metadata

license: apache-2.0
tags:
  - image-segmentation
  - generated_from_trainer
metrics:
  - accuracy
widget:
  - src: https://i.ibb.co/NL52HmG/sana.png
    example_title: Healthy
  - src: https://i.ibb.co/P44CL1q/marchita.png
    example_title: Bean Rust
model-index:
  - name: vit-model-ojas
    results: []

vit-model-ojas

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: 0.0099
Accuracy: 1.0

Model description

You can manage to segment the images of plant leaves to be able to know if they are healthy or withered.

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: 8
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 4

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.1457	3.85	500	0.0099	1.0

Framework versions

Transformers 4.28.0
Pytorch 2.0.1+cu118
Tokenizers 0.13.3