segformer-finetuned-segments-plantleafdisease-DEC

This model is a fine-tuned version of nancyalarabawy/segformer-finetuned-segments-plantleafdisease-may-25 on the all plus aug dataset. It achieves the following results on the evaluation set:

• eval_loss: 0.0249
• eval_mean_iou: 0.7357
• eval_mean_accuracy: 0.9156
• eval_overall_accuracy: 0.9916
• eval_accuracy_unlabeled: nan
• eval_accuracy_healthy: 0.9794
• eval_accuracy_blast: 0.8521
• eval_accuracy_background: 0.9975
• eval_accuracy_alstonia herpes: 0.8728
• eval_accuracy_mango anthracnose: 0.9309
• eval_accuracy_pomengrate spots: 0.9346
• eval_accuracy_blight spots: 0.8934
• eval_accuracy_chlorisis: 0.9443
• eval_accuracy_leaf spots: 0.9201
• eval_accuracy_apple scab: 0.8382
• eval_accuracy_black rot: 0.8716
• eval_accuracy_cedar rust: 0.9525
• eval_iou_unlabeled: 0.0
• eval_iou_healthy: 0.9690
• eval_iou_blast: 0.7758
• eval_iou_background: 0.9954
• eval_iou_alstonia herpes: 0.7583
• eval_iou_mango anthracnose: 0.6425
• eval_iou_pomengrate spots: 0.8681
• eval_iou_blight spots: 0.6074
• eval_iou_chlorisis: 0.9190
• eval_iou_leaf spots: 0.7070
• eval_iou_apple scab: 0.7455
• eval_iou_black rot: 0.8060
• eval_iou_cedar rust: 0.7695
• eval_runtime: 155.0063
• eval_samples_per_second: 16.915
• eval_steps_per_second: 1.058
• epoch: 13.3486
• step: 17500

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: 1e-05
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 200
• num_epochs: 15

Framework versions

• Transformers 4.47.1
• Pytorch 2.5.1+cu121
• Datasets 3.2.0
• Tokenizers 0.21.0