Hugging Face's logo

krismp
/
emotion_recognition

Image Classification
Transformers
PyTorch
vit
Generated from Trainer
Eval Results
Model card Files
xet
Community
3
emotion_recognition / README.md
krismp's picture
krismp
End of training
1093dc6
preview code
|
raw
history blame
4.75 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_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: 0.125

emotion_recognition

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: 2.0993
  • Accuracy: 0.125

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: 0.0005
  • 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: 50

Training results

Training Loss Epoch Step Validation Loss Accuracy
No log 1.0 40 2.0986 0.125
No log 2.0 80 2.0816 0.125
No log 3.0 120 2.0798 0.125
No log 4.0 160 2.0765 0.125
No log 5.0 200 2.0765 0.125
No log 6.0 240 2.0820 0.125
No log 7.0 280 2.0796 0.125
No log 8.0 320 2.0826 0.125
No log 9.0 360 2.0759 0.125
No log 10.0 400 2.0799 0.125
No log 11.0 440 2.0593 0.125
No log 12.0 480 2.0813 0.125
2.0843 13.0 520 2.0817 0.125
2.0843 14.0 560 2.1626 0.125
2.0843 15.0 600 2.1105 0.125
2.0843 16.0 640 2.0921 0.125
2.0843 17.0 680 2.0878 0.125
2.0843 18.0 720 2.0877 0.125
2.0843 19.0 760 2.0815 0.125
2.0843 20.0 800 2.0812 0.125
2.0843 21.0 840 2.0810 0.125
2.0843 22.0 880 2.0796 0.125
2.0843 23.0 920 2.0798 0.125
2.0843 24.0 960 2.0808 0.125
2.0948 25.0 1000 2.0812 0.125
2.0948 26.0 1040 2.0806 0.125
2.0948 27.0 1080 2.0797 0.125
2.0948 28.0 1120 2.0795 0.125
2.0948 29.0 1160 2.0801 0.125
2.0948 30.0 1200 2.0792 0.125
2.0948 31.0 1240 2.0783 0.125
2.0948 32.0 1280 2.0792 0.125
2.0948 33.0 1320 2.0786 0.125
2.0948 34.0 1360 2.0769 0.125
2.0948 35.0 1400 2.0686 0.125
2.0948 36.0 1440 2.0616 0.125
2.0948 37.0 1480 2.0653 0.125
2.0804 38.0 1520 2.0970 0.125
2.0804 39.0 1560 2.0815 0.125
2.0804 40.0 1600 2.0743 0.125
2.0804 41.0 1640 2.0802 0.125
2.0804 42.0 1680 2.0655 0.125
2.0804 43.0 1720 2.0768 0.125
2.0804 44.0 1760 2.0642 0.125
2.0804 45.0 1800 2.0637 0.125
2.0804 46.0 1840 2.0687 0.125
2.0804 47.0 1880 2.0603 0.125
2.0804 48.0 1920 2.0507 0.125
2.0804 49.0 1960 2.0395 0.125
2.0589 50.0 2000 2.0600 0.125

Framework versions

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