优洛V7 | Obs 虚拟相机仅显示单帧答案

【问题标题】：Yolo V7 | Obs Virtual Camera Shows Only Single Frame优洛V7 | Obs 虚拟相机仅显示单帧
【发布时间】：2022-10-23 13:52:21
【问题描述】：

我正在使用 yolo v7 制作一个项目。我使用 Obs 作为 yolo v7 的虚拟摄像头 obs 的输入是特定的应用程序/游戏屏幕

这是我写的终端行。

py .\yolov7\detect.py --weights .\yolov7-tiny.pt --source 0  --conf-thres 0.2 --save-txt --view-img

我只得到了输出单帧

终端输出：

Namespace(weights=['.\\yolov7-tiny.pt'], source='0', img_size=640, conf_thres=0.2, iou_thres=0.45, device='', view_img=True, save_txt=True, save_conf=False, nosave=False, classes=None, agnostic_nms=False, augment=False, update=False, project='runs/detect', name='exp', exist_ok=False, no_trace=False)
YOLOR  v0.1-115-g072f76c torch 1.12.1+cu116 CUDA:0 (NVIDIA GeForce GTX 1650, 4095.6875MB)

Fusing layers... 
Model Summary: 200 layers, 6219709 parameters, 229245 gradients
 Convert model to Traced-model... 
 traced_script_module saved! 
 model is traced! 

1/1: 0... [swscaler @ 000001d35d7340c0] Warning: data is not aligned! This can lead to a speed loss
 success (640x480 at 0.00 FPS).

Exception in thread Thread-1 (update):
Traceback (most recent call last):
  File "C:\Users\Thiroshan\AppData\Local\Programs\Python\Python310\lib\threading.py", line 1016, in _bootstrap_inner
    self.run()
  File "C:\Users\Thiroshan\AppData\Local\Programs\Python\Python310\lib\threading.py", line 953, in run
    self._target(*self._args, **self._kwargs)
  File "C:\Users\Thiroshan\Desktop\python\Projects\Reinforcement\Aim_ai_fps\yolov7\utils\datasets.py", line 318, in update
    time.sleep(1 / self.fps)  # wait time
ZeroDivisionError: float division by zero
C:\Users\Thiroshan\AppData\Local\Programs\Python\Python310\lib\site-packages\torch\functional.py:478: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at  ..\aten\src\ATen\native\TensorShape.cpp:2895.)
  return _VF.meshgrid(tensors, **kwargs)  # type: ignore[attr-defined]

视频检测除网络摄像头（Obs 虚拟摄像头）外运行良好为了在没有 obs 的情况下测试网络摄像头，我没有网络摄像头

我使用检查 Obs 虚拟相机开放式CV它工作得很好

让我知道为什么 yolo v7 有网络摄像头问题

# import the opencv library
import cv2 
# define a video capture object
vid = cv2.VideoCapture(0)
  
while(True):
      
    # Capture the video frame
    # by frame
    ret, frame = vid.read()
  
    # Display the resulting frame
    cv2.imshow('frame', frame)
      
    # the 'q' button is set as the
    # quitting button you may use any
    # desired button of your choice
    if cv2.waitKey(1) & 0xFF == ord('q'):
        break
  
# After the loop release the cap object
vid.release()
# Destroy all the windows
cv2.destroyAllWindows()

【问题讨论】：

标签： object-detection yolo obs

【解决方案1】：

我已经通过下载解决了这个问题https://www.xsplit.com/vcam和虚拟化同时OBS

它到底在做什么

使用 OBS 虚拟化凸轮
阅读OBS里面的虚拟摄像头Xsplit vcam
阅读Xsplit输出到约洛（对我来说 cam id 是 0）

【讨论】：