-
hi~
I want to try ur arcface github, but how can I get the dataset
-
您好,当前平台为RV1109,使用arcface转换模型,开启rknn2precompile,保存预编译模型(rknn.export_rknn_precompile_model)报以下错误:
![image](https://user-images.githubusercontent.com/26894108/145171996-a12c1769-3869-4ccf-b40a-7c1dc5f2d…
-
我在租的服务器上跑的时候遇到了“RuntimeError: expected device cuda:0 and dtype Float but got device cuda:0 and dtype Long”这个错误,
torch是1.2.0版本的,网上说是因为版本太低,也可以通过更改数据类型解决,
我是把onehot替换为onehot.float()之后就解决了。
-
# 論文
ArcFace: Additive Angular Margin Loss for Deep Face Recognition
https://arxiv.org/pdf/1801.07698.pdf
2018/01/23
# 動機
レシピの画像検索について発表したときに,Face Recognitionで似たような手法(Triplet Loss)を利用しており,別の手法も…
-
请问下您放出来的36层预训练模型用的是哪一种LOSS训的,Amsoftmax还是ArcFace还是Combine的呢
-
which repository is used to get onnx models for the recognition model? arcface-torch or arcface-mxnet
-
## ざっくり言うと
- 分類先が日々増えるような顔認識では,通常の分類モデルを作り続けるのは難しい.そこで距離空間を学習し,KNNのような方法で判別する方法が取られる.
- クラス内分散が小さく,クラス間分散が大きいと,判別しやすい
- 顔認識等で用いられる距離学習において,ArcFaceという学習モデル(ロス関数)を提案
- ArcFaceは通常のsoftmaxへ渡される部分を内積では…
-
Dear authors, thank you very much for releasing the repository.
May I ask if a trained checkpoint for the ResNet-50 backbone can be provided? We would like to compare with your paper, but have been …
-
**Describe the bug**
When running SubCenter-ArcFace-r100-gpu the container starts but does not function reporting the following error (see logs for full errors)
I have not seen any worker / job when…
-
**Describe the bug**
I've tried multiple methods to run SubCenter-ArcFace-r100-GPU build in Unraid with no success. When trying to run recognition on a face I get the error:
error_outline
Erro…