简体繁体 English

如何将 yolo 边界样式从 (x,y,w,h) 更改为 (x,y,w,h,a)？

[英]How to change yolo bounding style from (x,y,w,h) to (x,y,w,h,a)?

原文 2019-12-07 08:31:27 4 1 python/ python-3.x/ deep-learning/ bounding-box/ yolo

I'm training yolo model, I have the bounding boxes in this format(x,y,w,h,a)=>ex (197.996317 669.721413 390.070453 29.258397 7.696052) the "a" is the angle of the bounding box , I want to implement the angel to bounding box format and train the yolo network我正在训练yolo模型，我有这种格式的边界框(x,y,w,h,a)=>ex (197.996317 669.721413 390.070453 29.258397 7.696052) “a”是边界框的角度，我想要实现angel to bounding box格式并训练yolo网络

I already calculated bounding box and his angle but I don't know how to implement that to the yolo network style.我已经计算了边界框和他的角度，但我不知道如何将其实现到 yolo 网络风格。

How can I implement angle to yolo bounding box style?如何实现 yolo 边界框样式的角度？

1 个解决方案

Well 60 images is really not - You dont have enough combination - explaining why u need to retrain.嗯，60 张图片真的不是 - 你没有足够的组合 - 解释为什么你需要重新训练。

Read this here https://github.com/AlexeyAB/darknet#how-to-train-to-detect-your-custom-objects It also applies to the original repository.在这里阅读https://github.com/AlexeyAB/darknet#how-to-train-to-detect-your-custom-objects它也适用于原始存储库。

如何将 2D 边界框像素坐标 (x, y, w, h) 转换为相对坐标（Yolo 格式）？ - How to convert 2D bounding box pixel coordinates (x, y, w, h) into relative coordinates (Yolo format)?

以 x,y,w,h 格式调整图像大小及其边界框 - Resize image and it's bounding box in x,y,w,h format

如何将cv2.rectangle边界框转换为YoloV4标注格式（相对x,y,w,h）？ - How to convert cv2.rectangle bounding box to YoloV4 annotation format (relative x,y,w,h)?

如何在此裁剪图像中获取 x,y,w,h 的每个值？ - How to get each value of x,y,w,h in this crop image?

img[y:y+h, x:x+w] 坐标系的工作原理 - How it works the coordinate system of img[y:y+h, x:x+w]

如何有效地将形状为（w，h，3）的numpy图像转换为在第三轴上具有r，g，b，x，y的（w，h，5）？ - How to I efficiently transform a numpy image of shape (w, h, 3) to (w,h,5) which has r,g,b,x,y in third axis?

y = x / sum(x, dim=0) 的反向传播，其中张量 x 的大小为 (H,W) - Back-Propagation of y = x / sum(x, dim=0) where size of tensor x is (H,W)

无法编写接受 3 个参数并返回矩形坐标 (x,y,h,w) 的函数 - unable to write a function that take 3 arguments and return the rectangle coordinate (x,y,h,w)

Python - OpenCV，detectMultiScale输出没有逗号分隔x，y，h，w值 - Python - OpenCV, detectMultiScale output doesn't have commas separating x,y,h,w values

PyQt5：我无法理解 QGraphicsScene 的 setSceneRect(x, y, w, h) - PyQt5: I can't understand QGraphicsScene's setSceneRect(x, y, w, h)

暂无

暂无

声明:本站的技术帖子网页，遵循CC BY-SA 4.0协议，如果您需要转载，请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.

相关问题 如何将 2D 边界框像素坐标 (x, y, w, h) 转换为相对坐标（Yolo 格式）？ - How to convert 2D bounding box pixel coordinates (x, y, w, h) into relative coordinates (Yolo format)? 以 x,y,w,h 格式调整图像大小及其边界框 - Resize image and it's bounding box in x,y,w,h format 如何将cv2.rectangle边界框转换为YoloV4标注格式（相对x,y,w,h）？ - How to convert cv2.rectangle bounding box to YoloV4 annotation format (relative x,y,w,h)? 如何在此裁剪图像中获取 x,y,w,h 的每个值？ - How to get each value of x,y,w,h in this crop image? img[y:y+h, x:x+w] 坐标系的工作原理 - How it works the coordinate system of img[y:y+h, x:x+w] 如何有效地将形状为（w，h，3）的numpy图像转换为在第三轴上具有r，g，b，x，y的（w，h，5）？ - How to I efficiently transform a numpy image of shape (w, h, 3) to (w,h,5) which has r,g,b,x,y in third axis? y = x / sum(x, dim=0) 的反向传播，其中张量 x 的大小为 (H,W) - Back-Propagation of y = x / sum(x, dim=0) where size of tensor x is (H,W) 无法编写接受 3 个参数并返回矩形坐标 (x,y,h,w) 的函数 - unable to write a function that take 3 arguments and return the rectangle coordinate (x,y,h,w) Python - OpenCV，detectMultiScale输出没有逗号分隔x，y，h，w值 - Python - OpenCV, detectMultiScale output doesn't have commas separating x,y,h,w values PyQt5：我无法理解 QGraphicsScene 的 setSceneRect(x, y, w, h) - PyQt5: I can't understand QGraphicsScene's setSceneRect(x, y, w, h)

相关标签

粤ICP备18138465号 © 2020-2024 STACKOOM.COM