Hugging Face's logo

hansin91
/
emotion_classification

Image Classification
Transformers
PyTorch
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
emotion_classification / README.md
hansin91's picture
hansin91
End of training
631d57a
preview code
|
raw
history blame
3.61 kB
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_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: 0.58125

emotion_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: 2.0973
  • Accuracy: 0.5813

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: 4e-05
  • train_batch_size: 16
  • eval_batch_size: 16
  • seed: 42
  • gradient_accumulation_steps: 3
  • total_train_batch_size: 48
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 500
  • num_epochs: 30

Training results

Training Loss Epoch Step Validation Loss Accuracy
0.0283 0.97 13 2.0768 0.575
0.0243 1.95 26 2.1315 0.5437
0.0174 3.0 40 2.1721 0.5437
0.0176 3.98 53 2.1687 0.525
0.0172 4.95 66 2.0882 0.5375
0.016 6.0 80 1.9676 0.5687
0.017 6.97 93 2.1717 0.5375
0.0169 7.95 106 2.0982 0.5375
0.0157 9.0 120 2.0893 0.5563
0.0169 9.97 133 1.7681 0.6188
0.0179 10.95 146 2.1032 0.5437
0.0186 12.0 160 2.1116 0.55
0.0196 12.97 173 2.2203 0.5625
0.018 13.95 186 2.0634 0.575
0.0193 15.0 200 2.2562 0.5312
0.026 15.97 213 2.3150 0.5062
0.0171 16.95 226 2.0457 0.5437
0.0194 18.0 240 1.9336 0.5938
0.0657 18.98 253 2.1706 0.5188
0.0537 19.95 266 2.0839 0.5437
0.0566 21.0 280 2.3004 0.4813
0.074 21.98 293 2.1488 0.5375
0.0394 22.95 306 2.4144 0.475
0.0228 24.0 320 2.2085 0.55
0.0514 24.98 333 2.1443 0.5312
0.0553 25.95 346 2.3013 0.5062
0.0436 27.0 360 1.9988 0.5813
0.1468 27.98 373 2.0166 0.5563
0.2184 28.95 386 2.4145 0.5
0.1519 29.25 390 2.2032 0.5375

Framework versions

  • Transformers 4.33.2
  • Pytorch 2.0.1+cu118
  • Datasets 2.14.5
  • Tokenizers 0.13.3