-
Hi, Congrats to the authors! Great work, the performance of the synthetic data is almost on the verge of exceeding the real data. I'm having some problems reproducing the paper. The performance in Ta…
-
## 环境
- 【FastDeploy版本】： 说明具体的版本，如fastdeploy-linux-gpu-0.8.0
- 【系统平台】: Windows x64(Windows11)
- 【硬件】： 如 Nvidia GPU 1650TI， CUDA 12.0 CUDNN 8.2
- 【编译语言】： Python(3.9）
- 【模型跑不通】
- - 执行`examples\…
-
Hi ,Thank you for your work sharing. I added Adaface to project insightFace and verified the effect of Adaface in dataset MV1Mv3, but in Glint360K, the effect of Adaface is worse than that of Cosface.…
-
such as: `simlist_ir_101_adaface_webface4m_faces_webface_112x112.pth`
-
Hi
I have
python3 test_3880_crossres.py
Traceback (most recent call last):
File "/home/bc/Projects/OpenSource/AdaFace/test_3880_crossres.py", line 9, in
from backbone.iresnet import ir…
-
According to README AdaFace takes `bgr_input` which is 112x112x3 torch tensor
> https://github.com/mk-minchul/AdaFace#general-inference-guideline
However the sample code for inferencing uses `…
-
Hi, thank you for the awesome work.
I notice that in your Ported Models (e.g. [r100 12m AdaFace]) description, you ported the original repo's weight to tensorflow version.
May I ask how did you …
-
Firstly, congrats on the paper and great results.
Currently, I face an issue when I resume the training with the [pre-trained model (R50-MS1Mv2)](https://drive.google.com/file/d/1eUaSHG4pGlIZK7hBk…
-
I am trying to train AdaFace with my own dataset: a custom folder ('data'), a subfolder called 'imgs' that has a collection of other folders ('folder_001', 'folder_002', etc) with various photos of th…
-
Hi!,
I am trying to do fine-tuning of the last layer of the adaface model, for this leaving frozen all the weights of the network, except those belonging to the last layers. The problem is that the…