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: 0.0480
• Mean Iou: 0.4892
• Mean Accuracy: 0.9785
• Overall Accuracy: 0.9785
• Accuracy Unlabeled: nan
• Accuracy Tool: 0.9785
• Iou Unlabeled: 0.0
• Iou Tool: 0.9785

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: 50

Training results

Training Loss	Epoch	Step	Validation Loss	Mean Iou	Mean Accuracy	Overall Accuracy	Accuracy Unlabeled	Accuracy Tool	Iou Unlabeled	Iou Tool
0.257	1.82	20	0.4274	0.4894	0.9788	0.9788	nan	0.9788	0.0	0.9788
0.14	3.64	40	0.1857	0.4878	0.9756	0.9756	nan	0.9756	0.0	0.9756
0.0945	5.45	60	0.1383	0.4877	0.9754	0.9754	nan	0.9754	0.0	0.9754
0.0766	7.27	80	0.1041	0.4907	0.9813	0.9813	nan	0.9813	0.0	0.9813
0.0752	9.09	100	0.1055	0.4836	0.9672	0.9672	nan	0.9672	0.0	0.9672
0.0433	10.91	120	0.1180	0.4659	0.9318	0.9318	nan	0.9318	0.0	0.9318
0.0358	12.73	140	0.0857	0.4831	0.9662	0.9662	nan	0.9662	0.0	0.9662
0.0357	14.55	160	0.0765	0.4865	0.9730	0.9730	nan	0.9730	0.0	0.9730
0.0401	16.36	180	0.0898	0.4793	0.9587	0.9587	nan	0.9587	0.0	0.9587
0.042	18.18	200	0.0755	0.4828	0.9655	0.9655	nan	0.9655	0.0	0.9655
0.0366	20.0	220	0.0744	0.4818	0.9635	0.9635	nan	0.9635	0.0	0.9635
0.0213	21.82	240	0.0708	0.4828	0.9656	0.9656	nan	0.9656	0.0	0.9656
0.0284	23.64	260	0.0684	0.4851	0.9701	0.9701	nan	0.9701	0.0	0.9701
0.0237	25.45	280	0.0625	0.4879	0.9757	0.9757	nan	0.9757	0.0	0.9757
0.0189	27.27	300	0.0603	0.4858	0.9716	0.9716	nan	0.9716	0.0	0.9716
0.026	29.09	320	0.0632	0.4860	0.9719	0.9719	nan	0.9719	0.0	0.9719
0.0231	30.91	340	0.0662	0.4840	0.9680	0.9680	nan	0.9680	0.0	0.9680
0.0218	32.73	360	0.0563	0.4855	0.9710	0.9710	nan	0.9710	0.0	0.9710
0.0253	34.55	380	0.0627	0.4848	0.9697	0.9697	nan	0.9697	0.0	0.9697
0.0142	36.36	400	0.0621	0.4844	0.9689	0.9689	nan	0.9689	0.0	0.9689
0.0214	38.18	420	0.0668	0.4820	0.9639	0.9639	nan	0.9639	0.0	0.9639
0.0166	40.0	440	0.0555	0.4858	0.9716	0.9716	nan	0.9716	0.0	0.9716
0.0185	41.82	460	0.0545	0.4859	0.9718	0.9718	nan	0.9718	0.0	0.9718
0.0218	43.64	480	0.0500	0.4876	0.9753	0.9753	nan	0.9753	0.0	0.9753
0.0184	45.45	500	0.0481	0.4892	0.9784	0.9784	nan	0.9784	0.0	0.9784
0.018	47.27	520	0.0487	0.4893	0.9786	0.9786	nan	0.9786	0.0	0.9786
0.0254	49.09	540	0.0480	0.4892	0.9785	0.9785	nan	0.9785	0.0	0.9785

Framework versions

• Transformers 4.28.0
• Pytorch 2.1.0+cu118
• Datasets 2.15.0
• Tokenizers 0.13.3