Downloads · 30 days
4
9% of all-time downloads
model_timesformer_subset
namnh2002/model_timesformer_subset
model_timesformer_subset is a video classification model from namnh2002. 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
43
Public
Parameters
121M
3.4 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors485 MB · 100%
At a glance
- Task
- Video Classification
- Library
- transformers
- License
- cc-by-nc-4.0
- Model type
- timesformer
- Access
- Public
- Created
- Mar 4, 2024
- Updated
- Mar 4, 2024
- SHA
- d0e5e7c8
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. -->
model_timesformer_subset_01
This model is a fine-tuned version of facebook/timesformer-base-finetuned-k600 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.6413
- Accuracy: 0.5375
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
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- training_steps: 4000
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 2.0091 | 0.25 | 1000 | 1.8240 | 0.4785 |
| 1.7196 | 1.25 | 2000 | 1.6658 | 0.515 |
| 1.5516 | 2.25 | 3000 | 1.6609 | 0.534 |
| 1.2154 | 3.25 | 4000 | 1.6112 | 0.5435 |
Framework versions
- Transformers 4.38.1
- Pytorch 2.1.2
- Datasets 2.1.0
- Tokenizers 0.15.2
- Task
- Video Classification
- Library
- transformers
- Type
- timesformer
- License
- cc-by-nc-4.0
- Created
- Mar 4, 2024
- Updated
- Mar 4, 2024