45 lines
1.7 KiB
Python
45 lines
1.7 KiB
Python
|
"""延迟分析 - batch=1 优化后"""
|
||
|
|
import sys
|
||
|
|
import os
|
||
|
|
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
|
||
|
|
|
||
|
|
import time
|
||
|
|
import numpy as np
|
||
|
|
|
||
|
|
from config.settings import get_settings
|
||
|
|
from core.preprocessor import ImagePreprocessor, BatchPreprocessor
|
||
|
|
|
||
|
|
settings = get_settings()
|
||
|
|
preprocessor = ImagePreprocessor(settings.inference)
|
||
|
|
|
||
|
|
img = np.random.randint(0, 255, (1080, 1920, 3), dtype=np.uint8)
|
||
|
|
roi_mock = type('ROI', (), {'x1': 300, 'y1': 100, 'x2': 1000, 'y2': 800, 'enabled': True, 'roi_type': 0})()
|
||
|
|
|
||
|
|
times_preprocess_single = []
|
||
|
|
times_preprocess_batch = []
|
||
|
|
|
||
|
|
for _ in range(100):
|
||
|
|
# 1. preprocess_single
|
||
|
|
start = time.perf_counter()
|
||
|
|
cropped = preprocessor.preprocess_single(img, roi_mock)
|
||
|
|
t = (time.perf_counter() - start) * 1000
|
||
|
|
times_preprocess_single.append(t)
|
||
|
|
|
||
|
|
# 2. preprocess_batch (batch=1)
|
||
|
|
start = time.perf_counter()
|
||
|
|
batch_data, _ = preprocessor._batch_preprocessor.preprocess_batch([cropped[0]])
|
||
|
|
t = (time.perf_counter() - start) * 1000
|
||
|
|
times_preprocess_batch.append(t)
|
||
|
|
|
||
|
|
print("延迟分析 (batch=1 优化后):")
|
||
|
|
print(f" preprocess_single: {np.mean(times_preprocess_single):.2f}ms")
|
||
|
|
print(f" preprocess_batch: {np.mean(times_preprocess_batch):.2f}ms")
|
||
|
|
print(f" 总预处理: {np.mean(times_preprocess_single) + np.mean(times_preprocess_batch):.2f}ms")
|
||
|
|
print()
|
||
|
|
print(f"TensorRT batch=1 推理: ~2.5ms")
|
||
|
|
print(f"TensorRT batch=4 推理: ~5.0ms")
|
||
|
|
print()
|
||
|
|
print("推算总延迟:")
|
||
|
|
print(f" batch=1: {np.mean(times_preprocess_single) + np.mean(times_preprocess_batch):.2f} + 2.5 ≈ 8-12ms")
|
||
|
|
print(f" batch=4: {np.mean(times_preprocess_single) + np.mean(times_preprocess_batch):.2f} + 5 ≈ 10-15ms")
|