-
请问结合adaface和partial fc时，原文中的这段代码该怎么加？
if isinstance(x, tuple):
cos_thetas, bad_grad = x
targets[bad_grad.squeeze(-1)] = -100
zws98 updated
11 months ago
-
insightface published 8 checkpoint of partial fc. Each checkpoint corresponds to a part of FC layer. For example, glint360k has 360000 identities. Each checkpoint has shape (360000/8, 512).
Please h…
-
I compared partial fc (r=0.2， pytorch version) with full softmax for my dataset (1 million identities). The precision of partial fc (r=0.2) is lower than that of softmax. Could you give some advices? …
-
I trained a model for 15 epochs and then my machine shut down, I want to continue this training but the loss shown is same as that of 0th epoch. the checkpoint was saved as:-
` checkp…
-
I got this error after about 100k iterations:
Fri Oct 23 17:16:00 2020[0]:[2020-10-23 17:16:00.707119: W horovod/common/stall_inspector.cc:105] One or more tensors were submitted to be reduced, g…
-
我是一名学生，想要复现文章的代码，我按照代码中的注释使用 BrainGNN_Pytorch 项目中的 01-fetch_data.py 下载了 ABIDE 数据集的 pipeline: cpac，atlas: ho 的数据，将下载的数据放在了 ./input/data/ 文件夹，我将 Phenotypic_V1_0b_preprocessed1.csv 中创建了 Group 列，等于 DX_GRO…
-
The library declares
```ts
declare const Markdown: React.FC;
```
This makes it hard to wrap the `Markdown` component because every type becomes an `any`. For example:
```ts
import Markdown…
-
hi, I tried partial_fc for training. As installed the same version of the requests and set the same settings in default.py, I got the segmentation fault:11. I used emore for training.
The error oc…
-
I find that it is forced to use partial fc in arcface_torch, but I just want to use arcface. Is there any offical implement with pytorch? Or need I implement it by myself (any advice to do this, I'…
-
It's a great job!
I'm currently trying to add the Magface loss to the insightface's partial FC, but it doesn't work.
The x_norm is getting larger during training between 30 and 40, resulting in a …