Downloads · 30 days
0
wild-chimpanzee-foundation/uniformerv2_large-clip-k710-pre-k400_cb-focal-loss
uniformerv2_large-clip-k710-pre-k400_cb-focal-loss is a video classification model from wild-chimpanzee-foundation. Use it for the video classification task on the model card, and read the license before you ship it in a product. The card lists the license as mit.
UniformerV2 is a large transformer-based model trained on a binary classification task. Specifically, it is trained to detect whether the input video contains a chimpanzee(s) exhibiting a reaction to the presence of a…
Downloads · 30 days
0
Access
Public
Updated Feb 13, 2024
Repo size
1.4 GB
Likes
0
Public
Click a slice to open those files.
.pth1.4 GB · 100%
From the Hugging Face model README
UniformerV2 is a large transformer-based model trained on a binary classification task. Specifically, it is trained to detect whether the input video contains a chimpanzee(s) exhibiting a reaction to the presence of a camera trap.
UniformerV2 is a large transformer-based model trained on a binary classification task. Specifically, it is trained to detect whether the input video contains a chimpanzee(s) exhibiting a reaction to the presence of a camera trap. As the dataset heavily favours videos exhibiting no reaction to the camera, we employ a class-balanced focal loss to address the class imbalance.
It is trained on camera trap video footage from 15 different countries in Africa as part of the The Pan African Programme: The Cultured Chimpanzee.
We use mean average precision to evaluate models
| Dataset | Model | Loss | mAP (%) |
|---|---|---|---|
| PanAf | Uniformer | CB Focal | 87.82% |