|
|
|
""" |
|
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/Zgi9g1ksQHc' # 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.mlmodel # 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 os |
|
import platform |
|
import sys |
|
from pathlib import Path |
|
|
|
import torch |
|
|
|
FILE = Path(__file__).resolve() |
|
ROOT = FILE.parents[0] |
|
if str(ROOT) not in sys.path: |
|
sys.path.append(str(ROOT)) |
|
ROOT = Path(os.path.relpath(ROOT, Path.cwd())) |
|
|
|
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.plots import Annotator, colors, save_one_box |
|
from utils.torch_utils import select_device, smart_inference_mode |
|
|
|
|
|
@smart_inference_mode() |
|
def run( |
|
weights=ROOT / "yolov5s.pt", |
|
source=ROOT / "data/images", |
|
data=ROOT / "data/coco128.yaml", |
|
imgsz=(640, 640), |
|
conf_thres=0.25, |
|
iou_thres=0.45, |
|
max_det=1000, |
|
device="", |
|
view_img=False, |
|
save_txt=False, |
|
save_conf=False, |
|
save_crop=False, |
|
nosave=False, |
|
classes=None, |
|
agnostic_nms=False, |
|
augment=False, |
|
visualize=False, |
|
update=False, |
|
project=ROOT / "runs/detect", |
|
name="exp", |
|
exist_ok=False, |
|
line_thickness=3, |
|
hide_labels=False, |
|
hide_conf=False, |
|
half=False, |
|
dnn=False, |
|
vid_stride=1, |
|
): |
|
source = str(source) |
|
save_img = not nosave and not source.endswith( |
|
".txt" |
|
) |
|
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) |
|
|
|
|
|
save_dir = increment_path( |
|
Path(project) / name, exist_ok=exist_ok |
|
) |
|
(save_dir / "labels" if save_txt else save_dir).mkdir( |
|
parents=True, exist_ok=True |
|
) |
|
|
|
|
|
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) |
|
|
|
|
|
bs = 1 |
|
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 |
|
|
|
|
|
model.warmup(imgsz=(1 if pt or model.triton else bs, 3, *imgsz)) |
|
seen, windows, dt = 0, [], (Profile(), Profile(), Profile()) |
|
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() |
|
im /= 255 |
|
if len(im.shape) == 3: |
|
im = im[None] |
|
|
|
|
|
with dt[1]: |
|
visualize = ( |
|
increment_path(save_dir / Path(path).stem, mkdir=True) |
|
if visualize |
|
else False |
|
) |
|
pred = model(im, augment=augment, visualize=visualize) |
|
|
|
|
|
with dt[2]: |
|
pred = non_max_suppression( |
|
pred, |
|
conf_thres, |
|
iou_thres, |
|
classes, |
|
agnostic_nms, |
|
max_det=max_det, |
|
) |
|
|
|
|
|
|
|
|
|
|
|
for i, det in enumerate(pred): |
|
seen += 1 |
|
if webcam: |
|
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) |
|
save_path = str(save_dir / p.name) |
|
txt_path = str(save_dir / "labels" / p.stem) + ( |
|
"" if dataset.mode == "image" else f"_{frame}" |
|
) |
|
s += "%gx%g " % im.shape[2:] |
|
gn = torch.tensor(im0.shape)[ |
|
[1, 0, 1, 0] |
|
] |
|
imc = im0.copy() if save_crop else im0 |
|
annotator = Annotator( |
|
im0, line_width=line_thickness, example=str(names) |
|
) |
|
results = [] |
|
if len(det): |
|
|
|
det[:, :4] = scale_boxes( |
|
im.shape[2:], det[:, :4], im0.shape |
|
).round() |
|
results.append((path, det)) |
|
|
|
return results |
|
|