Convnext Nano.cosface Ms1mv3

🚀 Model card for gaunernst/convnext_nano.cosface_ms1mv3

ConvNeXt-Nano for face recognition, trained on the MS1MV3 dataset. This model is fully compatible with timm and was trained using the repository: https://github.com/gau-nernst/timm-face.

🚀 Quick Start

This model is a ConvNeXt-Nano model designed for face recognition, trained on the MS1MV3 dataset. It can be easily integrated into projects using the timm library.

✨ Features

• Dataset: Trained on the gaunernst/ms1mv3-recordio dataset.
• Library Compatibility: Fully compatible with the timm library.
• Functionality: Suitable for image feature extraction tasks.

💻 Usage Examples

Basic Usage

import timm
import torch.nn.functional as F

model = timm.create_model("hf_hub:gaunernst/convnext_nano.cosface_ms1mv3", pretrained=True).eval()
embs = model(torch.randn(1, 3, 112, 112))  # output shape (1, 512)
embs = F.normalize(embs, dim=1)  # model output is not normalized