README.md

metadata

license: other
tags:
  - generated_from_trainer
datasets:
  - image_folder
metrics:
  - accuracy
base_model: google/mobilenet_v2_1.0_224
model-index:
  - name: mobilenet_v2_1.0_224-plant-disease-identification
    results:
      - task:
          type: image-classification
          name: Image Classification
        dataset:
          name: New Plant Diseases Dataset
          type: image_folder
          config: default
          split: train
          args: default
        metrics:
          - type: accuracy
            value: 0.9541
            name: Accuracy

mobilenet_v2_1.0_224-plant-disease-identification

This model is a fine-tuned version of google/mobilenet_v2_1.0_224 on the Kaggle version of the Plant Village dataset. It achieves the following results on the evaluation set:

• Cross Entropy Loss: 0.15
• Accuracy: 0.9541

Intended uses & limitations

For identifying common diseases in crops and assessing plant health. Not to be used as a replacement for an actual diagnosis from experts.

Training and evaluation data

The plant village dataset consists of 38 classes of diseases in common crops (including healthy/normal crops).

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 5e-5
• train_batch_size: 256
• eval_batch_size: 256
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.2
• num_epochs: 6

Framework versions

• Transformers 4.27.3
• Pytorch 1.13.0
• Datasets 2.1.0
• Tokenizers 0.13.2