问题描述
我正在使用 Roboflow 的 YOlov5 代码来训练自定义数据集。
我有一个包含对象 1 到 11 的数据集。我成功地获得了良好的结果。我的下一步是在不训练模型的情况下一起识别对象组，并显示结果。
我正在将经过训练的模型部署到 RaspBerry Pi 3B+ 上，并使用 pi 摄像头对其进行实时测试。
我想在检测到物体时在屏幕上显示物体计数，并且还识别出例如三个第 2 类物体和两个第 5 类物体是第 1 组，并将其显示出来。我该怎么做？
请参考以下链接。
谢谢！
这是代码的 google colab 链接： https://colab.research.google.com/drive/1gDZ2xcTOgR39tGGs-EZ6i3RTs16wmzZQ
检测.py：
import argparse
import time
from pathlib import Path
import cv2
import torch
import torch.backends.cudnn as cudnn
from numpy import random
from models.experimental import attempt_load
from utils.datasets import LoadStreams,LoadImages
from utils.general import check_img_size,check_requirements,check_imshow,non_max_suppression,apply_classifier,\
scale_coords,xyxy2xywh,strip_optimizer,set_logging,increment_path
from utils.plots import plot_one_Box
from utils.torch_utils import select_device,load_classifier,time_synchronized
def detect(save_img=False):
source,weights,view_img,save_txt,imgsz = opt.source,opt.weights,opt.view_img,opt.save_txt,opt.img_size
webcam = source.isnumeric() or source.endswith('.txt') or source.lower().startswith(
('rtsp://','rtmp://','http://'))
# Directories
save_dir = Path(increment_path(Path(opt.project) / opt.name,exist_ok=opt.exist_ok)) # increment run
(save_dir / 'labels' if save_txt else save_dir).mkdir(parents=True,exist_ok=True) # make dir
# Initialize
set_logging()
device = select_device(opt.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_size
if half:
model.half() # to FP16
# Second-stage classifier
classify = False
if classify:
modelc = load_classifier(name='resnet101',n=2) # initialize
modelc.load_state_dict(torch.load('weights/resnet101.pt',map_location=device)['model']).to(device).eval()
# Set DataLoader
vid_path,vid_writer = None,None
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)
else:
save_img = True
dataset = LoadImages(source,stride=stride)
# Get names and colors
names = model.module.names if hasattr(model,'module') else model.names
colors = [[random.randint(0,255) for _ in range(3)] for _ in names]
# Run inference
if device.type != 'cpu':
model(torch.zeros(1,3,imgsz,imgsz).to(device).type_as(next(model.parameters()))) # run once
t0 = time.time()
for path,img,im0s,vid_cap in dataset:
img = torch.from_numpy(img).to(device)
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)
# Inference
t1 = time_synchronized()
pred = model(img,augment=opt.augment)[0]
# Apply NMS
pred = non_max_suppression(pred,opt.conf_thres,opt.IoU_thres,classes=opt.classes,agnostic=opt.agnostic_nms)
t2 = time_synchronized()
# Apply Classifier
if classify:
pred = apply_classifier(pred,modelc,im0s)
# Process detections
for i,det in enumerate(pred): # detections per image
if webcam: # batch_size >= 1
p,s,im0,frame = path[i],'%g: ' % i,im0s[i].copy(),dataset.count
else:
p,frame = path,'',getattr(dataset,'frame',0)
p = Path(p) # to Path
save_path = str(save_dir / p.name) # img.jpg
txt_path = str(save_dir / 'labels' / p.stem) + ('' if dataset.mode == 'image' else f'_{frame}') # img.txt
s += '%gx%g ' % img.shape[2:] # print string
gn = torch.tensor(im0.shape)[[1,1,0]] # normalization gain whwh
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
# Write results
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 opt.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 view_img: # Add bBox to image
label = f'{names[int(cls)]} {conf:.2f}'
plot_one_Box(xyxy,label=label,color=colors[int(cls)],line_thickness=3)
# Print time (inference + NMS)
print(f'{s}Done. ({t2 - t1:.3f}s)')
# Stream results
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'
if vid_path != save_path: # new video
vid_path = save_path
if isinstance(vid_writer,cv2.VideoWriter):
vid_writer.release() # release prevIoUs video writer
fourcc = 'mp4v' # output video codec
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))
vid_writer = cv2.VideoWriter(save_path,cv2.VideoWriter_fourcc(*fourcc),fps,(w,h))
vid_writer.write(im0)
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 ''
print(f"Results saved to {save_dir}{s}")
print(f'Done. ({time.time() - t0:.3f}s)')
if __name__ == '__main__':
parser = argparse.ArgumentParser()
parser.add_argument('--weights',nargs='+',type=str,default='yolov5s.pt',help='model.pt path(s)')
parser.add_argument('--source',default='data/images',help='source') # file/folder,0 for webcam
parser.add_argument('--img-size',type=int,default=640,help='inference size (pixels)')
parser.add_argument('--conf-thres',type=float,default=0.25,help='object confidence threshold')
parser.add_argument('--IoU-thres',default=0.45,help='IoU threshold for NMS')
parser.add_argument('--device',default='',help='cuda device,i.e. 0 or 0,2,3 or cpu')
parser.add_argument('--view-img',action='store_true',help='display results')
parser.add_argument('--save-txt',help='save results to *.txt')
parser.add_argument('--save-conf',help='save confidences in --save-txt labels')
parser.add_argument('--classes',help='filter by class: --class 0,or --class 0 2 3')
parser.add_argument('--agnostic-nms',help='class-agnostic NMS')
parser.add_argument('--augment',help='augmented inference')
parser.add_argument('--update',help='update all models')
parser.add_argument('--project',default='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',help='existing project/name ok,do not increment')
opt = parser.parse_args()
print(opt)
check_requirements()
with torch.no_grad():
if opt.update: # update all models (to fix SourceChangeWarning)
for opt.weights in ['yolov5s.pt','yolov5m.pt','yolov5l.pt','yolov5x.pt']:
detect()
strip_optimizer(opt.weights)
else:
detect()
解决方法
暂无找到可以解决该程序问题的有效方法，小编努力寻找整理中！
如果你已经找到好的解决方法，欢迎将解决方案带上本链接一起发送给小编。
小编邮箱:dio#foxmail.com (将#修改为@）