Hugging Face's logo

karthiksv
/
vit-base-beans

Image Classification
Transformers
PyTorch
vit
generated_from_trainer
Inference Endpoints
Model card Files Community
3
vit-base-beans / README.md
lewtun's picture
lewtun HF staff
Add evaluation results on beans dataset
35dcd65
preview code
|
raw history blame
2.26 kB
metadata
license: apache-2.0
tags:
  - image-classification
  - generated_from_trainer
datasets:
  - beans
model-index:
  - name: vit-base-beans
    results:
      - task:
          type: image-classification
          name: Image Classification
        dataset:
          name: beans
          type: beans
          config: default
          split: test
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.4140625
            verified: true
          - name: Precision Macro
            type: precision
            value: 0.39234923492349233
            verified: true
          - name: Precision Micro
            type: precision
            value: 0.4140625
            verified: true
          - name: Precision Weighted
            type: precision
            value: 0.3907979860486049
            verified: true
          - name: Recall Macro
            type: recall
            value: 0.41325212255444815
            verified: true
          - name: Recall Micro
            type: recall
            value: 0.4140625
            verified: true
          - name: Recall Weighted
            type: recall
            value: 0.4140625
            verified: true
          - name: F1 Macro
            type: f1
            value: 0.3298611111111111
            verified: true
          - name: F1 Micro
            type: f1
            value: 0.4140625
            verified: true
          - name: F1 Weighted
            type: f1
            value: 0.3292643229166667
            verified: true
          - name: loss
            type: loss
            value: 1.0843162536621094
            verified: true

vit-base-beans

This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the beans dataset.

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: 8
  • eval_batch_size: 8
  • seed: 1337
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 5.0

Framework versions

  • Transformers 4.19.0.dev0
  • Pytorch 1.10.1
  • Datasets 2.1.0
  • Tokenizers 0.12.1