Downloads · 30 days
3
5% of all-time downloads
videomae-base-finetuned-ucf-crimevbinary-balanced
shahadalll/videomae-base-finetuned-ucf-crimevbinary-balanced
videomae-base-finetuned-ucf-crimevbinary-balanced is a video classification model from shahadalll. 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. --
All-time downloads
65
Public
Parameters
86.2M
3.8 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors345 MB · 100%
At a glance
- Task
- Video Classification
- Library
- transformers
- License
- cc-by-nc-4.0
- Model type
- videomae
- Access
- Public
- Created
- Nov 16, 2024
- Updated
- Nov 16, 2024
- SHA
- 96478ebf
Base models
Model card
From the Hugging Face model README
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
videomae-base-finetuned-ucf-crimevbinary-balanced
This model is a fine-tuned version of MCG-NJU/videomae-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3486
- Accuracy: 0.8611
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 3e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 30
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.719 | 1.0 | 29 | 0.6348 | 0.6944 |
| 0.5756 | 2.0 | 58 | 0.5475 | 0.75 |
| 0.4718 | 3.0 | 87 | 0.4779 | 0.7778 |
| 0.4986 | 4.0 | 116 | 0.4849 | 0.8056 |
| 0.3705 | 5.0 | 145 | 0.4065 | 0.8056 |
| 0.3042 | 6.0 | 174 | 0.5558 | 0.8333 |
| 0.2333 | 7.0 | 203 | 0.4220 | 0.8889 |
| 0.4724 | 8.0 | 232 | 0.2888 | 0.8333 |
| 0.0119 | 9.0 | 261 | 0.5093 | 0.8889 |
| 0.2417 | 10.0 | 290 | 0.7827 | 0.7778 |
Framework versions
- Transformers 4.47.0.dev0
- Pytorch 2.5.1+cu124
- Datasets 3.1.0
- Tokenizers 0.20.3
- Task
- Video Classification
- Library
- transformers
- Type
- videomae
- License
- cc-by-nc-4.0
- Created
- Nov 16, 2024
- Updated
- Nov 16, 2024