Files
douyin_guaji-main/test_real_parallel_ocr.py
T
Your Name 7db9864848 feat: Introduce JPEG support check and remove obsolete files
- Added a new script `check_jpeg_support.py` to verify device support for JPEG screenshots, enhancing functionality for image processing.
- Deleted obsolete files including `auto_test_result.txt`, `CODE_QUALITY_REVIEW.md`, and others to streamline the project and improve maintainability.
- Cleaned up unnecessary blank lines in various scripts to enhance readability and organization.
2025-12-31 17:01:18 +08:00

378 lines
14 KiB
Python
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
真实场景并行OCR性能对比测试
模拟实际使用中的多区域并行OCR识别
"""
import os
import sys
import time
from concurrent.futures import ThreadPoolExecutor
from PIL import Image
import numpy as np
import tempfile
def create_test_regions(full_image_path):
"""从完整截图中创建多个测试区域(模拟真实OCR场景)"""
try:
img = Image.open(full_image_path)
if img.mode != 'RGB':
img = img.convert('RGB')
width, height = img.size
# 判断是否是完整截图(1080x2400)还是裁剪区域
is_full_screenshot = width >= 1000 and height >= 2000
if is_full_screenshot:
# 完整截图:创建多个测试区域
# 模拟真实的OCR区域(基于福袋详情页的常见区域)
regions = {
"福袋倒计时_分钟": (400, 1050, 500, 1150), # 倒计时分钟区域
"福袋倒计时_秒": (480, 1110, 570, 1230), # 倒计时秒区域(用户提供的区域)
"福袋内容": (50, 800, 500, 1000), # 福袋内容区域
"福袋价值": (200, 1300, 400, 1400), # 价值区域
"任务列表": (50, 600, 500, 750), # 任务列表区域
"参与按钮": (300, 1500, 800, 1600), # 按钮状态区域
}
else:
# 裁剪区域:使用当前图片作为测试区域之一,创建其他相似大小的区域
# 从文件名提取坐标信息(如果存在)
coords_from_filename = None
if "(480,1110)-(570,1230)" in full_image_path:
coords_from_filename = (480, 1110, 570, 1230)
# 创建多个相似大小的测试区域
# 如果图片较小,创建多个相同大小的区域用于测试
# 这些区域会在完整截图的合理位置
regions = {}
# 使用当前图片作为第一个区域
if coords_from_filename:
x1, y1, x2, y2 = coords_from_filename
regions["福袋倒计时_秒"] = (x1, y1, x2, y2)
# 创建其他相邻区域
offset_x = x2 - x1
offset_y = y2 - y1
regions["福袋倒计时_分钟"] = (x1 - offset_x - 20, y1, x1 - 20, y2)
regions["福袋内容"] = (x1, y1 - offset_y - 20, x2, y1 - 20)
regions["福袋价值"] = (x1, y2 + 20, x2, y2 + offset_y + 20)
else:
# 如果无法从文件名提取坐标,使用图片本身作为唯一测试区域
# 创建多个相同大小的区域(通过复制当前图片)
regions["区域1"] = (0, 0, width, height)
regions["区域2"] = (0, 0, width, height) # 相同区域,用于测试并行
regions["区域3"] = (0, 0, width, height) # 相同区域,用于测试并行
regions["区域4"] = (0, 0, width, height) # 相同区域,用于测试并行
regions["区域5"] = (0, 0, width, height) # 相同区域,用于测试并行
regions["区域6"] = (0, 0, width, height) # 相同区域,用于测试并行
# 裁剪并保存区域图片
region_images = {}
temp_dir = tempfile.gettempdir()
for name, (x1, y1, x2, y2) in regions.items():
try:
# 确保坐标在图片范围内
x1 = max(0, min(x1, img.width))
y1 = max(0, min(y1, img.height))
x2 = max(x1, min(x2, img.width))
y2 = max(y1, min(y2, img.height))
if x2 > x1 and y2 > y1:
crop_img = img.crop((x1, y1, x2, y2))
temp_path = os.path.join(temp_dir, f"ocr_test_{name}.png")
crop_img.save(temp_path)
region_images[name] = {
'path': temp_path,
'size': crop_img.size,
'coords': (x1, y1, x2, y2)
}
except (ValueError, OSError, IOError) as e:
print(f"[WARNING] 无法裁剪区域 {name}: {e}")
return region_images, img.size
except (OSError, IOError, ValueError) as e:
print(f"[ERROR] 无法处理图片: {e}")
return {}, None
def ocr_single_region(image_path, region_name, ocr_processor):
"""对单个区域进行OCR识别"""
try:
img = Image.open(image_path)
if img.mode != 'RGB':
img = img.convert('RGB')
img_np = np.array(img)
start_time = time.time()
if ocr_processor.ocr_type == "easyocr":
result = ocr_processor.ocr.readtext(img_np)
else:
result = ocr_processor.ocr.ocr(img_np)
elapsed = (time.time() - start_time) * 1000
# 提取文本
from Underlying_Operations import underlying_operations
ops = underlying_operations()
text = ops.extract_ocr_content(result)
return {
'region': region_name,
'text': text,
'time': elapsed,
'success': True
}
except Exception as e:
import traceback
error_msg = f"{type(e).__name__}: {str(e)}"
print(f" [DEBUG] {region_name} OCR错误: {error_msg}")
return {
'region': region_name,
'text': '',
'time': 0,
'success': False,
'error': error_msg
}
def test_parallel_ocr_real(region_images, config_name, omp_threads, max_workers):
"""测试真实场景的并行OCR"""
print(f"\n{'='*70}")
print(f"测试: {config_name}")
print(f"{'='*70}")
print(f"配置: OMP_NUM_THREADS={omp_threads}, max_workers={max_workers}")
print(f"区域数量: {len(region_images)}")
print()
# 设置OMP线程数
old_omp = os.environ.get('OMP_NUM_THREADS', '4')
os.environ['OMP_NUM_THREADS'] = str(omp_threads)
# 初始化OCR(使用新的OMP设置)
try:
from operations.ocr_operations import OCRProcessor
ocr_processor = OCRProcessor()
# 访问受保护方法以初始化OCR引擎(测试代码中需要)
# 使用 getattr 来避免 pylance 警告
ensure_ocr = getattr(ocr_processor, '_ensure_ocr')
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 (ImportError, AttributeError, RuntimeError) as e:
print(f"[ERROR] OCR引擎初始化失败: {e}")
os.environ['OMP_NUM_THREADS'] = old_omp
return None
# 显示区域信息
print("OCR区域信息:")
for name, info in region_images.items():
print(f" {name}: {info['size'][0]}x{info['size'][1]} 像素, 坐标: {info['coords']}")
print()
# 并行执行OCR
print("开始并行OCR识别...")
start_time = time.time()
results = []
def ocr_task(name, path):
return ocr_single_region(path, name, ocr_processor)
with ThreadPoolExecutor(max_workers=max_workers) as executor:
# 提交所有任务
futures = {
executor.submit(ocr_task, name, info['path']): name
for name, info in region_images.items()
}
# 收集结果
for future in futures:
region_name = futures[future]
try:
result = future.result(timeout=60) # 每个任务最多60秒
results.append(result)
status = "✓" if result['success'] else "✗"
print(f" {status} {region_name}: {result['time']:.0f}ms, 结果: {result['text'][:30] if result['text'] else '(空)'}")
except TimeoutError:
print(f" ✗ {region_name}: 超时(>60秒)")
results.append({
'region': region_name,
'text': '',
'time': 0,
'success': False,
'error': 'Timeout'
})
except (RuntimeError, AttributeError, KeyError) as e:
print(f" ✗ {region_name}: 失败 - {e}")
results.append({
'region': region_name,
'text': '',
'time': 0,
'success': False,
'error': str(e)
})
total_elapsed = (time.time() - start_time) * 1000
# 恢复OMP设置
os.environ['OMP_NUM_THREADS'] = old_omp
# 统计结果
successful_results = [r for r in results if r['success']]
total_task_time = sum(r['time'] for r in successful_results)
avg_task_time = total_task_time / len(successful_results) if successful_results 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: {len(region_images):.1f}x)")
print()
return {
'total_time': total_elapsed,
'task_times': [r['time'] for r in successful_results],
'results': results,
'config': config_name
}
def main():
"""主函数"""
# 默认图片路径(完整截图)
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("真实场景并行OCR性能对比测试")
print("=" * 70)
print()
print(f"测试图片: {os.path.basename(image_path)}")
print()
# 创建测试区域
print("准备测试区域...")
region_images, full_size = create_test_regions(image_path)
if not region_images:
print("[ERROR] 无法创建测试区域")
return
if full_size is not None:
print(f"完整截图尺寸: {full_size[0]}x{full_size[1]}")
else:
print("完整截图尺寸: 未知")
print(f"成功创建 {len(region_images)} 个测试区域")
print()
# 获取系统信息
cpu_count = os.cpu_count() or 4
print("系统信息:")
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 (ImportError, AttributeError):
optimal_workers = 6
print()
# 测试1: 优化前配置(OMP=1, workers=6)
result_old = test_parallel_ocr_real(
region_images,
"优化前配置",
omp_threads=1,
max_workers=6
)
# 等待一下,让系统稳定
time.sleep(1)
# 测试2: 优化后配置(OMP=4, workers=10)
result_new = test_parallel_ocr_real(
region_images,
"优化后配置",
omp_threads=4,
max_workers=optimal_workers
)
# 性能对比总结
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()
# 详细对比
if result_old['task_times'] and result_new['task_times']:
old_avg = sum(result_old['task_times']) / len(result_old['task_times'])
new_avg = sum(result_new['task_times']) / len(result_new['task_times'])
print("任务级性能对比:")
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")
print(f" 单任务性能提升: {old_avg/new_avg:.2f}x")
print()
# 识别结果对比
print("识别结果对比:")
for old_result in result_old['results']:
region_name = old_result['region']
new_result = next((r for r in result_new['results'] if r['region'] == region_name), None)
if old_result['success'] and new_result and new_result['success']:
old_text = old_result['text'][:20] if old_result['text'] else '(空)'
new_text = new_result['text'][:20] if new_result['text'] else '(空)'
match = "✓" if old_text == new_text else "✗"
print(f" {match} {region_name}: 结果一致")
# 清理临时文件
print()
print("清理临时文件...")
for info in region_images.values():
try:
if os.path.exists(info['path']):
os.remove(info['path'])
except (OSError, PermissionError):
pass
print()
print("=" * 70)
print("测试完成")
print("=" * 70)
if __name__ == "__main__":
main()