yolov5-face

yolov5-face copied to clipboard

Why am I having this problem? AssertionError: No results.txt files found in /content/yolov5-face/runs/train/exp, nothing to plot.

4

When I run this command: !python3 train.py --data data/widerface.yaml --cfg models/yolov5s.yaml --weights yolovs-face.pt --epochs 1 I run into this problem. Traceback (most recent call last): File "train.py", line 513, in...

m-hajiabadi

test-widerface

5

请问这是什么原因呐

zuofengyouliang

what is the argment "folder_pict" ?

1

In test_widerface.py line 129. ``` parser.add_argument('--folder_pict', default='/yolov5-face/data/widerface/val/wider_val.txt', type=str, help='folder_pict') ``` what is the argment "folder_pict" and where is it..?

sungeun-yoo

yolov7-face?

1

Hi is there any plan to test this face detector on the yolov7 backbone to maybe have a new SoTa?

ofirkris

断点加载训练好的模型 resume net 后面接着训的模型不能保存了 是为啥?

sssssshf

ONNX file generated by export.py cannot be loaded by OpenCV

2

1. Downloaded yolov5n-face.pt from the following link: https://drive.google.com/file/d/18oenL6tjFkdR1f5IgpYeQfDFqU4w3jEr/view?usp=sharing 2. Generated onnx file by export.py script `export PYTHONPATH="$PWD" && python export.py --weights weights/yolov5n-face.pt --img 640 --batch 1` 3. Tried to run...

WorldTreeBug

关于在自定义数据集上训练的一些问题？

37

@derronqi 大佬你好，就是我是一名大二学生，然后是在中北大学的robomaster战队里负责用神经网络识别装甲板实现自动瞄准，不过就是之前我用yolo系列训练出来的模型最后实际测试时得到的bbox和装甲板的轮廓并不能很好的拟合，导致后续使用pnp进行姿态解算时会有较大误差，所以我想将传统yolo的数据集格式改为用四个角点的归一化坐标，然后我看到了您这个项目，不过我看您的数据集格式里还是包含了传统yolo的归一化后的中心点坐标和w，h，然后我现在的数据集格式是像这样：1 0.673029 0.373564 0.678429 0.426232 0.830433 0.401262 0.824525 0.351212，第一个数字是类别id，后面八个数字是归一化后的装甲板的四个角点坐标，但是我看您的这个仓库里训练是用的wider face数据集，所以我想是得改动dataloader的部分才能训练吗？望大佬解惑

Hezhexi2002

您好，感谢您的工作！ 想问一下，对于关键点，是直接回归关键点坐标还是回归偏离值的呢？

arthur0219

there are my paramters: **parser = argparse.ArgumentParser() parser.add_argument('--weights', type=str, default='weights/yolov5s-face.pt', help='initial weights path') parser.add_argument('--cfg', type=str, default='models/yolov5s.yaml', help='model.yaml path') parser.add_argument('--data', type=str, default='data/plate-face.yaml', help='data.yaml path')** others paramters are default.Then when i run...

Xiloy

where are the landmarks for the eyes, nose, & mouth?

1

so do your models output the landmark coordinates (i.e. eyes, mouth, nose coordinates) or do they just put a bounding box on the faces. When I tried your inference script...

yvielcastillejos