yolov5-face
yolov5-face copied to clipboard
YOLO5Face: Why Reinventing a Face Detector (https://arxiv.org/abs/2105.12931) ECCV Workshops 2022)
Hello, is it possible to draw the bounding box for the eyes and the mouth? because it seems like it only return 5 landmark only.
Could you provide pre-trained model for large face detection? I found that you provide new training dataset Multi-Task-Facial without updating corresponding pre-trained models. Thanks.
Traceback (most recent call last): File "train.py", line 513, in train(hyp, opt, device, tb_writer, wandb) File "train.py", line 299, in train scaler.step(optimizer) # optimizer.step File "/home/fut/miniconda3/lib/python3.8/site-packages/torch/cuda/amp/grad_scaler.py", line 321, in step...
Hi, I really appreicate your efforts on this outstanding face detector. And I am trying to train my own detector on other kind of objects, but I am a little...
![2022-09-21 11_15_06-WiderFaceDetection ipynb - Colaboratory](https://user-images.githubusercontent.com/62481421/191479173-8df75f49-4a74-41b5-8e4f-cfb361e0db2f.png) i just get this error when i run the command !python train.py --img 640 --batch 16 --epochs 25 --data data/widerface.yaml --weights yolov5s-face.pt --cache any help?
![image](https://user-images.githubusercontent.com/37979677/190538487-b48bf4f0-bfb8-4058-b3af-ba6487f2ede1.png) box 和 关键点坐标转换不对 orgimg = show_results(orgimg, det[j, :4], conf, det[j, 5:15], class_num)
Hi, I tried the suggested command to convert the .pt model to .trt but its giving error- ONNX export success, saved as yolov5s-face.onnx Export complete (5.96s). Visualize with https://github.com/lutzroeder/netron. pred's...
I have tried to train YOLOv5n model by myself and compared it to your pretrained weights. All the hyperparameters are taken from this repository. Results for pretrained model: ``` ====================...
非常感谢您的开源工作。 当我用wider_face数据集训练时,类别是 1,此时class,即output[:,15]是没有参与训练的,那您开源的模型yolov5l-face.pt中output[:,15]是参与预测的,这样不会有问题吗?还是我理解的有问题,期待您的回复。感谢!