补全yolov5的代码

This commit is contained in:
2025-03-13 17:48:59 +08:00
parent 6daea23f0a
commit 9d369b9898
42 changed files with 8571 additions and 171 deletions

View File

@ -2,6 +2,14 @@ from sqlalchemy.orm import Session
from typing import List
from fastapi import UploadFile
import subprocess
from yolov5.models.common import DetectMultiBackend
from yolov5.utils.torch_utils import select_device
from yolov5.utils.dataloaders import LoadStreams
from yolov5.utils.general import check_img_size, Profile, non_max_suppression, cv2, scale_boxes
import torch
from pathlib import Path
from ultralytics.utils.plotting import Annotator, colors, save_one_box
import platform
from app.model.crud import project_detect_crud as pdc
from app.model.schemas.project_detect_schemas import ProjectDetectIn, ProjectDetectOut, ProjectDetectLogIn
@ -172,8 +180,96 @@ async def run_commend(weights: str, source: str, project: str, name: str,
pdc.add_detect_imgs(detect_log_imgs, session)
def run_detect_rtsp():
return None
def run_detect_rtsp(weights_pt: str, rtsp_url: str, data: str):
"""
rtsp 视频流推理
:param weights_pt: 权重文件
:param rtsp_url: 视频流地址
:param data: yaml文件
:return:
"""
# 选择设备CPU 或 GPU
device = select_device('cpu')
# 加载模型
model = DetectMultiBackend(weights_pt, device=device, dnn=False, data=data, fp16=False)
stride, names, pt = model.stride, model.names, model.pt
imgsz = check_img_size((640, 640), s=stride) # check image size
dataset = LoadStreams(rtsp_url, img_size=imgsz, stride=stride, auto=pt, vid_stride=1)
bs = len(dataset)
model.warmup(imgsz=(1 if pt or model.triton else bs, 3, *imgsz))
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]:
if model.xml and im.shape[0] > 1:
pred = None
for image in ims:
if pred is None:
pred = model(image, augment=False, visualize=False).unsqueeze(0)
else:
pred = torch.cat((pred, model(image, augment=False, visualize=False).unsqueeze(0)),
dim=0)
pred = [pred, None]
else:
pred = model(im, augment=False, visualize=False)
# NMS
with dt[2]:
pred = non_max_suppression(pred, 0.25, 0.45, None, False, max_det=1000)
# Process predictions
for i, det in enumerate(pred): # per image
seen += 1
p, im0, frame = path[i], im0s[i].copy(), dataset.count
s += f"{i}: "
p = Path(p) # to Path
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 False else im0 # for save_crop
annotator = Annotator(im0, line_width=3, 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 False else f"{names[c]}"
confidence = float(conf)
confidence_str = f"{confidence:.2f}"
c = int(cls) # integer class
label = None if False else (names[c] if False else f"{names[c]} {conf:.2f}")
annotator.box_label(xyxy, label, color=colors(c, True))
# Stream results
im0 = annotator.result()
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