--- 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](https://huggingface.co./nvidia/mit-b0) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.0406 - Mean Iou: 0.3913 - Mean Accuracy: 0.7826 - Overall Accuracy: 0.7826 - Accuracy Unlabeled: nan - Accuracy Tool: nan - Accuracy Wear: 0.7826 - Iou Unlabeled: 0.0 - Iou Tool: nan - Iou Wear: 0.7826 ## 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 | |:-------------:|:-----:|:----:|:---------------:|:--------:|:-------------:|:----------------:|:------------------:|:-------------:|:-------------:|:-------------:|:--------:|:--------:| | 0.7907 | 1.18 | 20 | 0.8970 | 0.3905 | 0.7810 | 0.7810 | nan | nan | 0.7810 | 0.0 | nan | 0.7810 | | 0.515 | 2.35 | 40 | 0.4998 | 0.3753 | 0.7506 | 0.7506 | nan | nan | 0.7506 | 0.0 | nan | 0.7506 | | 0.405 | 3.53 | 60 | 0.3773 | 0.4074 | 0.8148 | 0.8148 | nan | nan | 0.8148 | 0.0 | nan | 0.8148 | | 0.3532 | 4.71 | 80 | 0.3191 | 0.4127 | 0.8255 | 0.8255 | nan | nan | 0.8255 | 0.0 | nan | 0.8255 | | 0.2912 | 5.88 | 100 | 0.2693 | 0.4314 | 0.8628 | 0.8628 | nan | nan | 0.8628 | 0.0 | nan | 0.8628 | | 0.2128 | 7.06 | 120 | 0.2297 | 0.4067 | 0.8133 | 0.8133 | nan | nan | 0.8133 | 0.0 | nan | 0.8133 | | 0.1676 | 8.24 | 140 | 0.1849 | 0.4101 | 0.8203 | 0.8203 | nan | nan | 0.8203 | 0.0 | nan | 0.8203 | | 0.1712 | 9.41 | 160 | 0.1446 | 0.3677 | 0.7354 | 0.7354 | nan | nan | 0.7354 | 0.0 | nan | 0.7354 | | 0.1344 | 10.59 | 180 | 0.1265 | 0.3931 | 0.7861 | 0.7861 | nan | nan | 0.7861 | 0.0 | nan | 0.7861 | | 0.1315 | 11.76 | 200 | 0.1023 | 0.3511 | 0.7022 | 0.7022 | nan | nan | 0.7022 | 0.0 | nan | 0.7022 | | 0.109 | 12.94 | 220 | 0.1047 | 0.3986 | 0.7973 | 0.7973 | nan | nan | 0.7973 | 0.0 | nan | 0.7973 | | 0.0985 | 14.12 | 240 | 0.0913 | 0.4042 | 0.8084 | 0.8084 | nan | nan | 0.8084 | 0.0 | nan | 0.8084 | | 0.0711 | 15.29 | 260 | 0.0773 | 0.3192 | 0.6384 | 0.6384 | nan | nan | 0.6384 | 0.0 | nan | 0.6384 | | 0.0636 | 16.47 | 280 | 0.0798 | 0.4138 | 0.8275 | 0.8275 | nan | nan | 0.8275 | 0.0 | nan | 0.8275 | | 0.0619 | 17.65 | 300 | 0.0692 | 0.3770 | 0.7540 | 0.7540 | nan | nan | 0.7540 | 0.0 | nan | 0.7540 | | 0.0573 | 18.82 | 320 | 0.0608 | 0.3386 | 0.6771 | 0.6771 | nan | nan | 0.6771 | 0.0 | nan | 0.6771 | | 0.0579 | 20.0 | 340 | 0.0609 | 0.3882 | 0.7765 | 0.7765 | nan | nan | 0.7765 | 0.0 | nan | 0.7765 | | 0.0505 | 21.18 | 360 | 0.0552 | 0.3748 | 0.7496 | 0.7496 | nan | nan | 0.7496 | 0.0 | nan | 0.7496 | | 0.0514 | 22.35 | 380 | 0.0606 | 0.4208 | 0.8416 | 0.8416 | nan | nan | 0.8416 | 0.0 | nan | 0.8416 | | 0.0475 | 23.53 | 400 | 0.0513 | 0.3796 | 0.7593 | 0.7593 | nan | nan | 0.7593 | 0.0 | nan | 0.7593 | | 0.0442 | 24.71 | 420 | 0.0526 | 0.4185 | 0.8371 | 0.8371 | nan | nan | 0.8371 | 0.0 | nan | 0.8371 | | 0.0408 | 25.88 | 440 | 0.0526 | 0.4044 | 0.8087 | 0.8087 | nan | nan | 0.8087 | 0.0 | nan | 0.8087 | | 0.0337 | 27.06 | 460 | 0.0485 | 0.3932 | 0.7865 | 0.7865 | nan | nan | 0.7865 | 0.0 | nan | 0.7865 | | 0.0384 | 28.24 | 480 | 0.0463 | 0.4049 | 0.8098 | 0.8098 | nan | nan | 0.8098 | 0.0 | nan | 0.8098 | | 0.0469 | 29.41 | 500 | 0.0459 | 0.3687 | 0.7374 | 0.7374 | nan | nan | 0.7374 | 0.0 | nan | 0.7374 | | 0.0305 | 30.59 | 520 | 0.0444 | 0.3610 | 0.7220 | 0.7220 | nan | nan | 0.7220 | 0.0 | nan | 0.7220 | | 0.0364 | 31.76 | 540 | 0.0461 | 0.4147 | 0.8294 | 0.8294 | nan | nan | 0.8294 | 0.0 | nan | 0.8294 | | 0.034 | 32.94 | 560 | 0.0434 | 0.3907 | 0.7813 | 0.7813 | nan | nan | 0.7813 | 0.0 | nan | 0.7813 | | 0.0276 | 34.12 | 580 | 0.0431 | 0.3880 | 0.7759 | 0.7759 | nan | nan | 0.7759 | 0.0 | nan | 0.7759 | | 0.0281 | 35.29 | 600 | 0.0424 | 0.3761 | 0.7522 | 0.7522 | nan | nan | 0.7522 | 0.0 | nan | 0.7522 | | 0.0264 | 36.47 | 620 | 0.0438 | 0.4045 | 0.8090 | 0.8090 | nan | nan | 0.8090 | 0.0 | nan | 0.8090 | | 0.0269 | 37.65 | 640 | 0.0430 | 0.4041 | 0.8082 | 0.8082 | nan | nan | 0.8082 | 0.0 | nan | 0.8082 | | 0.0245 | 38.82 | 660 | 0.0409 | 0.3803 | 0.7607 | 0.7607 | nan | nan | 0.7607 | 0.0 | nan | 0.7607 | | 0.0241 | 40.0 | 680 | 0.0436 | 0.4147 | 0.8295 | 0.8295 | nan | nan | 0.8295 | 0.0 | nan | 0.8295 | | 0.027 | 41.18 | 700 | 0.0417 | 0.3901 | 0.7803 | 0.7803 | nan | nan | 0.7803 | 0.0 | nan | 0.7803 | | 0.0227 | 42.35 | 720 | 0.0405 | 0.3914 | 0.7828 | 0.7828 | nan | nan | 0.7828 | 0.0 | nan | 0.7828 | | 0.0269 | 43.53 | 740 | 0.0409 | 0.3907 | 0.7814 | 0.7814 | nan | nan | 0.7814 | 0.0 | nan | 0.7814 | | 0.0223 | 44.71 | 760 | 0.0409 | 0.3938 | 0.7877 | 0.7877 | nan | nan | 0.7877 | 0.0 | nan | 0.7877 | | 0.0268 | 45.88 | 780 | 0.0405 | 0.3888 | 0.7776 | 0.7776 | nan | nan | 0.7776 | 0.0 | nan | 0.7776 | | 0.0228 | 47.06 | 800 | 0.0408 | 0.3908 | 0.7817 | 0.7817 | nan | nan | 0.7817 | 0.0 | nan | 0.7817 | | 0.0218 | 48.24 | 820 | 0.0406 | 0.3868 | 0.7736 | 0.7736 | nan | nan | 0.7736 | 0.0 | nan | 0.7736 | | 0.0221 | 49.41 | 840 | 0.0406 | 0.3913 | 0.7826 | 0.7826 | nan | nan | 0.7826 | 0.0 | nan | 0.7826 | ### Framework versions - Transformers 4.28.0 - Pytorch 2.1.0+cu121 - Datasets 2.16.0 - Tokenizers 0.13.3