upernet-convnext-base-AIData

This model is a fine-tuned version of openmmlab/upernet-convnext-base on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.0003
• Mean Iou: 0.8976
• Mean Accuracy: 0.9402
• Overall Accuracy: 0.9999
• Per Category Iou: [0.9999419319790964, 0.7952921395544347]
• Per Category Accuracy: [0.9999725748376043, 0.8804094927873429]

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: 5e-05
• train_batch_size: 8
• eval_batch_size: 8
• 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: linear
• num_epochs: 50
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Mean Iou	Mean Accuracy	Overall Accuracy	Per Category Iou	Per Category Accuracy
0.0005	12.5	200	0.0003	0.8981	0.9393	0.9999	[0.9999424089512944, 0.7962884858709405]	[0.9999735287562963, 0.8785481619357841]
0.0005	25.0	400	0.0003	0.8908	0.9232	0.9999	[0.9999394285464914, 0.7816931671680275]	[0.9999787753091024, 0.8464402047463937]
0.0005	37.5	600	0.0003	0.8969	0.9390	0.9999	[0.9999415743053811, 0.7938578039545646]	[0.9999728133172773, 0.8780828292228944]
0.0005	50.0	800	0.0003	0.8976	0.9402	0.9999	[0.9999419319790964, 0.7952921395544347]	[0.9999725748376043, 0.8804094927873429]

Framework versions

• Transformers 4.46.3
• Pytorch 2.5.1+cu121
• Datasets 3.1.0
• Tokenizers 0.20.3