xingguang12

我想做一个车载相机视角下的数据集，但是网上很多图片和视频有水印，很难去获取到，你们能告诉我一些渠道去获取这些图片或者视频吗？十分感谢

对您在论文中写的负样本训练（NST）方法有点疑惑？

2

 您在论文中写道“在训练过程中，将同时检测人行横道和引导箭头，引导箭头将从最终的检测结果中排除。这样实际上增加了训练中导箭的损失函数。”，请问您是怎么将引导箭头将从最终的检测结果中排除的？我在您的detect.py代码中并没有看到相应操作，您能指点我一下吗？

Why is it so bad to use the trained weight file to detect?

5

### Search before asking - [X] I have searched the YOLOv5 [issues](https://github.com/ultralytics/yolov5/issues) and [discussions](https://github.com/ultralytics/yolov5/discussions) and found no similar questions. ### Question I trained my data set with yolov5s, trained on...

How to add inter-frame correlation when detecting video?

2

### Search before asking - [X] I have searched the Ultralytics YOLO [issues](https://github.com/ultralytics/ultralytics/issues) and [discussions](https://github.com/ultralytics/ultralytics/discussions) and found no similar questions. ### Question When detecting a video, sometimes the object does...

How to choose the best IOU threshold during inference？

4

How to choose the best IOU threshold during reasoning to make the detection effect better？

How to write the bitstream obtained from `PyNvVideoCodec` encoding into a video file (e.g., MP4).

1

`import cv2 import numpy as np cap = cv2.VideoCapture(0) while True: ret, frame = cap.read() if not ret: break height, width, channels = frame.shape print(f"Width: {width}, Height: {height}") # Convert...

How to handle errors when using UltraDict in multiprocessing and how to asynchronously wait for UltraDict to be written to in the main process.

6

`import time import random import threading from multiprocessing import Process, Manager from UltraDict import UltraDict class A(): def __init__(self, name, dictname): self.name = name self.dictname = dictname self.personnum = -1...