执行")
|
||
print(" - 充分利用多核CPU资源")
|
||
print(" - 预计性能提升: 30-50% (取决于任务数量和CPU核心数)")
|
||
print()
|
||
|
||
# 5. 验证OCR引擎是否已初始化
|
||
print("5. OCR引擎状态")
|
||
print("-" * 70)
|
||
try:
|
||
from operations.ocr_operations import _ocr_processor
|
||
if _ocr_processor.ocr is not None:
|
||
print(f" OCR引擎: {_ocr_processor.ocr_type}")
|
||
print(" 状态: 已初始化")
|
||
else:
|
||
print(" 状态: 未初始化(延迟初始化)")
|
||
except Exception as e:
|
||
print(f" 状态: 检查失败 - {e}")
|
||
print()
|
||
|
||
print("=" * 70)
|
||
print("检查完成")
|
||
print("=" * 70)
|
||
|
||
def test_ocr_performance():
|
||
"""测试OCR性能(需要实际运行OCR)"""
|
||
print()
|
||
print("=" * 70)
|
||
print("OCR性能测试")
|
||
print("=" * 70)
|
||
print()
|
||
print("提示: 此测试需要实际运行OCR任务")
|
||
print(" 可以在实际使用中观察OCR耗时变化")
|
||
print()
|
||
print("测试方法:")
|
||
print("1. 运行程序,观察OCR任务的耗时")
|
||
print("2. 对比优化前后的性能差异")
|
||
print("3. 查看日志中的OCR耗时信息")
|
||
print()
|
||
|
||
if __name__ == "__main__":
|
||
test_ocr_multithread_config()
|
||
test_ocr_performance()
|