yolov5 口罩检测flask部署
- 这个报错不知道怎么解决，网上查了解决方案加 import matplotlib 和 matplotlib.use(‘Agg’) 还是没用。不过只是关闭界面才出现的，应该不影响使用。
OSError: [Errno 41] Protocol wrong type for socket
Assertion failed: (NSViewIsCurrentlyBuildingLayerTreeForDisplay() != currentlyBuildingLayerTree), function NSViewSetCurrentlyBuildingLayerTreeForDisplay, file /System/Volumes/Data/SWE/macOS/BuildRoots/e90674e518/Library/Caches/com.apple.xbs/Sources/AppKit/AppKit-2022.50.114/AppKit.subproj/NSView.m, line 13412.
Process finished with exit code 132 (interrupted by signal 4: SIGILL)
使用手机摄像头通过 rtsp 推流
省了三百块钱去买摄像头做毕设
- 安卓机下载 ip 摄像头
- 设置-用户名全删掉-密码全删掉-无客户端关闭摄像头选项关闭-打开后启动rtsp 服务器开启-返回-打开摄像头服务器-勾选 rtsp-后面的地址即为所需
参考资料
阿里云Ubuntu 部署
github flask yolov3 部署
flask 在浏览器中播放rtsp实时流
用 google colab 部署（未成功）
因为在上面不能使用 cv2.imshow，好像用的是 别的-imshow包，所以不能实时显示。。会出现一直显示帧画面往下更新而不是覆盖原来帧的实时画面，后面就没整了。但是一帧一帧的结果信息还是会输出的，只是没画面。且结果也会保存在 google 硬盘上。
使用 google colab 调用摄像头
from IPython.display import display, Javascript
from google.colab.output import eval_js
from base64 import b64decode
def take_photo(filename='photo.jpg', quality=0.8):
js = Javascript('''
async function takePhoto(quality) {
const div = document.createElement('div');
const capture = document.createElement('button');
capture.textContent = 'Capture';
div.appendChild(capture);
const video = document.createElement('video');
video.style.display = 'block';
const stream = await navigator.mediaDevices.getUserMedia({video: true});
document.body.appendChild(div);
div.appendChild(video);
video.srcObject = stream;
await video.play();
// Resize the output to fit the video element.
google.colab.output.setIframeHeight(document.documentElement.scrollHeight, true);
// Wait for Capture to be clicked.
await new Promise((resolve) => capture.onclick = resolve);
const canvas = document.createElement('canvas');
canvas.width = video.videoWidth;
canvas.height = video.videoHeight;
canvas.getContext('2d').drawImage(video, 0, 0);
stream.getVideoTracks()[0].stop();
div.remove();
return canvas.toDataURL('image/jpeg', quality);
}
''')
display(js)
data = eval_js('takePhoto({})'.format(quality))
binary = b64decode(data.split(',')[1])
with open(filename, 'wb') as f:
f.write(binary)
return filename
from IPython.display import Image
try:
filename = take_photo()
print('Saved to {}'.format(filename))
# Show the image which was just taken.
display(Image(filename))
except Exception as err:
# Errors will be thrown if the user does not have a webcam or if they do not
# grant the page permission to access it.
print(str(err))
只能调用电脑摄像头
from flask import Flask, render_template, Response
import argparse
from pathlib import Path
import os
import cv2
import torch
import torch.backends.cudnn as cudnn
from numpy import random
import numpy as np
import sys
from models.common import DetectMultiBackend
from utils.datasets import IMG_FORMATS, VID_FORMATS, LoadImages, LoadStreams
from utils.general import (LOGGER, check_file, check_img_size, check_imshow, check_requirements, colorstr,
increment_path, non_max_suppression, print_args, scale_coords, strip_optimizer, xyxy2xywh)
from utils.plots import Annotator, colors, save_one_box
from utils.torch_utils import select_device, time_sync
'''
***模型初始化***
'''
@torch.no_grad()
def model_load(weights="/Users/sinkarsenic/Downloads/mask_detect/权重/best.pt", # model.pt path(s)
device='cpu', # cuda device, i.e. 0 or 0,1,2,3 or cpu
half=False, # use FP16 half-precision inference
dnn=False, # use OpenCV DNN for ONNX inference
):
device = select_device(device)
half &= device.type != 'cpu' # half precision only supported on CUDA
device = select_device(device)
model = DetectMultiBackend(weights, device=device, dnn=dnn)
stride, names, pt, jit, onnx = model.stride, model.names, model.pt, model.jit, model.onnx
# Half
half &= pt and device.type != 'cpu' # half precision only supported by PyTorch on CUDA
if pt:
model.model.half() if half else model.model.float()
print("模型加载完成!")
return model
app = Flask(__name__, static_url_path='',
static_folder='static',
template_folder='templates')
@app.route('/')
def index():
return render_template('index.html')
def gen():
model = model_load()
device = select_device('cpu')
imgsz = [640, 640] # inference size (pixels)
conf_thres = 0.25 # confidence threshold
iou_thres = 0.45 # NMS IOU threshold
max_det = 1000 # maximum detections per image
view_img = False # show results
save_txt = False # save results to *.txt
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 # ugmented inference
visualize = False # visualize features
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
source = str(0)
webcam = True
stride, names, pt, jit, onnx = model.stride, model.names, model.pt, model.jit, model.onnx
imgsz = check_img_size(imgsz, s=stride) # check image size
save_img = not nosave and not source.endswith('.txt') # save inference images
# Dataloader
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, auto=pt and not jit)
bs = len(dataset) # batch_size
else:
dataset = LoadImages(source, img_size=imgsz, stride=stride, auto=pt and not jit)
bs = 1 # batch_size
vid_path, vid_writer = [None] * bs, [None] * bs
# Run inference
if pt and device.type != "cpu":
model(torch.zeros(1, 3, *imgsz).to(device).type_as(next(model.model.parameters()))) # warmup
dt, seen = [0.0, 0.0, 0.0], 0
for path, im, im0s, vid_cap, s in dataset:
t1 = time_sync()
im = torch.from_numpy(im).to(device)
im = im.half() if half 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
t2 = time_sync()
dt[0] += t2 - t1
# Inference
# visualize = increment_path(save_dir / Path(path).stem, mkdir=True) if visualize else False
pred = model(im, augment=augment, visualize=visualize)
t3 = time_sync()
dt[1] += t3 - t2
# NMS
pred = non_max_suppression(pred, conf_thres, iou_thres, classes, agnostic_nms, max_det=max_det)
dt[2] += time_sync() - t3
# Second-stage classifier (optional)
# pred = utils.general.apply_classifier(pred, classifier_model, im, im0s)
# 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 += '%gx%g ' % 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_coords(im.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 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 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)
# Print time (inference-only)
LOGGER.info(f'{s}Done. ({t3 - t2:.3f}s)')
# Stream results
im0 = annotator.result()
if view_img:
cv2.imshow(str(p), im0)
cv2.waitKey(1) # 1 millisecond
cv2.imwrite('frame.jpg', im0)
yield (b'--frame\r\n'
b'Content-Type: image/jpeg\r\n\r\n' + open('frame.jpg', 'rb').read() + b'\r\n')
# String results
print(s)
# wait key to break
if cv2.waitKey(1) & 0xFF == ord('q'):
break
@app.route('/video_feed')
def video_feed():
return Response(gen(),
mimetype='multipart/x-mixed-replace; boundary=frame')
if __name__ == '__main__':
parser = argparse.ArgumentParser()
parser.add_argument('--weights', nargs='+', type=str, default='/Users/sinkarsenic/Downloads/mask_detect/权重/best.pt', help='model.pt path(s)')
parser.add_argument('--source', type=str, default='0', 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=0.15, help='object confidence threshold')
parser.add_argument('--iou-thres', type=float, default=0.45, help='IOU threshold for NMS')
parser.add_argument('--device', default='', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')
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('--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('--frame-rate', default=0, type=int, help='sample rate')
opt = parser.parse_args()
app.run(debug=True)
使用 rtsp 推流
用的是伊拉克电视台的
from flask import Flask, render_template, Response
import argparse
from pathlib import Path
import os
import cv2
import torch
import torch.backends.cudnn as cudnn
from numpy import random
import numpy as np
import sys
from models.common import DetectMultiBackend
from utils.datasets import IMG_FORMATS, VID_FORMATS, LoadImages, LoadStreams
from utils.general import (LOGGER, check_file, check_img_size, check_imshow, check_requirements, colorstr,
increment_path, non_max_suppression, print_args, scale_coords, strip_optimizer, xyxy2xywh)
from utils.plots import Annotator, colors, save_one_box
from utils.torch_utils import select_device, time_sync
'''
***模型初始化***
'''
@torch.no_grad()
def model_load(weights="/Users/sinkarsenic/Downloads/mask_detect/权重/best.pt", # model.pt path(s)
device='cpu', # cuda device, i.e. 0 or 0,1,2,3 or cpu
half=False, # use FP16 half-precision inference
dnn=False, # use OpenCV DNN for ONNX inference
):
device = select_device(device)
half &= device.type != 'cpu' # half precision only supported on CUDA
device = select_device(device)
model = DetectMultiBackend(weights, device=device, dnn=dnn)
stride, names, pt, jit, onnx = model.stride, model.names, model.pt, model.jit, model.onnx
# Half
half &= pt and device.type != 'cpu' # half precision only supported by PyTorch on CUDA
if pt:
model.model.half() if half else model.model.float()
print("模型加载完成!")
return model
app = Flask(__name__, static_url_path='',
static_folder='static',
template_folder='templates')
@app.route('/')
def index():
return render_template('index.html')
def gen():
model = model_load()
sourse = "rtmp://ns8.indexforce.com/home/mystream"
device = select_device('cpu')
imgsz = [640, 640] # inference size (pixels)
conf_thres = 0.25 # confidence threshold
iou_thres = 0.45 # NMS IOU threshold
max_det = 1000 # maximum detections per image
view_img = False # show results
save_txt = False # save results to *.txt
save_conf = False # save confidences in --save-txt labels
save_crop = False # save cropped prediction boxes
nosave = True # 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 # ugmented inference
visualize = False # visualize features
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
source = str(sourse)
#webcam = False
stride, names, pt, jit, onnx = model.stride, model.names, model.pt, model.jit, model.onnx
imgsz = check_img_size(imgsz, s=stride) # check image size
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('.txt') or (is_url and not is_file)
if is_url and is_file:
source = check_file(source) # download
# Dataloader
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, auto=pt and not jit)
bs = len(dataset) # batch_size
else:
dataset = LoadImages(source, img_size=imgsz, stride=stride, auto=pt and not jit)
bs = 1 # batch_size
vid_path, vid_writer = [None] * bs, [None] * bs
# Run inference
if pt and device.type != "cpu":
model(torch.zeros(1, 3, *imgsz).to(device).type_as(next(model.model.parameters()))) # warmup
dt, seen = [0.0, 0.0, 0.0], 0
for path, im, im0s, vid_cap, s in dataset:
t1 = time_sync()
im = torch.from_numpy(im).to(device)
im = im.half() if half 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
t2 = time_sync()
dt[0] += t2 - t1
# Inference
# visualize = increment_path(save_dir / Path(path).stem, mkdir=True) if visualize else False
pred = model(im, augment=augment, visualize=visualize)
t3 = time_sync()
dt[1] += t3 - t2
# NMS
pred = non_max_suppression(pred, conf_thres, iou_thres, classes, agnostic_nms, max_det=max_det)
dt[2] += time_sync() - t3
# Second-stage classifier (optional)
# pred = utils.general.apply_classifier(pred, classifier_model, im, im0s)
# 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 += '%gx%g ' % 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_coords(im.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 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 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)
# Print time (inference-only)
LOGGER.info(f'{s}Done. ({t3 - t2:.3f}s)')
# Stream results
im0 = annotator.result()
if view_img:
cv2.imshow(str(p), im0)
cv2.waitKey(1) # 1 millisecond
cv2.imwrite('frame.jpg', im0)
yield (b'--frame\r\n'
b'Content-Type: image/jpeg\r\n\r\n' + open('frame.jpg', 'rb').read() + b'\r\n')
# String results
print(s)
# wait key to break
if cv2.waitKey(1) & 0xFF == ord('q'):
break
@app.route('/video_feed')
def video_feed():
return Response(gen(),
mimetype='multipart/x-mixed-replace; boundary=frame')
if __name__ == '__main__':
parser = argparse.ArgumentParser()
parser.add_argument('--weights', nargs='+', type=str, default='/Users/sinkarsenic/Downloads/mask_detect/权重/best.pt', help='model.pt path(s)')
parser.add_argument('--source', type=str, default='rtmp://ns8.indexforce.com/home/mystream', 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=0.15, help='object confidence threshold')
parser.add_argument('--iou-thres', type=float, default=0.45, help='IOU threshold for NMS')
parser.add_argument('--device', default='', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')
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('--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('--frame-rate', default=0, type=int, help='sample rate')
opt = parser.parse_args()
app.run(debug=False)
服务器的部署（未解决）
用的阿里云免费试用的 Ubuntu
问题一：qt.qpa.xcb: could not connect to display
qt.qpa.xcb: could not connect to display
qt.qpa.plugin: Could not load the Qt platform plugin “xcb” in “/usr/local/lib/python3.9/site-packages/cv2/qt/plugins” even though it was found.
This application failed to start because no Qt platform plugin could be initialized. Reinstalling the application may fix this problem.
Available platform plugins are: xcb.
好像是系统的问题？不能显示出画面。。。未解决
参考链接 1
参考链接 2
这个说的比较清楚
问题二：AttributeError: ‘Upsample‘ object has no attribute ‘recompute_scale_factor‘
解决办法