README.md

metadata

license: other
tags:
  - vision
  - image-segmentation
  - 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 the HorcruxNo13/toolwear_complete_tool dataset. It achieves the following results on the evaluation set:

• Loss: 0.0236
• Mean Iou: 0.4952
• Mean Accuracy: 0.9903
• Overall Accuracy: 0.9903
• Accuracy Unlabeled: nan
• Accuracy Tool: 0.9903
• Iou Unlabeled: 0.0
• Iou Tool: 0.9903

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
0.1696	1.18	20	0.3490	0.4962	0.9924	0.9924	nan	0.9924	0.0	0.9924
0.1045	2.35	40	0.0977	0.4878	0.9755	0.9755	nan	0.9755	0.0	0.9755
0.0871	3.53	60	0.0650	0.4953	0.9905	0.9905	nan	0.9905	0.0	0.9905
0.0542	4.71	80	0.0652	0.4956	0.9911	0.9911	nan	0.9911	0.0	0.9911
0.0507	5.88	100	0.0573	0.4952	0.9905	0.9905	nan	0.9905	0.0	0.9905
0.0702	7.06	120	0.0510	0.4942	0.9883	0.9883	nan	0.9883	0.0	0.9883
0.0455	8.24	140	0.0487	0.4892	0.9784	0.9784	nan	0.9784	0.0	0.9784
0.049	9.41	160	0.0430	0.4934	0.9867	0.9867	nan	0.9867	0.0	0.9867
0.048	10.59	180	0.0409	0.4940	0.9881	0.9881	nan	0.9881	0.0	0.9881
0.0476	11.76	200	0.0347	0.4965	0.9931	0.9931	nan	0.9931	0.0	0.9931
0.048	12.94	220	0.0366	0.4972	0.9944	0.9944	nan	0.9944	0.0	0.9944
0.0242	14.12	240	0.0341	0.4963	0.9926	0.9926	nan	0.9926	0.0	0.9926
0.0274	15.29	260	0.0305	0.4966	0.9933	0.9933	nan	0.9933	0.0	0.9933
0.0192	16.47	280	0.0318	0.4956	0.9913	0.9913	nan	0.9913	0.0	0.9913
0.0388	17.65	300	0.0280	0.4966	0.9932	0.9932	nan	0.9932	0.0	0.9932
0.0245	18.82	320	0.0280	0.4947	0.9894	0.9894	nan	0.9894	0.0	0.9894
0.0268	20.0	340	0.0268	0.4949	0.9899	0.9899	nan	0.9899	0.0	0.9899
0.0173	21.18	360	0.0278	0.4955	0.9910	0.9910	nan	0.9910	0.0	0.9910
0.0275	22.35	380	0.0270	0.4957	0.9914	0.9914	nan	0.9914	0.0	0.9914
0.0269	23.53	400	0.0271	0.4950	0.9899	0.9899	nan	0.9899	0.0	0.9899
0.0371	24.71	420	0.0252	0.4938	0.9876	0.9876	nan	0.9876	0.0	0.9876
0.0233	25.88	440	0.0264	0.4933	0.9867	0.9867	nan	0.9867	0.0	0.9867
0.0181	27.06	460	0.0257	0.4959	0.9918	0.9918	nan	0.9918	0.0	0.9918
0.0243	28.24	480	0.0255	0.4952	0.9904	0.9904	nan	0.9904	0.0	0.9904
0.0144	29.41	500	0.0244	0.4956	0.9912	0.9912	nan	0.9912	0.0	0.9912
0.0158	30.59	520	0.0251	0.4947	0.9894	0.9894	nan	0.9894	0.0	0.9894
0.017	31.76	540	0.0247	0.4955	0.9911	0.9911	nan	0.9911	0.0	0.9911
0.0179	32.94	560	0.0237	0.4965	0.9930	0.9930	nan	0.9930	0.0	0.9930
0.0162	34.12	580	0.0238	0.4956	0.9911	0.9911	nan	0.9911	0.0	0.9911
0.0191	35.29	600	0.0241	0.4950	0.9901	0.9901	nan	0.9901	0.0	0.9901
0.0133	36.47	620	0.0241	0.4956	0.9911	0.9911	nan	0.9911	0.0	0.9911
0.0118	37.65	640	0.0244	0.4948	0.9896	0.9896	nan	0.9896	0.0	0.9896
0.0133	38.82	660	0.0228	0.4960	0.9921	0.9921	nan	0.9921	0.0	0.9921
0.0197	40.0	680	0.0234	0.4957	0.9914	0.9914	nan	0.9914	0.0	0.9914
0.0168	41.18	700	0.0232	0.4961	0.9922	0.9922	nan	0.9922	0.0	0.9922
0.0119	42.35	720	0.0234	0.4957	0.9914	0.9914	nan	0.9914	0.0	0.9914
0.0155	43.53	740	0.0243	0.4950	0.9900	0.9900	nan	0.9900	0.0	0.9900
0.0126	44.71	760	0.0242	0.4949	0.9897	0.9897	nan	0.9897	0.0	0.9897
0.0129	45.88	780	0.0242	0.4955	0.9910	0.9910	nan	0.9910	0.0	0.9910
0.0116	47.06	800	0.0238	0.4953	0.9906	0.9906	nan	0.9906	0.0	0.9906
0.0122	48.24	820	0.0239	0.4954	0.9908	0.9908	nan	0.9908	0.0	0.9908
0.0164	49.41	840	0.0236	0.4952	0.9903	0.9903	nan	0.9903	0.0	0.9903

Framework versions

• Transformers 4.28.0
• Pytorch 2.1.0+cu121
• Datasets 2.16.0
• Tokenizers 0.13.3