Downloads · 30 days
37
6% of all-time downloads
videomae-base-finetuned-ucf_crime
rahulbarua/videomae-base-finetuned-ucf_crime
videomae-base-finetuned-ucf_crime is a video classification model from rahulbarua. 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
577
Public
Repo size
5.9 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin345 MB · 100%
At a glance
- Task
- Video Classification
- Library
- transformers
- License
- cc-by-nc-4.0
- Model type
- videomae
- Access
- Public
- Created
- May 21, 2023
- Updated
- May 21, 2023
- SHA
- 36038da6
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_crime
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: 1.4776
- Accuracy: 0.3720
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: 5e-05
- train_batch_size: 8
- eval_batch_size: 5
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- training_steps: 640
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.9349 | 0.06 | 40 | 1.9845 | 0.2332 |
| 1.8834 | 1.06 | 80 | 1.9134 | 0.3009 |
| 1.7506 | 2.06 | 120 | 1.8460 | 0.3080 |
| 1.6494 | 3.06 | 160 | 1.7691 | 0.2624 |
| 1.6189 | 4.06 | 200 | 1.7939 | 0.2537 |
| 1.6895 | 5.06 | 240 | 1.7809 | 0.2706 |
| 1.517 | 6.06 | 280 | 1.6773 | 0.3244 |
| 1.308 | 7.06 | 320 | 1.8364 | 0.3152 |
| 1.2267 | 8.06 | 360 | 2.0392 | 0.2440 |
| 1.4347 | 9.06 | 400 | 1.9110 | 0.2450 |
| 1.1567 | 10.06 | 440 | 1.7606 | 0.2840 |
| 1.1937 | 11.06 | 480 | 1.9803 | 0.2737 |
| 1.0729 | 12.06 | 520 | 1.8355 | 0.3352 |
| 1.0721 | 13.06 | 560 | 1.7808 | 0.3311 |
| 0.6594 | 14.06 | 600 | 1.8175 | 0.3060 |
| 0.7636 | 15.06 | 640 | 1.8409 | 0.3409 |
Framework versions
- Transformers 4.29.2
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
- Task
- Video Classification
- Library
- transformers
- Type
- videomae
- License
- cc-by-nc-4.0
- Created
- May 21, 2023
- Updated
- May 21, 2023