metadata
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: emotion_image_classification
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: 0.6
emotion_image_classification
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: 1.1587
- Accuracy: 0.6
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: 7e-05
- train_batch_size: 12
- eval_batch_size: 12
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 54 | 1.6922 | 0.2875 |
| No log | 2.0 | 108 | 1.4183 | 0.4688 |
| No log | 3.0 | 162 | 1.3431 | 0.4437 |
| No log | 4.0 | 216 | 1.1979 | 0.5437 |
| No log | 5.0 | 270 | 1.1368 | 0.6188 |
| No log | 6.0 | 324 | 1.1457 | 0.5875 |
| No log | 7.0 | 378 | 1.1509 | 0.575 |
| No log | 8.0 | 432 | 1.1037 | 0.5938 |
| No log | 9.0 | 486 | 1.1060 | 0.575 |
| 1.1174 | 10.0 | 540 | 1.1083 | 0.5938 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.17.0
- Tokenizers 0.15.2