metadata
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: visual_emotion_classification_vit_base_finetunned
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: 0.525
visual_emotion_classification_vit_base_finetunned
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 1.3848
- Accuracy: 0.525
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
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 2.0383 | 0.62 | 50 | 1.9425 | 0.2875 |
| 1.7682 | 1.25 | 100 | 1.6311 | 0.3875 |
| 1.6002 | 1.88 | 150 | 1.5707 | 0.425 |
| 1.413 | 2.5 | 200 | 1.4598 | 0.5 |
| 1.3389 | 3.12 | 250 | 1.3674 | 0.5875 |
| 1.2695 | 3.75 | 300 | 1.3950 | 0.525 |
| 1.1953 | 4.38 | 350 | 1.3466 | 0.5563 |
| 1.1615 | 5.0 | 400 | 1.3819 | 0.5062 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.17.0
- Tokenizers 0.15.1