reverseSystem
reverseSystem
> Hi, > Thanks for your awsome work! I am now confused in the generation of uv_weight_mask. Did you generate it using uv_kpt_ind.txt? And is uv_kpt_in.txt generated from Model_keypoints.mat? How...
the training acc is always stay 0.001 like below, so strange. But the val eval looks good(lower than arcface loss). 56786 Epoch 24/24 Batch 12000/12948 Training Loss 25.2287 (22.5939) Training...
The training parameters is default. At first, i wonder if it is too little training iterations. But the circle loss paper is only 182k iterations. less than 24epoch. So it...
> what's the megaface and ijbc acc ? how to look at the megaface acc? I only use the cmc_json which generated under the megaface_24 file. and generate the cmc...
The purpose of cutmix, mixup is to increase local information, and can also classify objects when they are occluded. it is usefull in object detection. There is little occlusion information...
> I've tried this kind of augmentation by erasing half of the aligned face to simulate face with mask the cutmix random crop(crop size is random,not fixed) from one batch...
> Hello, Dr. Zhao. > Thank you for awesome work and sharing AIM codes. > I have trained and tested on some public (e.g. FGNet) database with your codes. >...
> @dyk-ml In my opinion, self.encoder(x) can extract a face coder for face recognition. we only need to compare this vector to recognize a person. > But I think the...
> Download extra BFM information from 3DDFA(Face Alignment Across Large Poses: A 3D Solution) and HFPE(High-Fidelity Pose and Expression Normalization for Face Recognition in the Wild) > > website: http://www.cbsr.ia.ac.cn/users/xiangyuzhu/projects/3DDFA/main.htm...