Downloads · 30 days
4
1% of all-time downloads
videomae-base-finetuned-ucf101-epoch20
Q-Wind/videomae-base-finetuned-ucf101-epoch20
videomae-base-finetuned-ucf101-epoch20 is a video classification model from Q-Wind. 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
336
Public
Repo size
2.4 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
- Jul 1, 2023
- Updated
- Jul 2, 2023
- SHA
- 8b3eaed2
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-ucf101-epoch20
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: 1.8347
- Accuracy: 0.7704
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: 2
- eval_batch_size: 2
- 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: 79120
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.9278 | 0.05 | 3956 | 2.7016 | 0.3483 |
| 0.6674 | 1.05 | 7912 | 1.5344 | 0.5915 |
| 0.7501 | 2.05 | 11868 | 1.5602 | 0.6477 |
| 0.3266 | 3.05 | 15824 | 1.6153 | 0.6807 |
| 0.6674 | 4.05 | 19780 | 1.5007 | 0.7147 |
| 0.0025 | 5.05 | 23736 | 1.5732 | 0.7065 |
| 0.4971 | 6.05 | 27692 | 1.7131 | 0.7176 |
| 0.0001 | 7.05 | 31648 | 1.5947 | 0.7482 |
| 0.0003 | 8.05 | 35604 | 2.0551 | 0.6958 |
| 0.2192 | 9.05 | 39560 | 1.7950 | 0.7356 |
| 0.1505 | 10.05 | 43516 | 1.9480 | 0.7160 |
| 0.0 | 11.05 | 47472 | 1.5406 | 0.7573 |
| 0.0016 | 12.05 | 51428 | 1.9811 | 0.7207 |
| 0.0005 | 13.05 | 55384 | 1.8196 | 0.7385 |
| 0.0 | 14.05 | 59340 | 1.8393 | 0.7520 |
| 0.0 | 15.05 | 63296 | 1.6738 | 0.7667 |
| 0.0 | 16.05 | 67252 | 1.7355 | 0.7594 |
| 0.0416 | 17.05 | 71208 | 1.7013 | 0.7638 |
| 0.0 | 18.05 | 75164 | 1.6373 | 0.7709 |
| 0.0 | 19.05 | 79120 | 1.5901 | 0.7763 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu117
- Datasets 2.13.1
- Tokenizers 0.13.3
- Task
- Video Classification
- Library
- transformers
- Type
- videomae
- License
- cc-by-nc-4.0
- Created
- Jul 1, 2023
- Updated
- Jul 2, 2023