README.md

metadata

datasets:
  - rice
metrics:
  - accuracy
model-index:
  - name: rice_classification
    results:
      - task:
          name: Image Classification
          type: image-classification
        dataset:
          name: rice
          type: rice
          config: default
          split: train
          args: default
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.9768

image_classification

This model is a CNN model on the rice dataset to classify rice into 5 classes (Arborio, Basmati, Ipsala, Jasmine and Karacadag). It achieves the following results on the evaluation set:

• Loss: 0.0116
• Accuracy: 0.9768

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: 0.001
• train_batch_size: 16
• eval_batch_size: 16
• optimizer: Adam
• num_epochs: 5

Training results

Epoch	Loss	Accuracy
1.0	0.0510	0.9363
2.0	0.0099	0.9695
3.0	0.5962	0.9767
4.0	0.4232	0.9828
5.0	0.0011	0.9859