yusuf802/Leaf-Disease-Predictor

working

This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the leaf-images dataset. It achieves the following results on the evaluation set:

• Loss: 0.0857
• Accuracy: 0.9801

Model description

Finetuned model on 66000+ images of different species of leaves along with their diseases

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: 48
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.9728	0.08	100	0.9026	0.8922
0.4538	0.17	200	0.4412	0.9270
0.2368	0.25	300	0.2870	0.9399
0.2388	0.34	400	0.2208	0.9504
0.1422	0.42	500	0.2046	0.9508
0.1663	0.51	600	0.1538	0.9625
0.1535	0.59	700	0.1427	0.9653
0.1233	0.68	800	0.1133	0.9724
0.1079	0.76	900	0.1005	0.9759
0.1154	0.84	1000	0.0989	0.9748
0.08	0.93	1100	0.0857	0.9801

Framework versions

• Transformers 4.33.0
• Pytorch 2.0.0
• Datasets 2.1.0
• Tokenizers 0.13.3