--- 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: 0.1141 - 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