Downloads · 30 days
10
17% of all-time downloads
d2o2ji/videomae-base-finetuned-kinetics-allkisa-crop-background-0310-clip_duration-kisapplcroppadding
videomae-base-finetuned-kinetics-allkisa-crop-background-0310-clip_duration-kisapplcroppadding is a video classification model from d2o2ji. Use it for the video classification task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as cc-by-nc-4.0.
should probably proofread and complete it, then remove this comment. --
Downloads · 30 days
10
17% of all-time downloads
All-time downloads
59
Public
Parameters
86.2M
5.9 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors345 MB · 100%
From the Hugging Face model README
This model is a fine-tuned version of MCG-NJU/videomae-base-finetuned-kinetics on an unknown dataset. It achieves the following results on the evaluation set:
More information needed
More information needed
More information needed
The following hyperparameters were used during training:
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.0013 | 0.0100 | 255 | 0.4674 | 0.8421 |
| 0.0274 | 1.0100 | 510 | 0.4560 | 0.8289 |
| 0.1435 | 2.0100 | 765 | 0.6663 | 0.7650 |
| 0.3143 | 3.0100 | 1020 | 1.5072 | 0.6504 |
| 0.0054 | 4.0100 | 1275 | 0.6556 | 0.7462 |
| 0.0162 | 5.0100 | 1530 | 0.4079 | 0.8759 |
| 0.0054 | 6.0100 | 1785 | 0.5968 | 0.8308 |
| 0.0001 | 7.0100 | 2040 | 0.7019 | 0.8158 |
| 0.0001 | 8.0100 | 2295 | 0.7552 | 0.8289 |
| 0.2085 | 9.0100 | 2550 | 0.4732 | 0.8628 |
| 0.1964 | 10.0100 | 2805 | 0.6653 | 0.8477 |
| 0.0005 | 11.0100 | 3060 | 0.6082 | 0.8383 |
| 0.0016 | 12.0100 | 3315 | 0.8231 | 0.8496 |
| 0.0002 | 13.0100 | 3570 | 1.1288 | 0.8195 |
| 0.0001 | 14.0100 | 3825 | 0.8457 | 0.8496 |
| 0.0 | 15.0100 | 4080 | 1.0848 | 0.8252 |