Open nguyentrongnhat4869 opened 2 years ago
Hi, I'm glad to see your update. As far as I know arcface's input is the aligned face. I would like to ask where did you implement the align face in this deepstream or do you have any suggestion ideas for me. Thank you very much!
Em... I have updated a part, not completely, work is busy, you proposed the face alignment, in the Deepstream implementation is more trouble, which is constrained by the Deepstream processing of the code logical architecture, I have not implemented. If it’s tensorrt, it’s normal procedure.
Hi, I'm glad to see your update. As far as I know arcface's input is the aligned face. I would like to ask where did you implement the align face in this deepstream or do you have any suggestion ideas for me. Thank you very much!
Here’s what I think about this: 1. Write all model resolutions in src/deepstream_app.c , you get a corrected matrix like this. 2. In the installation directory, I prefer this, because the key is that we need to know how to get the computed matrix in the pipe, and changing the image. You’re welcome to give me some pointers
Thank you for your reply. I am also looking for a way to do face alignment, if I succeed I will share!
Thank you for your reply. I am also looking for a way to do face alignment, if I succeed I will share! Great. Can you tell me a little bit about how you write it? My current thinking is based on the official GST PLUGIN OPENCV Demo
Hi, I'm glad to see your update. As far as I know arcface's input is the aligned face. I would like to ask where did you implement the align face in this deepstream or do you have any suggestion ideas for me. Thank you very much!