yushe
yushe
> The problem has been solved. > Using a different version of TensorRT was a problem. This is my mistake. > > Thank you. Hi，did you make the mmpose tensorrt...
me too
if you use the knn-matting algrothm to generate the ground truth of alpha-matte base on some segementation dataset. Specifically， first you use gen_trimap.py to generate trimaps base on erode and...
@LinB203 I have tried your work, but I have run inference.py in the code multiple times and the output results are inconsistent each time. Therefore, I guess there may be...
@okmmsky888 sorry， I don't have any trained model. Due to an unexpected bug, the training process was interrupted...
不好意思，我好久没做反欺诈了 发自我的 iPhone > 在 2018年10月8日，16:33，weihua04 写道： > > 您好，请教个问题哈～针对纸质照片和电子屏显示照片的伪造攻击，有没有速度快效果差不多的特征？ > 请问有没有训练好的分类器模型能否上传下或者发给我呢[email protected]？非常感谢 > > ― > You are receiving this because you were mentioned. > Reply to this email directly,...
download lane.caffemodel as the link shows in file download.lane.caffemodel. and then see inference.py. It is the same as you use the traditional caffe model.
> emm...please, which project you use convert the pytorch model to caffe? Hi,I convert pytorch to onnx and then to caffe, you can reference this code:[https://github.com/hanson-young/nniefacelib/tree/master/PFPLD/cvtcaffe]( https://github.com/hanson-young/nniefacelib/tree/master/PFPLD/cvtcaffe)
You can simply comment this line, if not help, I will upload this file when I have time >>>>>>>>>>>>>>>> Have added file "antiSpofModel.h"!
@Adarine99 sorry, I haven't done this for a long time. take this code just for reference。