Downloads · 30 days
13
3% of all-time downloads
videomae-base-finetuned-ucf_crime2
Dijaaa/videomae-base-finetuned-ucf_crime2
videomae-base-finetuned-ucf_crime2 is a video classification model from Dijaaa. 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
388
Public
Repo size
20.4 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
- Sep 28, 2023
- Updated
- Oct 14, 2023
- SHA
- cbce463b
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_crime2
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: 2.1449
- Accuracy: 0.2689
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: 8
- seed: 42
- distributed_type: tpu
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- training_steps: 504
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 2.3843 | 0.17 | 85 | 2.5040 | 0.1662 |
| 2.2227 | 1.17 | 170 | 2.3376 | 0.1935 |
| 2.1317 | 2.17 | 255 | 2.2547 | 0.2329 |
| 2.0338 | 3.17 | 340 | 2.1470 | 0.2485 |
| 1.9639 | 4.17 | 425 | 2.0700 | 0.2558 |
| 1.8565 | 5.16 | 504 | 2.0882 | 0.2625 |
Framework versions
- Transformers 4.34.0
- Pytorch 2.0.0+cu117
- Datasets 2.14.5
- Tokenizers 0.14.1
- Task
- Video Classification
- Library
- transformers
- Type
- videomae
- License
- cc-by-nc-4.0
- Created
- Sep 28, 2023
- Updated
- Oct 14, 2023