metadata
license: apache-2.0
base_model: google/vit-base-patch16-224
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: emotion-recognition
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: imagefolder
type: imagefolder
config: default
split: train
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.44375
emotion-recognition
This model is a fine-tuned version of google/vit-base-patch16-224 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 2.5169
- Accuracy: 0.4437
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.001 | 1.0 | 40 | 2.2318 | 0.45 |
| 0.0033 | 2.0 | 80 | 2.3790 | 0.4562 |
| 0.0044 | 3.0 | 120 | 2.7947 | 0.375 |
| 0.0005 | 4.0 | 160 | 2.5546 | 0.425 |
| 0.0074 | 5.0 | 200 | 2.6530 | 0.4188 |
| 0.0003 | 6.0 | 240 | 2.4568 | 0.4313 |
| 0.0001 | 7.0 | 280 | 2.4512 | 0.45 |
| 0.0001 | 8.0 | 320 | 2.4578 | 0.4562 |
| 0.0001 | 9.0 | 360 | 2.4676 | 0.4375 |
| 0.0001 | 10.0 | 400 | 2.4747 | 0.4375 |
| 0.0001 | 11.0 | 440 | 2.4823 | 0.4437 |
| 0.0 | 12.0 | 480 | 2.4894 | 0.4437 |
| 0.0 | 13.0 | 520 | 2.4954 | 0.4437 |
| 0.0 | 14.0 | 560 | 2.5014 | 0.4437 |
| 0.0 | 15.0 | 600 | 2.5056 | 0.4437 |
| 0.0 | 16.0 | 640 | 2.5097 | 0.4437 |
| 0.0 | 17.0 | 680 | 2.5129 | 0.4437 |
| 0.0 | 18.0 | 720 | 2.5150 | 0.4437 |
| 0.0 | 19.0 | 760 | 2.5164 | 0.4437 |
| 0.0 | 20.0 | 800 | 2.5169 | 0.4437 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.2
- Tokenizers 0.19.1