README.md

metadata

license: apache-2.0
tags:
  - image-classification
  - generated_from_trainer
datasets:
  - beans
widget:
  - src: https://huggingface.co/nateraw/vit-base-beans/resolve/main/healthy.jpeg
    example_title: Healthy
  - src: >-
      https://huggingface.co/nateraw/vit-base-beans/resolve/main/angular_leaf_spot.jpeg
    example_title: Angular Leaf Spot
  - src: https://huggingface.co/nateraw/vit-base-beans/resolve/main/bean_rust.jpeg
    example_title: Bean Rust
metrics:
  - accuracy
model-index:
  - name: vit-base-beans
    results:
      - task:
          name: Image Classification
          type: image-classification
        dataset:
          name: beans
          type: beans
          args: default
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.9849624060150376
      - task:
          type: image-classification
          name: Image Classification
        dataset:
          name: beans
          type: beans
          config: default
          split: test
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.96875
            verified: true
          - name: Precision Macro
            type: precision
            value: 0.9716312056737588
            verified: true
          - name: Precision Micro
            type: precision
            value: 0.96875
            verified: true
          - name: Precision Weighted
            type: precision
            value: 0.9714095744680851
            verified: true
          - name: Recall Macro
            type: recall
            value: 0.9689922480620154
            verified: true
          - name: Recall Micro
            type: recall
            value: 0.96875
            verified: true
          - name: Recall Weighted
            type: recall
            value: 0.96875
            verified: true
          - name: F1 Macro
            type: f1
            value: 0.9689250225835592
            verified: true
          - name: F1 Micro
            type: f1
            value: 0.96875
            verified: true
          - name: F1 Weighted
            type: f1
            value: 0.9686822493224932
            verified: true
          - name: loss
            type: loss
            value: 0.1282731592655182
            verified: true

vit-base-beans

This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the beans dataset. It achieves the following results on the evaluation set:

• Loss: 0.0505
• Accuracy: 0.9850

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: 0.0002
• train_batch_size: 16
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 8
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.1166	1.54	100	0.0764	0.9850
0.1607	3.08	200	0.2114	0.9398
0.0067	4.62	300	0.0692	0.9774
0.005	6.15	400	0.0944	0.9624
0.0043	7.69	500	0.0505	0.9850

Framework versions

• Transformers 4.16.2
• Pytorch 1.10.0+cu111
• Datasets 1.18.3
• Tokenizers 0.11.0