farmaieu/upernet-swin-small-finetuned-plantorgans

来源：🤗有风险🏴‍☠️ 救援者：isiliconmit81M 参数325 MBsafetensors✓ 2 个校验和980 天前更新

upernet-swin-small-finetuned

This model is a fine-tuned version of openmmlab/upernet-swin-small on an jpodivin/plantorgans. It achieves the following results on the evaluation set:

Loss: 0.2923
Mean Iou: 0.4108
Mean Accuracy: 0.5178
Overall Accuracy: 0.7337
Accuracy Void: nan
Accuracy Fruit: 0.8691
Accuracy Leaf: 0.7085
Accuracy Flower: 0.0
Accuracy Stem: 0.4937
Iou Void: 0.0
Iou Fruit: 0.8653
Iou Leaf: 0.7034
Iou Flower: 0.0
Iou Stem: 0.4855
Median Iou: 0.4855

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: 0.0006
train_batch_size: 10
eval_batch_size: 10
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Mean Iou	Mean Accuracy	Overall Accuracy	Accuracy Void	Accuracy Fruit	Accuracy Leaf	Accuracy Stem	Iou Fruit	Iou Leaf	Iou Stem	Median Iou
0.2456	1.0	460	0.3706	0.4121	0.5223	0.7804	nan	0.8522	0.8235	0.4134	0.8452	0.8099	0.4053	0.4053
0.246	2.0	920	0.3135	0.3821	0.4813	0.6912	nan	0.8038	0.6825	0.4388	0.8016	0.6772	0.4319	0.4319
0.3118	3.0	1380	0.2923	0.4108	0.5178	0.7337	nan	0.8691	0.7085	0.4937	0.8653	0.7034	0.4855	0.4855

Framework versions

Transformers 4.36.2
Pytorch 2.1.2+cu121
Datasets 2.16.1
Tokenizers 0.15.0