CenterFace.pytorch
CenterFace.pytorch copied to clipboard
unofficial version of centerface, which achieves the best balance between speed and accuracy at face detection
损失函数
请问总损失一直维持在2.2,是什么问题呢,参数改了调小了初始学习率,总损失应该维持在多少大小?
我直接使用后 发现图片检测的都是错的,标注的类别是pig
When the image infer by the model, the image downsize 4x, the small face is 2-5 pixl in my data ,the keypoint heatmap center is very close, and then After...
您的DECODE 跟这个Star-Clouds感觉不大一样 可大致说明一下您的DECODE设计原理嘛 thanks https://github.com/chenjun2hao/CenterFace.pytorch/blob/master/src/lib/models/decode.py VS https://github.com/Star-Clouds/CenterFace/blob/master/prj-python/centerface.py
自行训练的数据发现人脸倾斜时,关键点预测不准,在训练上有什么优化策略么?
Thanks for your work. I have trained a face detection model. What should I do if I want to train a model with five landmarks? I mean which file shuold...
1.注意到您发布的模型中FPN通道数为64,而centerface中FPN的通道数为24。 2.您代码中的后处理用的nms是centernet中的pooling的方式,而centerface官方的代码中采用的是计算IOU的方式,请问您是否对这两种方式都进行测试过?是不是会对精度有一定影响呢?
I'm not albe to find requirements.txt so is not possibile to use pip3 that is more comfortable than conda