- Removed excessive blank lines in various Python scripts, markdown files, and configuration files to improve overall code clarity and maintainability. - Ensured consistent formatting throughout the project, contributing to a more organized codebase.
208 lines
6.6 KiB
Python
208 lines
6.6 KiB
Python
#!/usr/bin/env python3
|
|
# -*- coding: utf-8 -*-
|
|
"""
|
|
简化版并行OCR性能对比测试
|
|
直接使用提供的图片进行测试
|
|
"""
|
|
|
|
import os
|
|
import sys
|
|
import time
|
|
from concurrent.futures import ThreadPoolExecutor
|
|
from PIL import Image
|
|
import numpy as np
|
|
|
|
def test_ocr_with_config(image_path, config_name, omp_threads, max_workers, num_tasks=6):
|
|
"""使用指定配置测试OCR"""
|
|
print(f"\n{'='*70}")
|
|
print(f"{config_name}")
|
|
print(f"{'='*70}")
|
|
print(f"OMP_NUM_THREADS={omp_threads}, max_workers={max_workers}, 任务数={num_tasks}")
|
|
print()
|
|
|
|
# 设置OMP
|
|
old_omp = os.environ.get('OMP_NUM_THREADS', '4')
|
|
os.environ['OMP_NUM_THREADS'] = str(omp_threads)
|
|
|
|
# 加载图片
|
|
try:
|
|
img = Image.open(image_path)
|
|
if img.mode != 'RGB':
|
|
img = img.convert('RGB')
|
|
img_np = np.array(img)
|
|
print(f"图片: {os.path.basename(image_path)}")
|
|
print(f"尺寸: {img.size[0]}x{img.size[1]} 像素")
|
|
print()
|
|
except Exception as e:
|
|
print(f"[ERROR] 无法加载图片: {e}")
|
|
os.environ['OMP_NUM_THREADS'] = old_omp
|
|
return None
|
|
|
|
# 初始化OCR
|
|
try:
|
|
from operations.ocr_operations import OCRProcessor
|
|
ocr_processor = OCRProcessor()
|
|
ocr_processor._ensure_ocr()
|
|
|
|
if ocr_processor.ocr is None:
|
|
print("[ERROR] OCR引擎未初始化")
|
|
os.environ['OMP_NUM_THREADS'] = old_omp
|
|
return None
|
|
|
|
print(f"OCR引擎: {ocr_processor.ocr_type}")
|
|
print()
|
|
except Exception as e:
|
|
print(f"[ERROR] OCR引擎初始化失败: {e}")
|
|
os.environ['OMP_NUM_THREADS'] = old_omp
|
|
return None
|
|
|
|
# OCR任务函数
|
|
def ocr_task(task_id):
|
|
try:
|
|
start = time.time()
|
|
if ocr_processor.ocr_type == "easyocr":
|
|
result = ocr_processor.ocr.readtext(img_np)
|
|
else:
|
|
result = ocr_processor.ocr.ocr(img_np)
|
|
|
|
from Underlying_Operations import underlying_operations
|
|
ops = underlying_operations()
|
|
text = ops.extract_ocr_content(result)
|
|
elapsed = (time.time() - start) * 1000
|
|
return {'task_id': task_id, 'text': text, 'time': elapsed, 'success': True}
|
|
except Exception as e:
|
|
return {'task_id': task_id, 'text': '', 'time': 0, 'success': False, 'error': str(e)}
|
|
|
|
# 执行并行OCR
|
|
print("开始并行OCR测试...")
|
|
start_time = time.time()
|
|
results = []
|
|
|
|
with ThreadPoolExecutor(max_workers=max_workers) as executor:
|
|
futures = {executor.submit(ocr_task, i+1): i+1 for i in range(num_tasks)}
|
|
|
|
for future in futures:
|
|
try:
|
|
result = future.result()
|
|
results.append(result)
|
|
status = "✓" if result['success'] else "✗"
|
|
print(f" {status} 任务{result['task_id']}: {result['time']:.0f}ms, 结果: {result['text'][:20] if result['text'] else '(空)'}")
|
|
except Exception as e:
|
|
print(f" ✗ 任务失败: {e}")
|
|
|
|
total_elapsed = (time.time() - start_time) * 1000
|
|
|
|
# 恢复OMP设置
|
|
os.environ['OMP_NUM_THREADS'] = old_omp
|
|
|
|
# 统计
|
|
successful = [r for r in results if r['success']]
|
|
total_task_time = sum(r['time'] for r in successful)
|
|
avg_task_time = total_task_time / len(successful) if successful else 0
|
|
|
|
print()
|
|
print(f"总耗时: {total_elapsed:.0f}ms ({total_elapsed/1000:.2f}秒)")
|
|
print(f"任务总耗时: {total_task_time:.0f}ms")
|
|
print(f"平均每个任务: {avg_task_time:.0f}ms")
|
|
if total_task_time > 0:
|
|
efficiency = total_task_time / total_elapsed
|
|
print(f"并行效率: {efficiency:.2f}x (理想值: {num_tasks:.1f}x)")
|
|
print()
|
|
|
|
return {
|
|
'total_time': total_elapsed,
|
|
'avg_task_time': avg_task_time,
|
|
'config': config_name
|
|
}
|
|
|
|
def main():
|
|
"""主函数"""
|
|
default_image = "pic/debug_captures/2025-12-31/20251231_152116_ocr_福袋倒计时_秒_预处理后_(480,1110)-(570,1230)_模式_1_尺寸_270x360_来源_福袋倒计时_秒.png_有完整截图_是_有坐标_是_类型_digits.png"
|
|
|
|
if len(sys.argv) > 1:
|
|
image_path = sys.argv[1]
|
|
else:
|
|
image_path = default_image
|
|
|
|
if not os.path.isabs(image_path):
|
|
project_root = os.path.dirname(os.path.abspath(__file__))
|
|
image_path = os.path.join(project_root, image_path)
|
|
|
|
if not os.path.exists(image_path):
|
|
print(f"[ERROR] 图片文件不存在: {image_path}")
|
|
return
|
|
|
|
print("=" * 70)
|
|
print("并行OCR性能对比测试(简化版)")
|
|
print("=" * 70)
|
|
print()
|
|
print(f"测试图片: {os.path.basename(image_path)}")
|
|
|
|
# 获取系统信息
|
|
cpu_count = os.cpu_count() or 4
|
|
print(f"CPU核心数: {cpu_count}")
|
|
try:
|
|
from operations.screenshot_service import get_optimal_workers
|
|
optimal_workers = get_optimal_workers()
|
|
print(f"推荐线程池大小: {optimal_workers}")
|
|
except:
|
|
optimal_workers = 6
|
|
|
|
num_tasks = 6
|
|
print(f"测试任务数: {num_tasks}")
|
|
print()
|
|
|
|
# 测试1: 优化前
|
|
result_old = test_ocr_with_config(
|
|
image_path,
|
|
"优化前配置 (OMP=1, workers=6)",
|
|
omp_threads=1,
|
|
max_workers=6,
|
|
num_tasks=num_tasks
|
|
)
|
|
|
|
time.sleep(1) # 等待系统稳定
|
|
|
|
# 测试2: 优化后
|
|
result_new = test_ocr_with_config(
|
|
image_path,
|
|
"优化后配置 (OMP=4, workers=10)",
|
|
omp_threads=4,
|
|
max_workers=optimal_workers,
|
|
num_tasks=num_tasks
|
|
)
|
|
|
|
# 对比结果
|
|
print()
|
|
print("=" * 70)
|
|
print("性能对比总结")
|
|
print("=" * 70)
|
|
print()
|
|
|
|
if result_old and result_new:
|
|
old_time = result_old['total_time']
|
|
new_time = result_new['total_time']
|
|
speedup = old_time / new_time if new_time > 0 else 0
|
|
|
|
print(f"优化前总耗时: {old_time:.0f}ms ({old_time/1000:.2f}秒)")
|
|
print(f"优化后总耗时: {new_time:.0f}ms ({new_time/1000:.2f}秒)")
|
|
print(f"性能提升: {speedup:.2f}x")
|
|
print(f"时间减少: {(1 - new_time/old_time)*100:.1f}%")
|
|
print()
|
|
|
|
old_avg = result_old['avg_task_time']
|
|
new_avg = result_new['avg_task_time']
|
|
print(f"优化前平均任务耗时: {old_avg:.0f}ms")
|
|
print(f"优化后平均任务耗时: {new_avg:.0f}ms")
|
|
if new_avg > 0:
|
|
print(f"单任务性能提升: {old_avg/new_avg:.2f}x")
|
|
|
|
print()
|
|
print("=" * 70)
|
|
print("测试完成")
|
|
print("=" * 70)
|
|
|
|
if __name__ == "__main__":
|
|
main()
|
|
|