Downloads · 30 days
21
4% of all-time downloads
videomae-base-finetuned-ucf101-subset
Salvatore/videomae-base-finetuned-ucf101-subset
videomae-base-finetuned-ucf101-subset is a video classification model from Salvatore. 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
505
Public
Parameters
86.2M
23.8 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
- Aug 22, 2024
- Updated
- Sep 9, 2024
- SHA
- 1186329e
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-ucf101-subset
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: 1.4025
- Accuracy: 0.2237
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-06
- train_batch_size: 8
- eval_batch_size: 8
- 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: 480
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.3855 | 1.0 | 25 | 1.3973 | 0.275 |
| 1.4151 | 2.0 | 50 | 1.4034 | 0.1875 |
| 1.4342 | 3.0 | 75 | 1.4028 | 0.2 |
| 1.4189 | 4.0 | 100 | 1.3967 | 0.1625 |
| 1.3925 | 5.0 | 125 | 1.4030 | 0.2375 |
| 1.406 | 6.0 | 150 | 1.3974 | 0.1875 |
| 1.3868 | 7.0 | 175 | 1.4011 | 0.175 |
| 1.3969 | 8.0 | 200 | 1.4019 | 0.15 |
| 1.4233 | 9.0 | 225 | 1.3985 | 0.2125 |
| 1.4011 | 10.0 | 250 | 1.4081 | 0.25 |
| 1.3994 | 11.0 | 275 | 1.4037 | 0.175 |
| 1.3945 | 12.0 | 300 | 1.4094 | 0.2625 |
| 1.3844 | 13.0 | 325 | 1.4050 | 0.175 |
| 1.378 | 14.0 | 350 | 1.4081 | 0.275 |
| 1.3965 | 15.0 | 375 | 1.4095 | 0.275 |
| 1.3982 | 16.0 | 400 | 1.4116 | 0.275 |
| 1.385 | 17.0 | 425 | 1.4114 | 0.275 |
| 1.3735 | 18.0 | 450 | 1.4103 | 0.275 |
| 1.3817 | 19.0 | 475 | 1.4106 | 0.275 |
| 1.3785 | 19.2 | 480 | 1.4106 | 0.275 |
Framework versions
- Transformers 4.44.1
- Pytorch 2.4.0
- Datasets 2.19.1
- Tokenizers 0.19.1
- Task
- Video Classification
- Library
- transformers
- Type
- videomae
- License
- cc-by-nc-4.0
- Created
- Aug 22, 2024
- Updated
- Sep 9, 2024