前言
最近在研究如何让YOLOv5推理得更快，总体看来，主要有以下这些思路：
- 使用更快的 GPU，即：P100 -> V100 -> A100
- 多卡GPU推理
- 减小模型尺寸，即YOLOv5x -> YOLOv5l -> YOLOv5m -> YOLOv5s -> YOLOv5n
- 进行半精度FP16推理与
python detect.py --half - 减少–img-size，即 1280 -> 640 -> 320
- 导出成
ONNX或OpenVINO格式，获得CPU加速 - 导出到TensorRT获得GPU加速
- 批量输入图片进行推理
- 使用多进程/多线程进行推理
注：使用多卡GPU和多进程/多线程的推理并不会对单张图片推理起到加速作用，只适用于很多张图片一起进行推理的场景。
本篇主要来研究多进程/多线程是否能对YOLOv5算法推理起到加速作用。
实验环境
GPU：RTX2060
torch：1.7.1 cu110
检测图片大小：1920x1080
img-size：1920
使用半精度推理half=True
实验过程
先放实验代码(detect.py)，根据官方源码进行了小改：
代码语言：javascript复制import configparser
import time
from pathlib import Path
import cv2
import torch
import threading
import sys
import multiprocessing as mp
sys.path.append("yolov5")
from models.experimental import attempt_load
from utils.datasets import LoadImages
from utils.general import check_img_size, non_max_suppression, scale_coords
from utils.plots import Annotator, colors
from utils.torch_utils import select_device
from concurrent.futures import ThreadPoolExecutor
Detect_path = 'D:/Data/detect_outputs' # 检测图片输出路径
def detect(path, model_path, detect_size):
source = path
weights = model_path
imgsz = detect_size
conf_thres = 0.25
iou_thres = 0.45
device = ""
augment = True
save_img = True
save_dir = Path(Detect_path) # increment run
device = select_device(device)
half = device.type != 'cpu' # half precision only supported on CUDA
# Load model
model = attempt_load(weights, map_location=device) # load FP32 model
stride = int(model.stride.max()) # model stride
imgsz = check_img_size(imgsz, s=stride) # check img_sizef
if half:
model.half() # to FP16
# Set Dataloader
vid_path, vid_writer = None, None
dataset = LoadImages(source, img_size=imgsz, stride=stride)
# Get names and colors
names = model.module.names if hasattr(model, 'module') else model.names
# Run inference
if device.type != 'cpu':
model(torch.zeros(1, 3, imgsz, imgsz).to(device).type_as(next(model.parameters()))) # run once
result_list = []
for path, img, im0s, vid_cap in dataset:
# 读取图片传到gpu上
t1 = time.time()
img = torch.from_numpy(img).to(device)
print("read pictures cost time：", time.time() - t1)
t2 = time.time()
img = img.half() if half else img.float() # uint8 to fp16/32
img /= 255.0 # 0 - 255 to 0.0 - 1.0
if img.ndimension() == 3:
img = img.unsqueeze(0)
print("process pictures cost time：", time.time() - t2)
# Inference
pred = model(img, augment=augment)[0]
# Apply NMS
pred = non_max_suppression(pred, conf_thres, iou_thres)
# Process detections
for i, det in enumerate(pred): # detections per image
p, s, im0, frame = path, '', im0s, getattr(dataset, 'frame', 0)
p = Path(p) # to Path
save_path = str(save_dir / p.name) # img.jpg
s = '%gx%g ' % img.shape[2:] # print string
# print(s) # 384x640
s_result = '' # 输出检测结果
annotator = Annotator(im0, line_width=3, example=str(names))
if len(det):
# Rescale boxes from img_size to im0 size
det[:, :4] = scale_coords(img.shape[2:], det[:, :4], im0.shape).round()
# Print results
for c in det[:, -1].unique():
n = (det[:, -1] == c).sum() # detections per class
# s = f"{n} {names[int(c)]}{'s' * (n > 1)}, " # add to string
s = f"{n} {names[int(c)]}, " # add to string
s_result = f"{n} {names[int(c)]} "
# Write results
for *xyxy, conf, cls in reversed(det):
if save_img:
c = int(cls)
# label = f'{names[int(cls)]} {conf:.2f}'
label = f'{names[int(cls)]}'
# print(label)
annotator.box_label(xyxy, label, color=colors(c, True))
# print(xyxy)
print(f'{s}')
# print(f'{s_result}')
result_list.append(s_result)
# 将conf对象中的数据写入到文件中
conf = configparser.ConfigParser()
cfg_file = open("glovar.cfg", 'w')
conf.add_section("default") # 在配置文件中增加一个段
# 第一个参数是段名，第二个参数是选项名，第三个参数是选项对应的值
conf.set("default", "process", str(dataset.img_count))
conf.set("default", "total", str(dataset.nf))
conf.write(cfg_file)
cfg_file.close()
im0 = annotator.result()
# Save results (image with detections)
t3 = time.time()
if save_img:
if dataset.mode == 'image':
cv2.imwrite(save_path, im0)
else: # 'video' or 'stream'
if vid_path != save_path: # new video
vid_path = save_path
if isinstance(vid_writer, cv2.VideoWriter):
vid_writer.release() # release previous video writer
if vid_cap: # video
fps = vid_cap.get(cv2.CAP_PROP_FPS)
w = int(vid_cap.get(cv2.CAP_PROP_FRAME_WIDTH))
h = int(vid_cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
else: # stream
fps, w, h = 30, im0.shape[1], im0.shape[0]
save_path = '.mp4'
vid_writer = cv2.VideoWriter(save_path, cv2.VideoWriter_fourcc(*'mp4v'), fps, (w, h))
vid_writer.write(im0)
print("write pictures cost time：", time.time() - t3)
print('Done')
def run(path, model_path, detect_size):
with torch.no_grad():
detect(path, model_path, detect_size)首先进行小批量的图片进行实验，下面输入两张图片进行检测。
原始推理
代码语言：javascript复制if __name__ == '__main__':
s_t = time.time()
path1 = "D:/Data/image/DJI_0001_00100.jpg"
path2 = "D:/Data/image/DJI_0001_00530.jpg"
model_path = "../weights/best.pt"
detect_size = 1920
run(path1, model_path, detect_size)
run(path2, model_path, detect_size)
print("Tatal Cost Time:", time.time() - s_t)Tatal Cost Time: 3.496427059173584
线程池推理
开辟两个线程进行推理：
代码语言：javascript复制if __name__ == '__main__':
s_t = time.time()
pool = ThreadPoolExecutor(max_workers=2)
path1 = "D:/Data/image/DJI_0001_00100.jpg"
path2 = "D:/Data/image/DJI_0001_00530.jpg"
model_path = "../weights/best.pt"
detect_size = 1920
pool.submit(run, path1, model_path, detect_size)
pool.submit(run, path2, model_path, detect_size)
pool.shutdown(wait=True)
print("Tatal Cost Time:", time.time() - s_t)Tatal Cost Time: 3.2433135509490967
开双线程推理和原始推理时间类似，再次验证了python中的”伪多线程”。
进程池推理
开辟两个进程进行推理：
代码语言：javascript复制if __name__ == '__main__':
s_t = time.time()
pool = mp.Pool(processes=2)
path1 = "D:/Data/image/DJI_0001_00100.jpg"
path2 = "D:/Data/image/DJI_0001_00530.jpg"
model_path = "../weights/best.pt"
detect_size = 1920
pool.apply_async(run, (path1, model_path, detect_size,))
pool.apply_async(run, (path2, model_path, detect_size,))
pool.close()
pool.join()
print("Tatal Cost Time:", time.time() - s_t)Tatal Cost Time: 6.020772695541382
双进程推理
双进程推理时间竟然是原始推理的两倍，以为是进程池的开销太大，于是换种写法，不使用进程池：
代码语言：javascript复制if __name__ == '__main__':
s_t = time.time()
path1 = "D:/Data/image/DJI_0001_00100.jpg"
path2 = "D:/Data/image/DJI_0001_00530.jpg"
model_path = "../weights/best.pt"
detect_size = 1920
p1 = mp.Process(target=run, args=(path1, model_path, detect_size,))
p2 = mp.Process(target=run, args=(path2, model_path, detect_size,))
p1.start()
p2.start()
p1.join()
p2.join()
print("Tatal Cost Time:", time.time() - s_t)Tatal Cost Time: 6.089479446411133
发现双进程时间仍然较久，说明在数据较少时，进程的开销成本过高，这和我之前做的实验多线程和多进程的效率对比结果相类似。
于是下面将图像数量扩大到300张进行实验。
300pic-原始推理
代码语言：javascript复制if __name__ == '__main__':
s_t = time.time()
path1 = "D:/Data/image"
path2 = "D:/Data/image2"
path3 = "D:/Data/image3"
model_path = "../weights/best.pt"
detect_size = 1920
run(path1, model_path, detect_size)
run(path2, model_path, detect_size)
run(path3, model_path, detect_size)
print("Tatal Cost Time:", time.time() - s_t)Tatal Cost Time: 62.02898120880127
300pic-多进程推理
代码语言：javascript复制if __name__ == '__main__':
s_t = time.time()
path1 = "D:/Data/image"
path2 = "D:/Data/image2"
path3 = "D:/Data/image3"
model_path = "../weights/best.pt"
detect_size = 1920
p1 = mp.Process(target=run, args=(path1, model_path, detect_size,))
p2 = mp.Process(target=run, args=(path2, model_path, detect_size,))
p3 = mp.Process(target=run, args=(path3, model_path, detect_size,))
p1.start()
p2.start()
p3.start()
p1.join()
p2.join()
p3.join()
print("Tatal Cost Time:", time.time() - s_t)Tatal Cost Time: 47.85872721672058
和预期一样，当数据量提升上去时，多进程推理的速度逐渐超越原始推理。
总结
本次实验结果如下表所示：
图像处理张数 | 原始推理(s) | 多线程推理(s) | 多进程推理(s) |
|---|---|---|---|
2 | 3.49 | 3.24 | 6.08 |
300 | 62.02 | / | 47.85 |
值得注意的是，使用多进程推理时，进程间保持独立，这意味着模型需要被重复在GPU上进行创建，因此，可以根据单进程所占显存大小来估算显卡所支持的最大进程数。
后续：在顶配机上进行实验
后面嫖到了组里i9-13700K RTX4090的顶配主机，再进行实验，结果如下：
图像处理张数 | 原始推理(s) | 多线程推理(s) | 多进程推理(s) |
|---|---|---|---|
2 | 2.21 | 2.09 | 3.92 |
300 | 29.23 | / | 17.61 |
