README.md

metadata

license: other
tags:
  - generated_from_trainer
model-index:
  - name: segformer-b0-finetuned-segments-toolwear
    results: []

segformer-b0-finetuned-segments-toolwear

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

• Loss: 0.1338
• Mean Iou: 0.4591
• Mean Accuracy: 0.7164
• Overall Accuracy: 0.9595
• Accuracy Unlabeled: nan
• Accuracy Wear: 0.4489
• Accuracy Tool: 0.9838
• Iou Unlabeled: 0.0
• Iou Wear: 0.4154
• Iou Tool: 0.9618

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: 6e-05
• train_batch_size: 2
• eval_batch_size: 2
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 25

Training results

Training Loss	Epoch	Step	Validation Loss	Mean Iou	Mean Accuracy	Overall Accuracy	Accuracy Unlabeled	Accuracy Wear	Accuracy Tool	Iou Unlabeled	Iou Wear	Iou Tool
0.5488	1.82	20	0.7199	0.3293	0.5153	0.9405	nan	0.0476	0.9830	0.0	0.0475	0.9404
0.5195	3.64	40	0.3507	0.3622	0.5634	0.9239	nan	0.1667	0.9600	0.0	0.1629	0.9236
0.2738	5.45	60	0.2569	0.4662	0.7496	0.9435	nan	0.5363	0.9629	0.0	0.4547	0.9438
0.2461	7.27	80	0.2220	0.4491	0.7057	0.9482	nan	0.4389	0.9725	0.0	0.3982	0.9492
0.1999	9.09	100	0.1962	0.4492	0.7084	0.9597	nan	0.4319	0.9848	0.0	0.3860	0.9616
0.2004	10.91	120	0.1890	0.4031	0.6239	0.9537	nan	0.2610	0.9867	0.0	0.2539	0.9553
0.4753	12.73	140	0.1704	0.4360	0.6760	0.9494	nan	0.3753	0.9768	0.0	0.3562	0.9518
0.1606	14.55	160	0.1579	0.4483	0.7028	0.9580	nan	0.4222	0.9835	0.0	0.3822	0.9625
0.1388	16.36	180	0.1519	0.4829	0.7940	0.9565	nan	0.6152	0.9728	0.0	0.4900	0.9586
0.138	18.18	200	0.1374	0.5120	0.8119	0.9643	nan	0.6443	0.9795	0.0	0.5693	0.9668
0.1078	20.0	220	0.1400	0.4541	0.7066	0.9606	nan	0.4271	0.9860	0.0	0.3985	0.9638
0.1426	21.82	240	0.1323	0.4530	0.7053	0.9581	nan	0.4272	0.9834	0.0	0.3978	0.9611
0.3498	23.64	260	0.1338	0.4591	0.7164	0.9595	nan	0.4489	0.9838	0.0	0.4154	0.9618

Framework versions

• Transformers 4.28.0
• Pytorch 2.0.1+cu118
• Datasets 2.14.5
• Tokenizers 0.13.3