|
--- |
|
license: apache-2.0 |
|
base_model: google/vit-base-patch16-224-in21k |
|
tags: |
|
- image-classification |
|
- generated_from_trainer |
|
datasets: |
|
- imagefolder |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: Action_model |
|
results: |
|
- task: |
|
name: Image Classification |
|
type: image-classification |
|
dataset: |
|
name: action_class |
|
type: imagefolder |
|
config: default |
|
split: train |
|
args: default |
|
metrics: |
|
- name: Accuracy |
|
type: accuracy |
|
value: 0.799047619047619 |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# Action_model |
|
|
|
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the action_class dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.6551 |
|
- Accuracy: 0.7990 |
|
|
|
## 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: 0.0001 |
|
- train_batch_size: 32 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 10 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| 1.1382 | 0.32 | 100 | 1.0002 | 0.7676 | |
|
| 0.782 | 0.64 | 200 | 0.7673 | 0.7676 | |
|
| 0.6289 | 0.96 | 300 | 0.7073 | 0.7867 | |
|
| 0.5028 | 1.27 | 400 | 0.7261 | 0.7686 | |
|
| 0.4746 | 1.59 | 500 | 0.7464 | 0.7619 | |
|
| 0.4298 | 1.91 | 600 | 0.6551 | 0.7990 | |
|
| 0.3488 | 2.23 | 700 | 0.7359 | 0.7733 | |
|
| 0.266 | 2.55 | 800 | 0.8296 | 0.7514 | |
|
| 0.3651 | 2.87 | 900 | 0.8661 | 0.7305 | |
|
| 0.2796 | 3.18 | 1000 | 0.7188 | 0.7867 | |
|
| 0.2703 | 3.5 | 1100 | 0.8422 | 0.7476 | |
|
| 0.2608 | 3.82 | 1200 | 0.8207 | 0.7724 | |
|
| 0.251 | 4.14 | 1300 | 1.0252 | 0.7267 | |
|
| 0.2085 | 4.46 | 1400 | 1.0475 | 0.7171 | |
|
| 0.1715 | 4.78 | 1500 | 0.8852 | 0.7495 | |
|
| 0.2051 | 5.1 | 1600 | 0.8164 | 0.7790 | |
|
| 0.1481 | 5.41 | 1700 | 0.8825 | 0.7629 | |
|
| 0.177 | 5.73 | 1800 | 0.8623 | 0.7867 | |
|
| 0.1607 | 6.05 | 1900 | 0.9487 | 0.7610 | |
|
| 0.1273 | 6.37 | 2000 | 0.8985 | 0.7733 | |
|
| 0.1609 | 6.69 | 2100 | 0.9624 | 0.7505 | |
|
| 0.1583 | 7.01 | 2200 | 0.9015 | 0.7781 | |
|
| 0.1178 | 7.32 | 2300 | 0.9143 | 0.7762 | |
|
| 0.1175 | 7.64 | 2400 | 0.9671 | 0.7590 | |
|
| 0.1257 | 7.96 | 2500 | 0.8925 | 0.7838 | |
|
| 0.0939 | 8.28 | 2600 | 0.9257 | 0.7705 | |
|
| 0.1238 | 8.6 | 2700 | 0.9797 | 0.7648 | |
|
| 0.1219 | 8.92 | 2800 | 0.9399 | 0.7724 | |
|
| 0.0985 | 9.24 | 2900 | 0.9940 | 0.7648 | |
|
| 0.1069 | 9.55 | 3000 | 0.9392 | 0.7743 | |
|
| 0.0589 | 9.87 | 3100 | 0.9408 | 0.78 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.39.3 |
|
- Pytorch 2.1.2 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
|
|