Downloads · 30 days
14
29% of all-time downloads
vivit-b-16x2-kinetics400-CAER-SAMPLE
yehiawp4/vivit-b-16x2-kinetics400-CAER-SAMPLE
vivit-b-16x2-kinetics400-CAER-SAMPLE is a video classification model from yehiawp4. 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 mit.
should probably proofread and complete it, then remove this comment. --
All-time downloads
48
Public
Parameters
88.7M
709 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors355 MB · 100%
At a glance
- Task
- Video Classification
- Library
- transformers
- License
- mit
- Model type
- vivit
- Access
- Public
- Created
- Mar 20, 2024
- Updated
- Mar 20, 2024
- SHA
- 87419f2f
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. -->
vivit-b-16x2-kinetics400-CAER-SAMPLE
This model is a fine-tuned version of google/vivit-b-16x2-kinetics400 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.9485
- Accuracy: 0.2427
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: 2100
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 2.4781 | 0.09 | 196 | 1.8166 | 0.2439 |
| 2.0142 | 1.09 | 392 | 2.2946 | 0.1951 |
| 1.2947 | 2.09 | 588 | 1.6998 | 0.3659 |
| 0.8486 | 3.09 | 784 | 2.0369 | 0.2195 |
| 0.2636 | 4.09 | 980 | 1.9748 | 0.3171 |
| 0.2805 | 5.09 | 1176 | 2.3563 | 0.3659 |
| 0.0923 | 6.09 | 1372 | 2.3754 | 0.3659 |
| 0.1543 | 7.09 | 1568 | 2.7737 | 0.3171 |
| 0.0387 | 8.09 | 1764 | 2.6676 | 0.3659 |
| 0.0101 | 9.09 | 1960 | 2.7895 | 0.3415 |
| 0.0662 | 10.07 | 2100 | 2.7728 | 0.3415 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.1.0
- Datasets 2.18.0
- Tokenizers 0.15.2
- Task
- Video Classification
- Library
- transformers
- Type
- vivit
- License
- mit
- Created
- Mar 20, 2024
- Updated
- Mar 20, 2024