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: 0.1141
• Mean Iou: 0.4323
• Mean Accuracy: 0.8645
• Overall Accuracy: 0.8645
• Accuracy Unlabeled: nan
• Accuracy Tool: nan
• Accuracy Wear: 0.8645
• Iou Unlabeled: 0.0
• Iou Tool: nan
• Iou Wear: 0.8645

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	Accuracy Wear	Iou Unlabeled	Iou Tool	Iou Wear
0.7016	1.82	20	0.9090	0.4940	0.9880	0.9880	nan	nan	0.9880	0.0	nan	0.9880
0.5409	3.64	40	0.6405	0.4986	0.9972	0.9972	nan	nan	0.9972	0.0	nan	0.9972
0.4261	5.45	60	0.4407	0.4846	0.9692	0.9692	nan	nan	0.9692	0.0	nan	0.9692
0.3251	7.27	80	0.4075	0.4692	0.9383	0.9383	nan	nan	0.9383	0.0	nan	0.9383
0.2993	9.09	100	0.3055	0.4739	0.9477	0.9477	nan	nan	0.9477	0.0	nan	0.9477
0.2724	10.91	120	0.3326	0.4759	0.9518	0.9518	nan	nan	0.9518	0.0	nan	0.9518
0.2154	12.73	140	0.3281	0.4786	0.9573	0.9573	nan	nan	0.9573	0.0	nan	0.9573
0.1732	14.55	160	0.2322	0.4415	0.8831	0.8831	nan	nan	0.8831	0.0	nan	0.8831
0.1376	16.36	180	0.2063	0.3969	0.7937	0.7937	nan	nan	0.7937	0.0	nan	0.7937
0.1326	18.18	200	0.2147	0.4613	0.9226	0.9226	nan	nan	0.9226	0.0	nan	0.9226
0.1333	20.0	220	0.1711	0.4373	0.8747	0.8747	nan	nan	0.8747	0.0	nan	0.8747
0.1235	21.82	240	0.1550	0.4374	0.8748	0.8748	nan	nan	0.8748	0.0	nan	0.8748
0.0976	23.64	260	0.1640	0.4373	0.8745	0.8745	nan	nan	0.8745	0.0	nan	0.8745
0.078	25.45	280	0.1463	0.4505	0.9010	0.9010	nan	nan	0.9010	0.0	nan	0.9010
0.0753	27.27	300	0.1395	0.4387	0.8774	0.8774	nan	nan	0.8774	0.0	nan	0.8774
0.0703	29.09	320	0.1529	0.4550	0.9100	0.9100	nan	nan	0.9100	0.0	nan	0.9100
0.0665	30.91	340	0.1336	0.4414	0.8828	0.8828	nan	nan	0.8828	0.0	nan	0.8828
0.0606	32.73	360	0.1320	0.4484	0.8968	0.8968	nan	nan	0.8968	0.0	nan	0.8968
0.0814	34.55	380	0.1215	0.4220	0.8439	0.8439	nan	nan	0.8439	0.0	nan	0.8439
0.0578	36.36	400	0.1194	0.4266	0.8531	0.8531	nan	nan	0.8531	0.0	nan	0.8531
0.0511	38.18	420	0.1232	0.4417	0.8835	0.8835	nan	nan	0.8835	0.0	nan	0.8835
0.0471	40.0	440	0.1182	0.4409	0.8817	0.8817	nan	nan	0.8817	0.0	nan	0.8817
0.0484	41.82	460	0.1084	0.4258	0.8515	0.8515	nan	nan	0.8515	0.0	nan	0.8515
0.0497	43.64	480	0.1212	0.4425	0.8850	0.8850	nan	nan	0.8850	0.0	nan	0.8850
0.0624	45.45	500	0.1071	0.4266	0.8531	0.8531	nan	nan	0.8531	0.0	nan	0.8531
0.0509	47.27	520	0.1157	0.4339	0.8678	0.8678	nan	nan	0.8678	0.0	nan	0.8678
0.0496	49.09	540	0.1141	0.4323	0.8645	0.8645	nan	nan	0.8645	0.0	nan	0.8645

Framework versions

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