# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
"""
Run YOLOv5 detection inference on images, videos, directories, globs, YouTube, webcam, streams, etc.
Usage - sources:
$ python detect.py --weights yolov5s.pt --source 0 # webcam
img.jpg # image
vid.mp4 # video
screen # screenshot
path/ # directory
list.txt # list of images
list.streams # list of streams
'path/*.jpg' # glob
'https://youtu.be/LNwODJXcvt4' # YouTube
'rtsp://example.com/media.mp4' # RTSP, RTMP, HTTP stream
Usage - formats:
$ python detect.py --weights yolov5s.pt # PyTorch
yolov5s.torchscript # TorchScript
yolov5s.onnx # ONNX Runtime or OpenCV DNN with --dnn
yolov5s_openvino_model # OpenVINO
yolov5s.engine # TensorRT
yolov5s.mlpackage # CoreML (macOS-only)
yolov5s_saved_model # TensorFlow SavedModel
yolov5s.pb # TensorFlow GraphDef
yolov5s.tflite # TensorFlow Lite
yolov5s_edgetpu.tflite # TensorFlow Edge TPU
yolov5s_paddle_model # PaddlePaddle
"""
import argparse
import csv
import os
import platform
import sys
from pathlib import Path
import torch
FILE = Path(__file__).resolve()
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 ultralytics.utils.plotting import Annotator, colors, save_one_box
from models.common import DetectMultiBackend
from utils.dataloaders import IMG_FORMATS, VID_FORMATS, LoadImages, LoadScreenshots, LoadStreams
from utils.general import (
LOGGER,
Profile,
check_file,
check_img_size,
check_imshow,
check_requirements,
colorstr,
cv2,
increment_path,
non_max_suppression,
print_args,
scale_boxes,
strip_optimizer,
xyxy2xywh,
)
from utils.torch_utils import select_device, smart_inference_mode
# 新增：计算IOU函数
def calculate_iou(box1, box2):
"""计算两个边界框的IOU"""
x1, y1, x2, y2 = box1
x1g, y1g, x2g, y2g = box2
# 计算交集区域
xA = max(x1, x1g)
yA = max(y1, y1g)
xB = min(x2, x2g)
yB = min(y2, y2g)
# 计算交集面积
inter_area = max(0, xB - xA + 1) * max(0, yB - yA + 1)
# 计算并集面积
box1_area = (x2 - x1 + 1) * (y2 - y1 + 1)
box2_area = (x2g - x1g + 1) * (y2g - y1g + 1)
union_area = float(box1_area + box2_area - inter_area)
# 计算IOU
iou = inter_area / union_area
return iou
# 新增：计算准确率函数
def calculate_accuracy(gt_labels, pred_detections, iou_threshold=0.5):
"""计算目标检测的准确率"""
correct_predictions = 0
total_gt_objects = 0
total_pred_objects = 0
for img_name in gt_labels:
if img_name not in pred_detections:
continue
gt_boxes = gt_labels[img_name]
pred_boxes = pred_detections[img_name]
total_gt_objects += len(gt_boxes)
total_pred_objects += len(pred_boxes)
# 标记已匹配的真实标签
gt_matched = [False] * len(gt_boxes)
for pred_box in pred_boxes:
pred_class, pred_bbox, pred_conf = pred_box
best_iou = 0
best_gt_idx = -1
# 寻找最佳匹配的真实标签
for i, gt_box in enumerate(gt_boxes):
gt_class, gt_bbox = gt_box
if gt_matched[i]:
continue
iou = calculate_iou(pred_bbox, gt_bbox)
if iou > best_iou and pred_class == gt_class:
best_iou = iou
best_gt_idx = i
# 如果IOU超过阈值且类别正确，则计为正确预测
if best_gt_idx != -1 and best_iou >= iou_threshold:
correct_predictions += 1
gt_matched[best_gt_idx] = True
# 避免除零错误
if total_gt_objects == 0:
return 0.0
# 计算准确率
return correct_predictions / total_gt_objects
@smart_inference_mode()
def run(
weights=ROOT / "yolov5s.pt", # model path or triton URL
source=ROOT / "data/images", # file/dir/URL/glob/screen/0(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_format=0, # save boxes coordinates in YOLO format or Pascal-VOC format (0 for YOLO and 1 for Pascal-VOC)
save_csv=False, # save results in CSV format
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
vid_stride=1, # video frame-rate stride
gt_dir="", # 新增：真实标签目录
eval_interval=10, # 新增：评估间隔帧数
):
"""
Runs YOLOv5 detection inference on various sources like images, videos, directories, streams, etc.
Args:
weights (str | Path): Path to the model weights file or a Triton URL. Default is 'yolov5s.pt'.
source (str | Path): Input source, which can be a file, directory, URL, glob pattern, screen capture, or webcam
index. Default is 'data/images'.
data (str | Path): Path to the dataset YAML file. Default is 'data/coco128.yaml'.
imgsz (tuple[int, int]): Inference image size as a tuple (height, width). Default is (640, 640).
conf_thres (float): Confidence threshold for detections. Default is 0.25.
iou_thres (float): Intersection Over Union (IOU) threshold for non-max suppression. Default is 0.45.
max_det (int): Maximum number of detections per image. Default is 1000.
device (str): CUDA device identifier (e.g., '0' or '0,1,2,3') or 'cpu'. Default is an empty string, which uses the
best available device.
view_img (bool): If True, display inference results using OpenCV. Default is False.
save_txt (bool): If True, save results in a text file. Default is False.
save_format (int): Whether to save boxes coordinates in YOLO format or Pascal-VOC format. Default is 0.
save_csv (bool): If True, save results in a CSV file. Default is False.
save_conf (bool): If True, include confidence scores in the saved results. Default is False.
save_crop (bool): If True, save cropped prediction boxes. Default is False.
nosave (bool): If True, do not save inference images or videos. Default is False.
classes (list[int]): List of classes to filter detections by. Default is None.
agnostic_nms (bool): If True, perform class-agnostic non-max suppression. Default is False.
augment (bool): If True, use augmented inference. Default is False.
visualize (bool): If True, visualize feature maps. Default is False.
update (bool): If True, update all models' weights. Default is False.
project (str | Path): Directory to save results. Default is 'runs/detect'.
name (str): Name of the current experiment; used to create a subdirectory within 'project'. Default is 'exp'.
exist_ok (bool): If True, existing directories with the same name are reused instead of being incremented. Default is
False.
line_thickness (int): Thickness of bounding box lines in pixels. Default is 3.
hide_labels (bool): If True, do not display labels on bounding boxes. Default is False.
hide_conf (bool): If True, do not display confidence scores on bounding boxes. Default is False.
half (bool): If True, use FP16 half-precision inference. Default is False.
dnn (bool): If True, use OpenCV DNN backend for ONNX inference. Default is False.
vid_stride (int): Stride for processing video frames, to skip frames between processing. Default is 1.
gt_dir (str): 新增：真实标签目录路径
eval_interval (int): 新增：每隔多少帧计算一次准确率
Returns:
None
"""
source = str(source)
save_img = not nosave and not source.endswith(".txt") # save inference images
is_file = Path(source).suffix[1:] in (IMG_FORMATS + VID_FORMATS)
is_url = source.lower().startswith(("rtsp://", "rtmp://", "http://", "https://"))
webcam = source.isnumeric() or source.endswith(".streams") or (is_url and not is_file)
screenshot = source.lower().startswith("screen")
if is_url and is_file:
source = check_file(source) # download
# 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
# 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
# Dataloader
bs = 1 # batch_size
if webcam:
view_img = check_imshow(warn=True)
dataset = LoadStreams(source, img_size=imgsz, stride=stride, auto=pt, vid_stride=vid_stride)
bs = len(dataset)
elif screenshot:
dataset = LoadScreenshots(source, img_size=imgsz, stride=stride, auto=pt)
else:
dataset = LoadImages(source, img_size=imgsz, stride=stride, auto=pt, vid_stride=vid_stride)
vid_path, vid_writer = [None] * bs, [None] * bs
# 新增：加载真实标签数据
gt_labels = {}
if gt_dir:
gt_dir = Path(gt_dir)
for txt_file in gt_dir.glob("*.txt"):
img_name = txt_file.stem
gt_labels[img_name] = []
with open(txt_file, "r") as f:
for line in f:
parts = line.strip().split()
if len(parts) >= 5:
cls = int(parts[0])
# 将YOLO格式转换为xyxy格式
x, y, w, h = map(float, parts[1:5])
# 假设真实标签对应的图像尺寸与输入图像一致
x1 = (x - w/2) * imgsz[1]
y1 = (y - h/2) * imgsz[0]
x2 = (x + w/2) * imgsz[1]
y2 = (y + h/2) * imgsz[0]
gt_labels[img_name].append((cls, (x1, y1, x2, y2)))
# 新增：收集预测结果
pred_detections = {}
frame_count = 0
accuracy = 0.0 # 初始化准确率
# Run inference
model.warmup(imgsz=(1 if pt or model.triton else bs, 3, *imgsz)) # warmup
seen, windows, dt = 0, [], (Profile(device=device), Profile(device=device), Profile(device=device))
for path, im, im0s, vid_cap, s in dataset:
with dt[0]:
im = torch.from_numpy(im).to(model.device)
im = im.half() if model.fp16 else im.float() # uint8 to fp16/32
im /= 255 # 0 - 255 to 0.0 - 1.0
if len(im.shape) == 3:
im = im[None] # expand for batch dim
if model.xml and im.shape[0] > 1:
ims = torch.chunk(im, im.shape[0], 0)
# Inference
with dt[1]:
visualize = increment_path(save_dir / Path(path).stem, mkdir=True) if visualize else False
if model.xml and im.shape[0] > 1:
pred = None
for image in ims:
if pred is None:
pred = model(image, augment=augment, visualize=visualize).unsqueeze(0)
else:
pred = torch.cat((pred, model(image, augment=augment, visualize=visualize).unsqueeze(0)), dim=0)
pred = [pred, None]
else:
pred = model(im, augment=augment, visualize=visualize)
# NMS
with dt[2]:
pred = non_max_suppression(pred, conf_thres, iou_thres, classes, agnostic_nms, max_det=max_det)
# Second-stage classifier (optional)
# pred = utils.general.apply_classifier(pred, classifier_model, im, im0s)
# Define the path for the CSV file
csv_path = save_dir / "predictions.csv"
# Create or append to the CSV file
def write_to_csv(image_name, prediction, confidence):
"""Writes prediction data for an image to a CSV file, appending if the file exists."""
data = {"Image Name": image_name, "Prediction": prediction, "Confidence": confidence}
file_exists = os.path.isfile(csv_path)
with open(csv_path, mode="a", newline="") as f:
writer = csv.DictWriter(f, fieldnames=data.keys())
if not file_exists:
writer.writeheader()
writer.writerow(data)
# Process predictions
for i, det in enumerate(pred): # per image
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
save_path = str(save_dir / p.name) # im.jpg
txt_path = str(save_dir / "labels" / p.stem) + ("" if dataset.mode == "image" else f"_{frame}") # im.txt
s += "{:g}x{:g} ".format(*im.shape[2:]) # print string
gn = torch.tensor(im0.shape)[[1, 0, 1, 0]] # normalization gain whwh
imc = im0.copy() if save_crop else im0 # for save_crop
annotator = Annotator(im0, line_width=line_thickness, example=str(names))
if len(det):
# Rescale boxes from img_size to im0 size
det[:, :4] = scale_boxes(im.shape[2:], det[:, :4], im0.shape).round()
# Print results
for c in det[:, 5].unique():
n = (det[:, 5] == c).sum() # detections per class
s += f"{n} {names[int(c)]}{'s' * (n > 1)}, " # add to string
# Write results
for *xyxy, conf, cls in reversed(det):
c = int(cls) # integer class
label = names[c] if hide_conf else f"{names[c]}"
confidence = float(conf)
confidence_str = f"{confidence:.2f}"
if save_csv:
write_to_csv(p.name, label, confidence_str)
if save_txt: # Write to file
if save_format == 0:
coords = (
(xyxy2xywh(torch.tensor(xyxy).view(1, 4)) / gn).view(-1).tolist()
) # normalized xywh
else:
coords = (torch.tensor(xyxy).view(1, 4) / gn).view(-1).tolist() # xyxy
line = (cls, *coords, conf) if save_conf else (cls, *coords) # label format
with open(f"{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
label = None if hide_labels else (names[c] if hide_conf else f"{names[c]} {conf:.2f}")
annotator.box_label(xyxy, label, color=colors(c, True))
if save_crop:
save_one_box(xyxy, imc, file=save_dir / "crops" / names[c] / f"{p.stem}.jpg", BGR=True)
# 新增：收集预测结果
img_name = p.stem
pred_detections[img_name] = []
if len(det):
for *xyxy, conf, cls in det:
c = int(cls)
x1, y1, x2, y2 = map(int, xyxy)
pred_detections[img_name].append((c, (x1, y1, x2, y2), float(conf)))
# 新增：定期计算准确率并显示
frame_count += 1
if gt_dir and frame_count % eval_interval == 0:
accuracy = calculate_accuracy(gt_labels, pred_detections)
if save_img or view_img:
accuracy_text = f"Accuracy: {accuracy:.2f}"
annotator.text((10, 30), accuracy_text, txt_color=(255, 255, 255))
im0 = annotator.result()
# Stream results
im0 = annotator.result()
if view_img:
if platform.system() == "Linux" and p not in windows:
windows.append(p)
cv2.namedWindow(str(p), cv2.WINDOW_NORMAL | cv2.WINDOW_KEEPRATIO) # allow window resize (Linux)
cv2.resizeWindow(str(p), im0.shape[1], im0.shape[0])
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}{'' if len(det) else '(no detections), '}{dt[1].dt * 1e3:.1f}ms")
# 新增：在终端输出最终准确率
if gt_dir:
accuracy = calculate_accuracy(gt_labels, pred_detections)
LOGGER.info(f"Overall Accuracy: {accuracy:.4f}")
# Print results
t = tuple(x.t / 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[0]) # update model (to fix SourceChangeWarning)
def parse_opt():
"""
Parse command-line arguments for YOLOv5 detection, allowing custom inference options and model configurations.
Args:
--weights (str | list[str], optional): Model path or triton URL. Defaults to ROOT / 'yolov5s.pt'.
--source (str, optional): File/dir/URL/glob/screen/0(webcam). Defaults to ROOT / 'data/images'.
--data (str, optional): Dataset YAML path. Provides dataset configuration information.
--imgsz (list[int], optional): Inference size (height, width). Defaults to [640].
--conf-thres (float, optional): Confidence threshold. Defaults to 0.25.
--iou-thres (float, optional): NMS IoU threshold. Defaults to 0.45.
--max-det (int, optional): Maximum number of detections per image. Defaults to 1000.
--device (str, optional): CUDA device, i.e. 0 or 0,1,2,3 or cpu. Defaults to "".
--view-img (bool, optional): Flag to display results. Default is False.
--save-txt (bool, optional): Flag to save results to *.txt files. Default is False.
--save-format (int, optional): Whether to save boxes coordinates in YOLO format or Pascal-VOC format. Default is 0.
--save-csv (bool, optional): Flag to save results in CSV format. Default is False.
--save-conf (bool, optional): Flag to save confidences in labels saved via --save-txt. Default is False.
--save-crop (bool, optional): Flag to save cropped prediction boxes. Default is False.
--nosave (bool, optional): Flag to prevent saving images/videos. Default is False.
--classes (list[int], optional): List of classes to filter results by. Default is None.
--agnostic-nms (bool, optional): Flag for class-agnostic NMS. Default is False.
--augment (bool, optional): Flag for augmented inference. Default is False.
--visualize (bool, optional): Flag for visualizing features. Default is False.
--update (bool, optional): Flag to update all models in the model directory. Default is False.
--project (str, optional): Directory to save results. Default is ROOT / 'runs/detect'.
--name (str, optional): Sub-directory name for saving results within --project. Default is 'exp'.
--exist-ok (bool, optional): Flag to allow overwriting if the project/name already exists. Default is False.
--line-thickness (int, optional): Thickness (in pixels) of bounding boxes. Default is 3.
--hide-labels (bool, optional): Flag to hide labels in the output. Default is False.
--hide-conf (bool, optional): Flag to hide confidences in the output. Default is False.
--half (bool, optional): Flag to use FP16 half-precision inference. Default is False.
--dnn (bool, optional): Flag to use OpenCV DNN for ONNX inference. Default is False.
--vid-stride (int, optional): Video frame-rate stride. Default is 1.
--gt-dir (str, optional): 新增：真实标签目录路径
--eval-interval (int, optional): 新增：每隔多少帧计算一次准确率
Returns:
argparse.Namespace: Parsed command-line arguments as an argparse.Namespace object.
"""
parser = argparse.ArgumentParser()
parser.add_argument("--weights", nargs="+", type=str, default=ROOT / "yolov5s.pt", help="model path or triton URL")
parser.add_argument("--source", type=str, default=ROOT / "data/images", help="file/dir/URL/glob/screen/0(webcam)")
parser.add_argument("--data", type=str, default=ROOT / "data/coco128.yaml", help="(optional) dataset.yaml path")
parser.add_argument("--imgsz", "--img", "--img-size", nargs="+", type=int, default=[640], 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")
parser.add_argument("--save-txt", action="store_true", help="save results to *.txt")
parser.add_argument(
"--save-format",
type=int,
default=0,
help="whether to save boxes coordinates in YOLO format or Pascal-VOC format when save-txt is True, 0 for YOLO and 1 for Pascal-VOC",
)
parser.add_argument("--save-csv", action="store_true", help="save results in CSV format")
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")
parser.add_argument("--vid-stride", type=int, default=1, help="video frame-rate stride")
# 新增参数
parser.add_argument("--gt-dir", type=str, default="", help="ground truth labels directory")
parser.add_argument("--eval-interval", type=int, default=10, help="evaluate accuracy every N frames")
opt = parser.parse_args()
opt.imgsz *= 2 if len(opt.imgsz) == 1 else 1 # expand
print_args(vars(opt))
return opt
def main(opt):
"""
Executes YOLOv5 model inference based on provided command-line arguments, validating dependencies before running.
Args:
opt (argparse.Namespace): Command-line arguments for YOLOv5 detection.
Returns:
None
"""
check_requirements(ROOT / "requirements.txt", exclude=("tensorboard", "thop"))
run(**vars(opt))
if __name__ == "__main__":
opt = parse_opt()
main(opt)代码如上。yolov5在detect.py得到有类别和置信度标注的视频和图片，请问我如何操作，才能在有类别和置信度标注的视频和图片的基础上，在视频或图片中显示识别准确率Accuracy。请给出修改后的完整代码（尽量少修改，不要改变代码的其他地方），要求直接在vscode点击运行即可生成显示识别准确率Accuracy的视频或图片
探讨了在Java中使用File类的exists()方法时，遇到的问题与解决方案，尤其是在user.dir变化时，如何避免文件路径指向错误。建议使用绝对路径确保文件操作的一致性和准确性。
扫一扫
3850
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
