基于yolov5的火焰识别
基于yolov5的火焰识别
1、准备工作
yolov5项目下载
下载yolov5项目代码，其链接为：yolov5项目地址
并且在PC机上配置环境，即正常按照requirements安装依赖包，而后根据自身需要下载相应的权重文件(yolov5s、yolov5m、yolov5l、yolov5x)
数据集的准备
1、根据实际情况可以自身在网上爬取火焰图片
2、通过网上的资料下载相关数据集，大部分数据集是无标注的数据集，此处可参考工控-小白的博客博客地址，其中就有部分火焰识别数据集的下载链接
如下载的数据集无标注，那么使用lableImg进行标注，且将标注文件的保存格式设置为PascalVOC的类型，即xml格式的label文件，而后通过脚本将标签格式转换为.txt文件，并在文件上添加类别信息和对数据进行归一化。脚本脚本代码如下：
import os
import xml.etree.ElementTree as ET
from decimal import Decimal
dirpath = '/home/jiu/data_change/label_0' # 原来存放xml文件的目录
newdir = '/home/jiu/data_change/labels' # 修改label后形成的txt目录
if not os.path.exists(newdir):
os.makedirs(newdir)
for fp in os.listdir(dirpath):
root = ET.parse(os.path.join(dirpath, fp)).getroot()
xmin, ymin, xmax, ymax = 0, 0, 0, 0
sz = root.find('size')
width = float(sz[0].text)
height = float(sz[1].text)
filename = root.find('filename').text
print(fp)
with open(os.path.join(newdir, fp.split('.')[0] + '.txt'), 'a+') as f:
for child in root.findall('object'): # 找到图片中的所有框
sub = child.find('bndbox') # 找到框的标注值并进行读取
sub_label = child.find('name')
xmin = float(sub[0].text)
ymin = float(sub[1].text)
xmax = float(sub[2].text)
ymax = float(sub[3].text)
try: # 转换成yolov的标签格式，需要归一化到（0-1）的范围内
x_center = Decimal(str(round(float((xmin + xmax) / (2 * width)),6))).quantize(Decimal('0.000000'))
y_center = Decimal(str(round(float((ymin + ymax) / (2 * height)),6))).quantize(Decimal('0.000000'))
w = Decimal(str(round(float((xmax - xmin) / width),6))).quantize(Decimal('0.000000'))
h = Decimal(str(round(float((ymax - ymin) / height),6))).quantize(Decimal('0.000000'))
print(str(x_center) + ' ' + str(y_center)+ ' '+str(w)+ ' '+str(h))
#读取需要的标签
if sub_label.text == 'fire':
f.write(' '.join([str(0), str(x_center), str(y_center), str(w), str(h) + '\n']))
except ZeroDivisionError:
print(filename, '的 width有问题')
此处提供本人所使用的火焰数据集，该数据集一共1421张带火焰的图片，并将其分为训练集和测试集，其中训练集1200张，测试集221张；同样的将label也分为训练集和测试集，其图片和其label相对应。
数据集下载地址：Let’s go
txt标签：
xml标签：
将下载后的zip文件解压到项目目录中
项目实现
配置文件修改
新建一个.yaml文件，在其中添加(根据实际情况修改文件路径)：
train: /home/jiu/project/fire_detect/dataset/images/train # train images 1200 images
val: /home/jiu/project/fire_detect/dataset/images/val # val images 221 images
test: # test images (optional)
# Classes
nc: 1 # number of classes
names: [ 'fire' ] # class names
修改train.py以及detect.py
在train.py的parse_opt()函数中，修改’–weights’、’–data’、’–imgsz’等配置，其如下所示：
def parse_opt(known=False):
parser = argparse.ArgumentParser()
parser.add_argument('--weights', type=str, default='yolov5s.pt', help='initial weights path')
parser.add_argument('--cfg', type=str, default='', help='model.yaml path')
parser.add_argument('--data', type=str, default='data/coco128.yaml', help='dataset.yaml path')
parser.add_argument('--hyp', type=str, default='data/hyps/hyp.scratch.yaml', help='hyperparameters path')
parser.add_argument('--epochs', type=int, default=300)
parser.add_argument('--batch-size', type=int, default=8, help='total batch size for all GPUs')
parser.add_argument('--img-size', nargs='+', type=int, default=[320, 320], help='[train, val] image sizes')
parser.add_argument('--rect', action='store_true', help='rectangular training')
parser.add_argument('--resume', nargs='?', const=True, default=False, help='resume most recent training')
parser.add_argument('--nosave', action='store_true', help='only save final checkpoint')
parser.add_argument('--noval', action='store_true', help='only validate final epoch')
parser.add_argument('--noautoanchor', action='store_true', help='disable autoanchor check')
parser.add_argument('--evolve', type=int, nargs='?', const=300, help='evolve hyperparameters for x generations')
parser.add_argument('--bucket', type=str, default='', help='gsutil bucket')
parser.add_argument('--cache-images', action='store_true', help='cache images for faster training')
parser.add_argument('--image-weights', action='store_true', help='use weighted image selection for training')
parser.add_argument('--device', default='', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')
parser.add_argument('--multi-scale', action='store_true', help='vary img-size +/- 50%%')
parser.add_argument('--single-cls', action='store_true', help='train multi-class data as single-class')
parser.add_argument('--adam', action='store_true', help='use torch.optim.Adam() optimizer')
parser.add_argument('--sync-bn', action='store_true', help='use SyncBatchNorm, only available in DDP mode')
parser.add_argument('--workers', type=int, default=8, help='maximum number of dataloader workers')
parser.add_argument('--project', default='runs/train', help='save to project/name')
parser.add_argument('--entity', default=None, help='W&B entity')
parser.add_argument('--name', default='exp', help='save to project/name')
parser.add_argument('--exist-ok', action='store_true', help='existing project/name ok, do not increment')
parser.add_argument('--quad', action='store_true', help='quad dataloader')
parser.add_argument('--linear-lr', action='store_true', help='linear LR')
parser.add_argument('--label-smoothing', type=float, default=0.0, help='Label smoothing epsilon')
parser.add_argument('--upload_dataset', action='store_true', help='Upload dataset as W&B artifact table')
parser.add_argument('--bbox_interval', type=int, default=-1, help='Set bounding-box image logging interval for W&B')
parser.add_argument('--save_period', type=int, default=-1, help='Log model after every "save_period" epoch')
parser.add_argument('--artifact_alias', type=str, default="latest", help='version of dataset artifact to be used')
parser.add_argument('--local_rank', type=int, default=-1, help='DDP parameter, do not modify')
opt = parser.parse_known_args()[0] if known else parser.parse_args()
return opt
即’–weights’：添加yolov5的预训练权重文件，此处使用的是yolov5s.pt。如使用其他预训练权重文件，则在val.py中也应当相应修改
‘–data’：数据集的配置文件，即上面定义的.yaml文件
‘–imgsz’：输入图片的大小
在detect.py的parse_opt()函数中，同样修改’–weights’、’–source’、’–imgsz’等配置，其如下所示：
def parse_opt():
parser = argparse.ArgumentParser()
parser.add_argument('--weights', nargs='+', type=str,
default='/home/jiu/project/fire_detect/runs/train/exp/weights/best.pt',
help='model.pt path(s)')
parser.add_argument('--source', type=str, default='/home/jiu/project/fire_detect/test_images/2.mp4',
help='file/dir/URL/glob, 0 for webcam')
parser.add_argument('--imgsz', '--img', '--img-size', type=int, default=320, help='inference size (pixels)')
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-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: --class 0, or --class 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='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')
opt = parser.parse_args()
return opt
即’–weights’：添加训练好的权重文件
‘–source’：测试图片的路径或测试视频的路径
‘–imgsz’：输入图片的大小
训练过程
1、如在pycharm中运行，可直接运行train.py文件
2、如使用终端运行，则运行指令为：
python train.py --img 320 --batch 16 --epoch 300 --data data/coco128.yaml --cfg models/yolov5s.yaml --weights weights/yolov5s.pt --device '0'
实际测试
图片测试
# -*- coding: UTF-8 -*-
import time
import cv2
import torch
import copy
from models.experimental import attempt_load
from utils.datasets import letterbox
from utils.general import check_img_size, non_max_suppression, scale_coords, xyxy2xywh
def load_model(weights, device):
model = attempt_load(weights, map_location=device) # load FP32 model
return model
def show_results(img, xywh, conf, class_num):
h, w, c = img.shape
labels = ['fire']
tl = 1 or round(0.002 * (h + w) / 2) + 1 # line/font thickness
x1 = int(xywh[0] * w - 0.5 * xywh[2] * w)
y1 = int(xywh[1] * h - 0.5 * xywh[3] * h)
x2 = int(xywh[0] * w + 0.5 * xywh[2] * w)
y2 = int(xywh[1] * h + 0.5 * xywh[3] * h)
cv2.rectangle(img, (x1, y1), (x2, y2), (0, 255, 0), thickness=tl, lineType=cv2.LINE_AA)
tf = max(tl - 1, 1) # font thickness
label = str(labels[int(class_num)]) + ': ' + str(conf)[:5]
cv2.putText(img, label, (x1, y1 - 2), 0, tl / 3, [0, 0, 255], thickness=tf, lineType=cv2.LINE_AA)
return img
def detect_one(model, image_path, device):
# Load model
img_size = 320
conf_thres = 0.3
iou_thres = 0.2
orgimg = cv2.imread(image_path) # BGR
# orgimg = image_path
img0 = copy.deepcopy(orgimg)
assert orgimg is not None, 'Image Not Found ' + image_path
h0, w0 = orgimg.shape[:2] # orig hw
r = img_size / max(h0, w0) # resize image to img_size
if r != 1: # always resize down, only resize up if training with augmentation
interp = cv2.INTER_AREA if r < 1 else cv2.INTER_LINEAR
img0 = cv2.resize(img0, (int(w0 * r), int(h0 * r)), interpolation=interp)
imgsz = check_img_size(img_size, s=model.stride.max()) # check img_size
img = letterbox(img0, new_shape=imgsz)[0]
# Convert
img = img[:, :, ::-1].transpose(2, 0, 1).copy() # BGR to RGB, to 3x416x416
# Run inference
t0 = time.time()
img = torch.from_numpy(img).to(device)
img = 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
pred = model(img)[0]
# Apply NMS
pred = non_max_suppression(pred, conf_thres, iou_thres)
print('pred: ', pred)
print('img.shape: ', img.shape)
print('orgimg.shape: ', orgimg.shape)
# Process detections
for i, det in enumerate(pred): # detections per image
gn = torch.tensor(orgimg.shape)[[1, 0, 1, 0]].to(device) # normalization gain whwh
if len(det):
# Rescale boxes from img_size to im0 size
det[:, :4] = scale_coords(img.shape[2:], det[:, :4], orgimg.shape).round()
# Print results
for c in det[:, -1].unique():
n = (det[:, -1] == c).sum() # detections per class
for j in range(det.size()[0]):
xywh = (xyxy2xywh(torch.tensor(det[j, :4]).view(1, 4)) / gn).view(-1).tolist()
conf = det[j, 4].cpu().numpy()
class_num = det[j, 4].cpu().numpy()
orgimg = show_results(orgimg, xywh, conf, class_num)
# Stream results
print(f'Done. ({time.time() - t0:.3f}s)')
cv2.imshow('orgimg', orgimg)
cv2.imwrite('filename.jpg',orgimg)
if cv2.waitKey(0) == ord('q'): # q to quit
raise StopIteration
if __name__ == '__main__':
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
weights = '/home/jiu/project/fire_detect/runs/train/exp/weights/best.pt'
model = load_model(weights, device)
# using images
image_path = '/home/jiu/project/fire_detect/test_images/1.jpg'
detect_one(model, image_path, device)
print('over')
运行结果：
视频测试
可直接使用detect.py进行测试，其效果如下所示：
yolov5火焰识别
摄像头测试：
# -*- coding: UTF-8 -*-
import time
import cv2
import torch
import copy
from models.experimental import attempt_load
from utils.datasets import letterbox
from utils.general import check_img_size, non_max_suppression, scale_coords, xyxy2xywh
def load_model(weights, device):
model = attempt_load(weights, map_location=device) # load FP32 model
return model
def show_results(img, xywh, conf, class_num):
h, w, c = img.shape
labels = ['fire']
tl = 1 or round(0.002 * (h + w) / 2) + 1 # line/font thickness
x1 = int(xywh[0] * w - 0.5 * xywh[2] * w)
y1 = int(xywh[1] * h - 0.5 * xywh[3] * h)
x2 = int(xywh[0] * w + 0.5 * xywh[2] * w)
y2 = int(xywh[1] * h + 0.5 * xywh[3] * h)
cv2.rectangle(img, (x1, y1), (x2, y2), (0, 255, 0), thickness=tl, lineType=cv2.LINE_AA)
tf = max(tl - 1, 1) # font thickness
label = str(labels[int(class_num)]) + ': ' + str(conf)[:5]
cv2.putText(img, label, (x1, y1 - 2), 0, tl / 3, [0, 0, 255], thickness=tf, lineType=cv2.LINE_AA)
return img
def detect_one(model, image_path, device):
# Load model
img_size = 320
conf_thres = 0.3
iou_thres = 0.2
orgimg = image_path
img0 = copy.deepcopy(orgimg)
assert orgimg is not None, 'Image Not Found ' + image_path
h0, w0 = orgimg.shape[:2] # orig hw
r = img_size / max(h0, w0) # resize image to img_size
if r != 1: # always resize down, only resize up if training with augmentation
interp = cv2.INTER_AREA if r < 1 else cv2.INTER_LINEAR
img0 = cv2.resize(img0, (int(w0 * r), int(h0 * r)), interpolation=interp)
imgsz = check_img_size(img_size, s=model.stride.max()) # check img_size
img = letterbox(img0, new_shape=imgsz)[0]
# Convert
img = img[:, :, ::-1].transpose(2, 0, 1).copy() # BGR to RGB, to 3x416x416
# Run inference
t0 = time.time()
img = torch.from_numpy(img).to(device)
img = 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
pred = model(img)[0]
# Apply NMS
pred = non_max_suppression(pred, conf_thres, iou_thres)
print('pred: ', pred)
print('img.shape: ', img.shape)
print('orgimg.shape: ', orgimg.shape)
# Process detections
for i, det in enumerate(pred): # detections per image
gn = torch.tensor(orgimg.shape)[[1, 0, 1, 0]].to(device) # normalization gain whwh
if len(det):
# Rescale boxes from img_size to im0 size
det[:, :4] = scale_coords(img.shape[2:], det[:, :4], orgimg.shape).round()
# Print results
for c in det[:, -1].unique():
n = (det[:, -1] == c).sum() # detections per class
for j in range(det.size()[0]):
xywh = (xyxy2xywh(torch.tensor(det[j, :4]).view(1, 4)) / gn).view(-1).tolist()
conf = det[j, 4].cpu().numpy()
class_num = det[j, 4].cpu().numpy()
orgimg = show_results(orgimg, xywh, conf, class_num)
# Stream results
print(f'Done. ({time.time() - t0:.3f}s)')
return orgimg
if __name__ == '__main__':
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
weights = '/home/jiu/project/fire_detect/runs/train/exp/weights/best.pt'
model = load_model(weights, device)
# using camera
cap = cv2.VideoCapture(0)
while cap.isOpened():
_, frame = cap.read()
frame = detect_one(model, frame, device)
cv2.imshow("img", frame)
cv2.waitKey(1)
print('over')
这个测试效果就不贴了
最后，整个项目代码下载地址： fire_detect 密码: kwu1