README.md

metadata

license: apache-2.0
tags:
  - image-classification
  - vision
  - generated_from_trainer
datasets:
  - beans
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: 0.9699248120300752
      - task:
          type: image-classification
          name: Image Classification
        dataset:
          name: beans
          type: beans
          config: default
          split: test
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.90625
            verified: true
          - name: Precision Macro
            type: precision
            value: 0.9070628768303187
            verified: true
          - name: Precision Micro
            type: precision
            value: 0.90625
            verified: true
          - name: Precision Weighted
            type: precision
            value: 0.9065184916020672
            verified: true
          - name: Recall Macro
            type: recall
            value: 0.9069767441860465
            verified: true
          - name: Recall Micro
            type: recall
            value: 0.90625
            verified: true
          - name: Recall Weighted
            type: recall
            value: 0.90625
            verified: true
          - name: F1 Macro
            type: f1
            value: 0.9064471790906943
            verified: true
          - name: F1 Micro
            type: f1
            value: 0.90625
            verified: true
          - name: F1 Weighted
            type: f1
            value: 0.9058082094420463
            verified: true
          - name: loss
            type: loss
            value: 0.37941932678222656
            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: 0.1824
• Accuracy: 0.9699

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: 2e-05
• train_batch_size: 24
• eval_batch_size: 24
• seed: 1337
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 5.0

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.672	1.0	44	0.5672	0.9398
0.411	2.0	88	0.3027	0.9699
0.2542	3.0	132	0.2078	0.9699
0.1886	4.0	176	0.1882	0.9699
0.1931	5.0	220	0.1824	0.9699

Framework versions

• Transformers 4.20.0.dev0
• Pytorch 1.11.0+cu102
• Datasets 2.2.2
• Tokenizers 0.12.1