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_segmentsai_tools dataset. It achieves the following results on the evaluation set:

• Loss: 0.0341
• Mean Iou: 0.4939
• Mean Accuracy: 0.9878
• Overall Accuracy: 0.9878
• Accuracy Unlabeled: nan
• Accuracy Tool: 0.9878
• Iou Unlabeled: 0.0
• Iou Tool: 0.9878

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
0.2127	1.82	20	0.3537	0.4996	0.9991	0.9991	nan	0.9991	0.0	0.9991
0.2095	3.64	40	0.1407	0.4987	0.9974	0.9974	nan	0.9974	0.0	0.9974
0.1253	5.45	60	0.1011	0.4970	0.9940	0.9940	nan	0.9940	0.0	0.9940
0.0812	7.27	80	0.0821	0.4957	0.9914	0.9914	nan	0.9914	0.0	0.9914
0.0841	9.09	100	0.0652	0.4926	0.9851	0.9851	nan	0.9851	0.0	0.9851
0.0574	10.91	120	0.0612	0.4930	0.9861	0.9861	nan	0.9861	0.0	0.9861
0.047	12.73	140	0.0562	0.4940	0.9880	0.9880	nan	0.9880	0.0	0.9880
0.0542	14.55	160	0.0488	0.4937	0.9874	0.9874	nan	0.9874	0.0	0.9874
0.0405	16.36	180	0.0487	0.4958	0.9916	0.9916	nan	0.9916	0.0	0.9916
0.045	18.18	200	0.0484	0.4964	0.9929	0.9929	nan	0.9929	0.0	0.9929
0.0487	20.0	220	0.0412	0.4936	0.9873	0.9873	nan	0.9873	0.0	0.9873
0.0417	21.82	240	0.0397	0.4936	0.9872	0.9872	nan	0.9872	0.0	0.9872
0.0525	23.64	260	0.0393	0.4934	0.9868	0.9868	nan	0.9868	0.0	0.9868
0.0425	25.45	280	0.0381	0.4930	0.9861	0.9861	nan	0.9861	0.0	0.9861
0.0386	27.27	300	0.0393	0.4927	0.9855	0.9855	nan	0.9855	0.0	0.9855
0.0239	29.09	320	0.0387	0.4933	0.9866	0.9866	nan	0.9866	0.0	0.9866
0.0279	30.91	340	0.0369	0.4941	0.9882	0.9882	nan	0.9882	0.0	0.9882
0.0194	32.73	360	0.0368	0.4916	0.9832	0.9832	nan	0.9832	0.0	0.9832
0.0238	34.55	380	0.0370	0.4937	0.9874	0.9874	nan	0.9874	0.0	0.9874
0.0281	36.36	400	0.0347	0.4930	0.9859	0.9859	nan	0.9859	0.0	0.9859
0.0218	38.18	420	0.0351	0.4924	0.9848	0.9848	nan	0.9848	0.0	0.9848
0.0197	40.0	440	0.0354	0.4932	0.9864	0.9864	nan	0.9864	0.0	0.9864
0.0197	41.82	460	0.0343	0.4933	0.9865	0.9865	nan	0.9865	0.0	0.9865
0.0231	43.64	480	0.0345	0.4931	0.9862	0.9862	nan	0.9862	0.0	0.9862
0.0223	45.45	500	0.0346	0.4938	0.9875	0.9875	nan	0.9875	0.0	0.9875
0.0184	47.27	520	0.0340	0.4927	0.9854	0.9854	nan	0.9854	0.0	0.9854
0.0202	49.09	540	0.0341	0.4939	0.9878	0.9878	nan	0.9878	0.0	0.9878

Framework versions

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