-
Hi,
when run insight_test.py it says :
RuntimeError: Failed downloading url http://insightface.ai/files/models/arcface_r100_v1.zip
I assume it ws downloading from google drive ? but here i…
-
Met this question when using `predict.py`. Error code location is located at
```
i = order[0]
keep.append(i)
```
after check the code, I found the key is to update `squeeze()`…
-
在论文的F：YOLOv5Face on FDDB Dataset部分中，看到YOLOv5s在FDDB数据集中取得了0.9843的性能，这是如何检测出来的？
祝您生活愉快，万事顺心。
-
Hi team,
Thank you for releasing this amazing project.
I was skimming through your paper [YOLO5Face: Why Reinventing a Face Detector](https://arxiv.org/abs/2105.12931) and found that it's claim…
-
请问大佬 train.py有吗 类似yolo7pose一样 有train有detect
-
Hello, can only one face be detected?
Did not detect all the faces in the image #68 When you look here, you seem to be saying that you can modify the confidence threshold. What should I do?
-
-
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.mo…
-
**Is your feature request related to a problem? Please describe.**
* We'd like to reduce the processing time of our face detection models
* Specifically, we've borrowed two works
1. MTCNN [[ar…
-
你好，
1.对于其他轻量级网络对应的配置文件或者调试版本你这边有吗？相比于yolov5face在同样的轻量级backbone前提下，本算法是否有提高？
2.本文中有多个不同比列的anchor生成策略，这会不会带来时间(推理)速度慢的问题？
谢谢~