Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
datasets:
|
3 |
+
- gaunernst/ms1mv3-recordio
|
4 |
+
library_name: timm
|
5 |
+
tags:
|
6 |
+
- image-feature-extraction
|
7 |
+
- timm
|
8 |
+
---
|
9 |
+
|
10 |
+
# Model card for gaunernst/convnext_nano.cosface_ms1mv3
|
11 |
+
|
12 |
+
ConvNeXt-Nano for face recognition, trained on MS1MV3 dataset. The model was trained using this repo: https://github.com/gau-nernst/timm-face. It is fully compatible with `timm`.
|
13 |
+
|
14 |
+
## Usage
|
15 |
+
|
16 |
+
```python
|
17 |
+
import timm
|
18 |
+
import torch.nn.functional as F
|
19 |
+
|
20 |
+
model = timm.create_model("hf_hub:gaunernst/convnext_nano.cosface_ms1mv3", pretrained=True).eval()
|
21 |
+
embs = model(torch.randn(1, 3, 112, 112)) # output shape (1, 512)
|
22 |
+
embs = F.normalize(embs, dim=1) # model output is not normalized
|
23 |
+
```
|