metadata

license: other
base_model: nvidia/segformer-b0-finetuned-ade-512-512
tags:
  - generated_from_keras_callback
model-index:
  - name: bhaskarSingha/segformer-finetuned-paddyV1
    results: []

bhaskarSingha/segformer-finetuned-paddyV1

This model is a fine-tuned version of nvidia/segformer-b0-finetuned-ade-512-512 on an unknown dataset. It achieves the following results on the evaluation set:

Train Loss: nan
Validation Loss: nan
Validation Mean Iou: 0.0004
Validation Mean Accuracy: 0.5
Validation Overall Accuracy: 0.1499
Validation Accuracy Healthy: 1.0
Validation Accuracy Brownspot: 0.0
Validation Accuracy Leafblast: nan
Validation Iou Healthy: 0.0009
Validation Iou Brownspot: 0.0
Validation Iou Leafblast: nan
Epoch: 2

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:

optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'CosineDecay', 'config': {'initial_learning_rate': 5e-05, 'decay_steps': 1000, 'alpha': 0.0, 'name': 'CosineDecay', 'warmup_target': 5e-05, 'warmup_steps': 100}, 'registered_name': None}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
training_precision: float32

Training results

Train Loss	Validation Loss	Validation Mean Iou	Validation Mean Accuracy	Validation Overall Accuracy	Validation Accuracy Healthy	Validation Accuracy Leafblast	Validation Iou Healthy	Validation Iou Leafblast	Epoch
nan	nan	0.0004	0.5	0.1499	1.0	nan	0.0009	nan	0
nan	nan	0.0004	0.5	0.1499	1.0	nan	0.0009	nan	1
nan	nan	0.0004	0.5	0.1499	1.0	nan	0.0009	nan	2

Framework versions

Transformers 4.40.2
TensorFlow 2.15.0
Datasets 2.15.0
Tokenizers 0.19.1