为保证您获得更好的学习体验,请使用电脑阅读学习,本专栏对手机用户并不友好!
本文将以detec.py文件为主,带你从头开始逐一追踪代码,了解detect运行流程。
目录
detect.py:
common.py(models):
DetectMultiBackend: (line279)
datasets.py(utils):
LoadImages: (line178)
augmentations.py(utils):
letterbox: (line91)
plots.py(utils):
Annotator: (line68)
detect.py:
FILE 当前文件绝对路径
ROOT 整个yolov5项目的路径(多数情况下在文件的下载转移更新时已存在包导入时无法查找,则可查看该路径是否正确)
Parse_opt 定参,返回opt(存储所有参数信息)
Main ①检测requirement中依赖包
②执行Run
Run
1.判断source传入数据
①is_file: 判断输入图片格式是否在设定格式中(dataset.py)
②webcam:false
2. Directories,新建保存结果文件夹
# Directories
save_dir = increment_path(Path(project) / name, exist_ok=exist_ok) # increment run
(save_dir / 'labels' if save_txt else save_dir).mkdir(parents=True, exist_ok=True) # make dir
3. Load model,加载模型
# Load model
device = select_device(device)
model = DetectMultiBackend(weights, device=device, dnn=dnn, data=data, fp16=half)
stride, names, pt = model.stride, model.names, model.pt
imgsz = check_img_size(imgsz, s=stride) # check image size
①device:选择设备,摄像头、GPU、CPU等
②model:(weight,coco.yaml)显示后端框架(pytorch、TorchScri等)
DetectMultiBackend(common.py)
③加载模型数据
④imgsz保证图片尺寸为32的倍数,不是则自动计算出32倍数尺寸
4. Dataloader,加载待预测图片
# Dataloader
if webcam:
view_img = check_imshow()
cudnn.benchmark = True # set True to speed up constant image size inference
dataset = LoadStreams(source, img_size=imgsz, stride=stride, auto=pt)
bs = len(dataset) # batch_size
else:
dataset = LoadImages(source, img_size=imgsz, stride=stride, auto=pt)
bs = 1 # batch_size
vid_path, vid_writer = [None] * bs, [None] * bs
LoadImages(datasets.py)
5. Run inference,输入模型推理产生推理结果画出识别框:
初始化:
Warmup:传入一张空图片到GPU预热
LoadImages):
im: 图片numpy转pytroch支持的格式
/=255:归一化
扩张维度
Inference: 预测
visualize(默认false):若为true,保存推断过程特征图
pred: 检测框
augment:可对推断做数据增强,但降低模型运行速度
[1,18900,85]:85指4个坐标信息,1个置信度,80个类别概率
NMS: 非极大值过滤
pred: 1,5,6: 6指4坐标,1置信度,1类别
Process:
det: [5,6],5个矩形框, 6指4坐标,1置信度,1类别
seen:计数器
save_path:图片保存路径
txt_path:默认不保存txt文件
s:
gn:获得原图宽高,保存txt时有用
imc:判断是否把检测框裁剪保存
plots.py):原图绘制
if(det): 画框
det[] 从调整图中坐标映射回原图
遍历所有框:n统计所有框->s打印信息
write results:选择保存方式
add bbox to image(默认选择):
label:hide_labels、hide_conf(detect参数)是否打印
标签、置信度
annotator.box_label:画框
save_crop:默认false,是否保存截取检测框
stream: (view_img)展示结果
save_img: 保存图片
6. Print results,打印输出结果
# Print results
t = tuple(x / seen * 1E3 for x in dt) # speeds per image
LOGGER.info(f'Speed: %.1fms pre-process, %.1fms inference, %.1fms NMS per image at shape {(1, 3, *imgsz)}' % t)
if save_txt or save_img:
s = f"\n{len(list(save_dir.glob('labels/*.txt')))} labels saved to {save_dir / 'labels'}" if save_txt else ''
LOGGER.info(f"Results saved to {colorstr('bold', save_dir)}{s}")
if update:
strip_optimizer(weights) # update model (to fix SourceChangeWarning)
t: 统计预测每张图片平均时间
seen:预测图片数量,dt每张图片所用时间
LOGGER.info:日志
detect.py源码注释:
(有小改动,可对比自身本地项目文件阅读)
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
"""
Run inference on images, videos, directories, streams, etc.
Usage - sources:
$ python path/to/detect.py --weights yolov5s.pt --source 0 # webcam
img.jpg # image
vid.mp4 # video
path/ # directory
path/*.jpg # glob
'https://youtu.be/Zgi9g1ksQHc' # YouTube
'rtsp://example.com/media.mp4' # RTSP, RTMP, HTTP stream
Usage - formats:
$ python path/to/detect.py --weights yolov5s.pt # PyTorch
yolov5s.torchscript # TorchScript
yolov5s.onnx # ONNX Runtime or OpenCV DNN with --dnn
yolov5s.xml # OpenVINO
yolov5s.engine # TensorRT
yolov5s.mlmodel # CoreML (MacOS-only)
yolov5s_saved_model # TensorFlow SavedModel
yolov5s.pb # TensorFlow GraphDef
yolov5s.tflite # TensorFlow Lite
yolov5s_edgetpu.tflite # TensorFlow Edge TPU
"""
import argparse
import os
import sys
from pathlib import Path
import cv2
import torch
import torch.backends.cudnn as cudnn
FILE = Path(__file__).resolve() # 当前文件绝对路径
# 整个yolov5项目的路径
ROOT = FILE.parents[0] # YOLOv5 root directory
if str(ROOT) not in sys.path:
sys.path.append(str(ROOT)) # add ROOT to PATH
ROOT = Path(os.path.relpath(ROOT, Path.cwd())) # relative
from models.common import DetectMultiBackend
from utils.datasets import IMG_FORMATS, VID_FORMATS, LoadImages, LoadStreams
from utils.general import (LOGGER, check_file, check_img_size, check_imshow, check_requirements, colorstr,
increment_path, non_max_suppression, print_args, scale_coords, strip_optimizer, xyxy2xywh)
from utils.plots import Annotator, colors, save_one_box
from utils.torch_utils import select_device, time_sync
@torch.no_grad()
def run(weights=ROOT / 'yolov5s.pt', # model.pt path(s)
source=ROOT / 'data/images', # file/dir/URL/glob, 0 for webcam
data=ROOT / 'data/coco128.yaml', # dataset.yaml path
imgsz=(640, 640), # inference size (height, width)
conf_thres=0.25, # confidence threshold
iou_thres=0.45, # NMS IOU threshold
max_det=1000, # maximum detections per image
device='', # cuda device, i.e. 0 or 0,1,2,3 or cpu
view_img=False, # show results
save_txt=False, # save results to *.txt
save_conf=False, # save confidences in --save-txt labels
save_crop=False, # save cropped prediction boxes
nosave=False, # do not save images/videos
classes=None, # filter by class: --class 0, or --class 0 2 3
agnostic_nms=False, # class-agnostic NMS
augment=False, # augmented inference
visualize=False, # visualize features
update=False, # update all models
project=ROOT / 'runs/detect', # save results to project/name
name='exp', # save results to project/name
exist_ok=False, # existing project/name ok, do not increment
line_thickness=3, # bounding box thickness (pixels)
hide_labels=False, # hide labels
hide_conf=False, # hide confidences
half=False, # use FP16 half-precision inference
dnn=False, # use OpenCV DNN for ONNX inference
):
source = str(source)
save_img = not nosave and not source.endswith('.txt') # save inference images
# 判断输入的是否为文件地址且是否包含于相应格式
is_file = Path(source).suffix[1:] in (IMG_FORMATS + VID_FORMATS)
is_url = source.lower().startswith(('rtsp://', 'rtmp://', 'http://', 'https://')) # 判断是否为网络流地址(false)
# 判断是否传入是0-打开电脑摄像头,默认false
webcam = source.isnumeric() or source.endswith('.txt') or (is_url and not is_file)
if is_url and is_file:
source = check_file(source) # download
# Directories
# 新建保存结果文件夹
save_dir = increment_path(Path(project) / name, exist_ok=exist_ok) # increment run
(save_dir / 'labels' if save_txt else save_dir).mkdir(parents=True, exist_ok=True) # make dir
# Load model
# 加载模型
device = select_device(device) # 选择设备,摄像头、GPU、CPU等
# 显示后端框架(pytorch、TorchScri等)
model = DetectMultiBackend(weights, device=device, dnn=dnn, data=data, fp16=half)
stride, names, pt = model.stride, model.names, model.pt # 加载模型数据
# 保证图片尺寸为32的倍数,不是则自动计算出32倍数尺寸
imgsz = check_img_size(imgsz, s=stride) # check image size
# Dataloader
# 加载待预测图片
if webcam:
view_img = check_imshow()
cudnn.benchmark = True # set True to speed up constant image size inference
dataset = LoadStreams(source, img_size=imgsz, stride=stride, auto=pt)
bs = len(dataset) # batch_size
else:
# 初始化
dataset = LoadImages(source, img_size=imgsz, stride=stride, auto=pt)
bs = 1 # batch_size
vid_path, vid_writer = [None] * bs, [None] * bs
# Run inference
# 输入模型推理产生推理结果画出识别框:
# 传入一张空图片到GPU预热
model.warmup(imgsz=(1 if pt else bs, 3, *imgsz)) # warmup
dt, seen = [0.0, 0.0, 0.0], 0
for path, im, im0s, vid_cap, s in dataset:
t1 = time_sync()
# 图片numpy转pytroch支持的格式
im = torch.from_numpy(im).to(device)
im = im.half() if model.fp16 else im.float() # uint8 to fp16/32
# 图片归一化
im /= 255 # 0 - 255 to 0.0 - 1.0
# 扩张维度
if len(im.shape) == 3:
im = im[None] # expand for batch dim
t2 = time_sync()
dt[0] += t2 - t1
# Inference
# 若为true,保存推断过程特征图
visualize = increment_path(save_dir / Path(path).stem, mkdir=True) if visualize else False
pred = model(im, augment=augment, visualize=visualize) # 检测框[1,18900,85]
# [1,18900,85]指4个坐标信息,1个置信度,80个类别概率
# augment可对推断做数据增强,但降低模型运行速度
t3 = time_sync()
dt[1] += t3 - t2
# NMS
# 非极大值过滤
pred = non_max_suppression(pred, conf_thres, iou_thres, classes, agnostic_nms, max_det=max_det) # [1,5,6]
# [1,5,6]: 6指4坐标,1置信度,1类别
dt[2] += time_sync() - t3
# Second-stage classifier (optional)
# pred = utils.general.apply_classifier(pred, classifier_model, im, im0s)
# Process predictions
# det:[5,6],5个矩形框, 6指4坐标,1置信度,1类别
for i, det in enumerate(pred): # per image
# 计数器
seen += 1
if webcam: # batch_size >= 1
p, im0, frame = path[i], im0s[i].copy(), dataset.count
s += f'{i}: '
else:
p, im0, frame = path, im0s.copy(), getattr(dataset, 'frame', 0)
p = Path(p) # to Path
# 图片保存路径
save_path = str(save_dir / p.name) # im.jpg
# 默认不保存txt文件
txt_path = str(save_dir / 'labels' / p.stem) + ('' if dataset.mode == 'image' else f'_{frame}') # im.txt
s += '%gx%g ' % im.shape[2:] # print string
# 获得原图宽高,用于保存txt
gn = torch.tensor(im0.shape)[[1, 0, 1, 0]] # normalization gain whwh
# 判断是否把检测框裁剪保存
imc = im0.copy() if save_crop else im0 # for save_crop
# 原图绘制
annotator = Annotator(im0, line_width=line_thickness, example=str(names))
# 画框
if len(det):
# Rescale boxes from img_size to im0 size
# 从调整图中坐标映射回原图
det[:, :4] = scale_coords(im.shape[2:], det[:, :4], im0.shape).round()
# Print results
# 遍历所有框:n统计所有框用于基于s打印信息
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
# Write results
# 选择保存方式(默认选择第二种,即非txt)
for *xyxy, conf, cls in reversed(det):
if save_txt: # Write to file
xywh = (xyxy2xywh(torch.tensor(xyxy).view(1, 4)) / gn).view(-1).tolist() # normalized xywh
line = (cls, *xywh, conf) if save_conf else (cls, *xywh) # label format
with open(txt_path + '.txt', 'a') as f:
f.write(('%g ' * len(line)).rstrip() % line + '\n')
if save_img or save_crop or view_img: # Add bbox to image
c = int(cls) # integer class
# 是否打印标签、置信度
label = None if hide_labels else (names[c] if hide_conf else f'{names[c]} {conf:.2f}')
# 画框
annotator.box_label(xyxy, label, color=colors(c, True))
# 是否保存截取检测框(默认false)
if save_crop:
save_one_box(xyxy, imc, file=save_dir / 'crops' / names[c] / f'{p.stem}.jpg', BGR=True)
# Stream results
im0 = annotator.result()
if view_img:
cv2.imshow(str(p), im0)
cv2.waitKey(1) # 1 millisecond
# Save results (image with detections)
if save_img:
if dataset.mode == 'image':
cv2.imwrite(save_path, im0)
else: # 'video' or 'stream'
if vid_path[i] != save_path: # new video
vid_path[i] = save_path
if isinstance(vid_writer[i], cv2.VideoWriter):
vid_writer[i].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 = str(Path(save_path).with_suffix('.mp4')) # force *.mp4 suffix on results videos
vid_writer[i] = cv2.VideoWriter(save_path, cv2.VideoWriter_fourcc(*'mp4v'), fps, (w, h))
vid_writer[i].write(im0)
# Print time (inference-only)
LOGGER.info(f'{s}Done. ({t3 - t2:.3f}s)')
# Print results
# 统计预测每张图片平均时间,seen即预测图片数量,dt即每张图片所用时间
t = tuple(x / seen * 1E3 for x in dt) # speeds per image
LOGGER.info(f'Speed: %.1fms pre-process, %.1fms inference, %.1fms NMS per image at shape {(1, 3, *imgsz)}' % t)
if save_txt or save_img:
s = f"\n{len(list(save_dir.glob('labels/*.txt')))} labels saved to {save_dir / 'labels'}" if save_txt else ''
LOGGER.info(f"Results saved to {colorstr('bold', save_dir)}{s}")
if update:
strip_optimizer(weights) # update model (to fix SourceChangeWarning)
# 定参,返回opt(存储所有参数信息)
def parse_opt():
parser = argparse.ArgumentParser()
parser.add_argument('--weights', nargs='+', type=str, default=ROOT / 'runs/train//exp13/weights/best.pt', help='model path(s)')
parser.add_argument('--source', type=str, default=ROOT / 'C:/Users/Pictures/Saved Pictures/read11.avi', help='file/dir/URL/glob, 0 for webcam')
parser.add_argument('--data', type=str, default=ROOT / 'data/coco.yaml', help='(optional) dataset.yaml path')
parser.add_argument('--imgsz', '--img', '--img-size', nargs='+', type=int, default=[960, 540], help='inference size h,w')
parser.add_argument('--conf-thres', type=float, default=0.25, help='confidence threshold')
parser.add_argument('--iou-thres', type=float, default=0.45, help='NMS IoU threshold')
parser.add_argument('--max-det', type=int, default=1000, help='maximum detections per image')
parser.add_argument('--device', default='', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')
parser.add_argument('--view-img', action='store_true', help='show results') # 置信度
parser.add_argument('--save-txt', action='store_true', help='save results to *.txt')
parser.add_argument('--save-conf', action='store_true', help='save confidences in --save-txt labels')
parser.add_argument('--save-crop', action='store_true', help='save cropped prediction boxes')
parser.add_argument('--nosave', action='store_true', help='do not save images/videos')
parser.add_argument('--classes', nargs='+', type=int, help='filter by class: --classes 0, or --classes 0 2 3')
parser.add_argument('--agnostic-nms', action='store_true', help='class-agnostic NMS')
parser.add_argument('--augment', action='store_true', help='augmented inference')
parser.add_argument('--visualize', action='store_true', help='visualize features')
parser.add_argument('--update', action='store_true', help='update all models')
parser.add_argument('--project', default=ROOT / 'runs/detect', help='save results to project/name')
parser.add_argument('--name', default='exp', help='save results to project/name')
parser.add_argument('--exist-ok', action='store_true', help='existing project/name ok, do not increment')
parser.add_argument('--line-thickness', default=3, type=int, help='bounding box thickness (pixels)')
parser.add_argument('--hide-labels', default=False, action='store_true', help='hide labels')
parser.add_argument('--hide-conf', default=False, action='store_true', help='hide confidences')
parser.add_argument('--half', action='store_true', help='use FP16 half-precision inference')
parser.add_argument('--dnn', action='store_true', help='use OpenCV DNN for ONNX inference')
opt = parser.parse_args()
opt.imgsz *= 2 if len(opt.imgsz) == 1 else 1 # expand
print_args(FILE.stem, opt)
return opt
def main(opt):
# 检测requirement中依赖包
check_requirements(exclude=('tensorboard', 'thop'))
run(**vars(opt))
if __name__ == "__main__":
opt = parse_opt()
main(opt)
common.py(models):
DetectMultiBackend: (line279)
w 判断weights是否为list,若是取出第一个值作为传入路径
model_type 判断模型格式(pt、jit等),执行相应加载模式
fp16 半精度推算
if data 加载传入文件,获取names
datasets.py(utils):
LoadImages: (line178)
P: 根据相对路径获得绝对路径
判断是否带*,是否为文件夹,是否为文件
images/videos: 获取文件格式,判断图片格式是否包含在规定拓展名中
nf: 所有文件数
count: 文件中图片计数器,起索引作用
img0: 读入初始图
s: 字符串,表示输入的是第几张图片,用于后续打印
augmentations.py->letterbox)(需要32倍宽高)
vid_cap(None):
Convert:
augmentations.py(utils):
letterbox: (line91)
r: 长边缩放图片,(long/640)
填充图片:
if auto: 若auto(默认true)为true,判断图片宽高是否为32倍数,若满足直接读取
plots.py(utils):
Annotator: (line68)
初始化:
If-else: 默认opencv画框
box_label: 画框画标签
本文谨以用于代码详解笔记,而非项目点评和项目研发,若本文何处理解有误,劳烦广大读者指正。本人才疏学浅,请多包涵。