yolov5-face

yolov5-face copied to clipboard

Naughty-Galileo

hey guys , im new to dataset training , i don't know how to train or deploy the dataset , is there a tutorial somewhere about this . i tried...

YellowAfro

It should be a BUG

2

## Bug explain When the number of classes equals 1, which means single class. There is a bug. (The original code is single class, only Face) During the training process,...

Dpaul891

The training results on tensorboard is error. ``` tags = ['train/box_loss', 'train/obj_loss', 'train/cls_loss', 'train/landmark_loss' # landmark_loss 'metrics/precision', 'metrics/recall', 'metrics/mAP_0.5', 'metrics/mAP_0.5:0.95', 'val/box_loss', 'val/obj_loss', 'val/cls_loss', # val loss 'x/lr0', 'x/lr1', 'x/lr2'] #...

Naughty-Galileo

Hi Thanks for sharing this project. I infer yolov5n-0.5.pth and get the below result.  export model to tensorrt with ```python3 export.py --weights weights/yolov5n-0.5.pt --simplify --onnx2trt ``` command . with...

saeedkhanehgir

plotting results issue

1

Hello, Thanks for this great project. I was faced with some issues during training your code: 1- I got this warning error: "Images sizes do not match. This will cause...

mahdis-sa

转化ONNX时如何得到与推理相同的输出格式？

10

转化ONNX时如何得到与推理相同的输出格式？目前转化为ONNX时，输出为三个特征图的结果。怎么修改能得到和推理时一样的输出结果呢？如下图所示。  我修改了model.model[-1].export = False，输出格式相同，但是提示错误：  请问该如何解决？

suncheng-s

Hi, guys, Is that possible to apply the ptq int8 optimizations on yolov5face's torch2trt? I tried to add the supports of int8 optimization by using widerface val-dataset for calibrations and...

neoragex2002

Hi @derronqi, thanks for your amazing repo. I tried to convert your pretrained yolov5s-face.pt to onnx by `export.py --dynamic`. Everything works fine but when i try execute onnx model by...

DoVan-Thuan

xy and wh calculation

1

i notice that ， while in loss calculation and inference decoding : for x ,y and w,h calculation: (yolo.py) 59: y = y + torch.cat((x[i][:, :, :, :, 0:5].sigmoid(), torch.cat((x[i][:,...

leoluopy