--- library_name: transformers license: other base_model: nvidia/mit-b0 tags: - vision - image-segmentation - generated_from_trainer model-index: - name: segformer-b0-finetuned-segments-sidewalk-oct-22 results: [] --- # segformer-b0-finetuned-segments-sidewalk-oct-22 This model is a fine-tuned version of [nvidia/mit-b0](https://huggingface.co./nvidia/mit-b0) on the segments/sidewalk-semantic dataset. It achieves the following results on the evaluation set: - Loss: 1.4669 - Mean Iou: 0.1972 - Mean Accuracy: 0.2562 - Overall Accuracy: 0.7152 - Accuracy Unlabeled: nan - Accuracy Flat-road: 0.9357 - Accuracy Flat-sidewalk: 0.9011 - Accuracy Flat-crosswalk: 0.0 - Accuracy Flat-cyclinglane: 0.9814 - Accuracy Flat-parkingdriveway: 0.0 - Accuracy Flat-railtrack: nan - Accuracy Flat-curb: 0.3500 - Accuracy Human-person: 0.0 - Accuracy Human-rider: 0.0 - Accuracy Vehicle-car: 0.8336 - Accuracy Vehicle-truck: nan - Accuracy Vehicle-bus: 0.0 - Accuracy Vehicle-tramtrain: nan - Accuracy Vehicle-motorcycle: 0.0 - Accuracy Vehicle-bicycle: 0.0 - Accuracy Vehicle-caravan: nan - Accuracy Vehicle-cartrailer: nan - Accuracy Construction-building: 0.7899 - Accuracy Construction-door: 0.0 - Accuracy Construction-wall: 0.2041 - Accuracy Construction-fenceguardrail: 0.0 - Accuracy Construction-bridge: nan - Accuracy Construction-tunnel: nan - Accuracy Construction-stairs: 0.0 - Accuracy Object-pole: 0.0 - Accuracy Object-trafficsign: 0.0 - Accuracy Object-trafficlight: nan - Accuracy Nature-vegetation: 0.8356 - Accuracy Nature-terrain: 0.0 - Accuracy Sky: 0.5731 - Accuracy Void-ground: 0.0 - Accuracy Void-dynamic: 0.0 - Accuracy Void-static: 0.0 - Accuracy Void-unclear: nan - Iou Unlabeled: nan - Iou Flat-road: 0.6487 - Iou Flat-sidewalk: 0.6719 - Iou Flat-crosswalk: 0.0 - Iou Flat-cyclinglane: 0.9208 - Iou Flat-parkingdriveway: 0.0 - Iou Flat-railtrack: nan - Iou Flat-curb: 0.2442 - Iou Human-person: 0.0 - Iou Human-rider: 0.0 - Iou Vehicle-car: 0.5671 - Iou Vehicle-truck: nan - Iou Vehicle-bus: 0.0 - Iou Vehicle-tramtrain: nan - Iou Vehicle-motorcycle: 0.0 - Iou Vehicle-bicycle: 0.0 - Iou Vehicle-caravan: nan - Iou Vehicle-cartrailer: nan - Iou Construction-building: 0.5253 - Iou Construction-door: 0.0 - Iou Construction-wall: 0.1883 - Iou Construction-fenceguardrail: 0.0 - Iou Construction-bridge: nan - Iou Construction-tunnel: nan - Iou Construction-stairs: 0.0 - Iou Object-pole: 0.0 - Iou Object-trafficsign: 0.0 - Iou Object-trafficlight: nan - Iou Nature-vegetation: 0.5974 - Iou Nature-terrain: 0.0 - Iou Sky: 0.5671 - Iou Void-ground: 0.0 - Iou Void-dynamic: 0.0 - Iou Void-static: 0.0 - Iou Void-unclear: nan ## 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: 6 - eval_batch_size: 6 - seed: 42 - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: linear - num_epochs: 15 ### Training results | Training Loss | Epoch | Step | Validation Loss | Mean Iou | Mean Accuracy | Overall Accuracy | Accuracy Unlabeled | Accuracy Flat-road | Accuracy Flat-sidewalk | Accuracy Flat-crosswalk | Accuracy Flat-cyclinglane | Accuracy Flat-parkingdriveway | Accuracy Flat-railtrack | Accuracy Flat-curb | Accuracy Human-person | Accuracy Human-rider | Accuracy Vehicle-car | Accuracy Vehicle-truck | Accuracy Vehicle-bus | Accuracy Vehicle-tramtrain | Accuracy Vehicle-motorcycle | Accuracy Vehicle-bicycle | Accuracy Vehicle-caravan | Accuracy Vehicle-cartrailer | Accuracy Construction-building | Accuracy Construction-door | Accuracy Construction-wall | Accuracy Construction-fenceguardrail | Accuracy Construction-bridge | Accuracy Construction-tunnel | Accuracy Construction-stairs | Accuracy Object-pole | Accuracy Object-trafficsign | Accuracy Object-trafficlight | Accuracy Nature-vegetation | Accuracy Nature-terrain | Accuracy Sky | Accuracy Void-ground | Accuracy Void-dynamic | Accuracy Void-static | Accuracy Void-unclear | Iou Unlabeled | Iou Flat-road | Iou Flat-sidewalk | Iou Flat-crosswalk | Iou Flat-cyclinglane | Iou Flat-parkingdriveway | Iou Flat-railtrack | Iou Flat-curb | Iou Human-person | Iou Human-rider | Iou Vehicle-car | Iou Vehicle-truck | Iou Vehicle-bus | Iou Vehicle-tramtrain | Iou Vehicle-motorcycle | Iou Vehicle-bicycle | Iou Vehicle-caravan | Iou Vehicle-cartrailer | Iou Construction-building | Iou Construction-door | Iou Construction-wall | Iou Construction-fenceguardrail | Iou Construction-bridge | Iou Construction-tunnel | Iou Construction-stairs | Iou Object-pole | Iou Object-trafficsign | Iou Object-trafficlight | Iou Nature-vegetation | Iou Nature-terrain | Iou Sky | Iou Void-ground | Iou Void-dynamic | Iou Void-static | Iou Void-unclear | |:-------------:|:-------:|:----:|:---------------:|:--------:|:-------------:|:----------------:|:------------------:|:------------------:|:----------------------:|:-----------------------:|:-------------------------:|:-----------------------------:|:-----------------------:|:------------------:|:---------------------:|:--------------------:|:--------------------:|:----------------------:|:--------------------:|:--------------------------:|:---------------------------:|:------------------------:|:------------------------:|:---------------------------:|:------------------------------:|:--------------------------:|:--------------------------:|:------------------------------------:|:----------------------------:|:----------------------------:|:----------------------------:|:--------------------:|:---------------------------:|:----------------------------:|:--------------------------:|:-----------------------:|:------------:|:--------------------:|:---------------------:|:--------------------:|:---------------------:|:-------------:|:-------------:|:-----------------:|:------------------:|:--------------------:|:------------------------:|:------------------:|:-------------:|:----------------:|:---------------:|:---------------:|:-----------------:|:---------------:|:---------------------:|:----------------------:|:-------------------:|:-------------------:|:----------------------:|:-------------------------:|:---------------------:|:---------------------:|:-------------------------------:|:-----------------------:|:-----------------------:|:-----------------------:|:---------------:|:----------------------:|:-----------------------:|:---------------------:|:------------------:|:-------:|:---------------:|:----------------:|:---------------:|:----------------:| | 1.6415 | 2.8571 | 20 | 1.6084 | 0.1694 | 0.2310 | 0.6914 | nan | 0.9531 | 0.8595 | 0.0 | 0.9741 | 0.0001 | nan | 0.2029 | 0.0 | 0.0 | 0.8208 | nan | 0.0 | nan | 0.0 | 0.0 | nan | nan | 0.7820 | 0.0 | 0.0056 | 0.0 | nan | nan | 0.0 | 0.0 | 0.0 | nan | 0.8447 | 0.0 | 0.3309 | 0.0 | 0.0 | 0.0 | nan | nan | 0.5908 | 0.6652 | 0.0 | 0.8715 | 0.0001 | nan | 0.1537 | 0.0 | 0.0 | 0.5398 | nan | 0.0 | nan | 0.0 | 0.0 | nan | nan | 0.4867 | 0.0 | 0.0054 | 0.0 | nan | nan | 0.0 | 0.0 | 0.0 | nan | 0.5918 | 0.0 | 0.3307 | 0.0 | 0.0 | 0.0 | nan | | 1.2815 | 5.7143 | 40 | 1.5589 | 0.1752 | 0.2359 | 0.6972 | nan | 0.9423 | 0.8679 | 0.0 | 0.9794 | 0.0 | nan | 0.2620 | 0.0 | 0.0 | 0.8132 | nan | 0.0 | nan | 0.0 | 0.0 | nan | nan | 0.7779 | 0.0 | 0.0410 | 0.0 | nan | nan | 0.0 | 0.0 | 0.0 | nan | 0.8569 | 0.0 | 0.3579 | 0.0 | 0.0 | 0.0 | nan | nan | 0.6130 | 0.6656 | 0.0 | 0.8866 | 0.0 | nan | 0.1805 | 0.0 | 0.0 | 0.5453 | nan | 0.0 | nan | 0.0 | 0.0 | nan | nan | 0.4985 | 0.0 | 0.0381 | 0.0 | nan | nan | 0.0 | 0.0 | 0.0 | nan | 0.5938 | 0.0 | 0.3578 | 0.0 | 0.0 | 0.0 | nan | | 1.2436 | 8.5714 | 60 | 1.4972 | 0.1884 | 0.2481 | 0.7089 | nan | 0.9335 | 0.8880 | 0.0 | 0.9926 | 0.0 | nan | 0.3274 | 0.0 | 0.0 | 0.8123 | nan | 0.0 | nan | 0.0 | 0.0 | nan | nan | 0.7794 | 0.0 | 0.0690 | 0.0 | nan | nan | 0.0 | 0.0 | 0.0 | nan | 0.8518 | 0.0 | 0.5475 | 0.0 | 0.0 | 0.0 | nan | nan | 0.6532 | 0.6654 | 0.0 | 0.8826 | 0.0 | nan | 0.2386 | 0.0 | 0.0 | 0.5566 | nan | 0.0 | nan | 0.0 | 0.0 | nan | nan | 0.5082 | 0.0 | 0.0653 | 0.0 | nan | nan | 0.0 | 0.0 | 0.0 | nan | 0.5957 | 0.0 | 0.5442 | 0.0 | 0.0 | 0.0 | nan | | 1.2207 | 11.4286 | 80 | 1.4880 | 0.1931 | 0.2516 | 0.7137 | nan | 0.9329 | 0.9003 | 0.0 | 0.9711 | 0.0 | nan | 0.3744 | 0.0 | 0.0 | 0.8177 | nan | 0.0 | nan | 0.0 | 0.0 | nan | nan | 0.8023 | 0.0 | 0.1182 | 0.0 | nan | nan | 0.0 | 0.0 | 0.0 | nan | 0.8337 | 0.0 | 0.5407 | 0.0 | 0.0 | 0.0 | nan | nan | 0.6559 | 0.6672 | 0.0 | 0.9216 | 0.0 | nan | 0.2617 | 0.0 | 0.0 | 0.5584 | nan | 0.0 | nan | 0.0 | 0.0 | nan | nan | 0.5209 | 0.0 | 0.1091 | 0.0 | nan | nan | 0.0 | 0.0 | 0.0 | nan | 0.5960 | 0.0 | 0.5375 | 0.0 | 0.0 | 0.0 | nan | | 1.2494 | 14.2857 | 100 | 1.4669 | 0.1972 | 0.2562 | 0.7152 | nan | 0.9357 | 0.9011 | 0.0 | 0.9814 | 0.0 | nan | 0.3500 | 0.0 | 0.0 | 0.8336 | nan | 0.0 | nan | 0.0 | 0.0 | nan | nan | 0.7899 | 0.0 | 0.2041 | 0.0 | nan | nan | 0.0 | 0.0 | 0.0 | nan | 0.8356 | 0.0 | 0.5731 | 0.0 | 0.0 | 0.0 | nan | nan | 0.6487 | 0.6719 | 0.0 | 0.9208 | 0.0 | nan | 0.2442 | 0.0 | 0.0 | 0.5671 | nan | 0.0 | nan | 0.0 | 0.0 | nan | nan | 0.5253 | 0.0 | 0.1883 | 0.0 | nan | nan | 0.0 | 0.0 | 0.0 | nan | 0.5974 | 0.0 | 0.5671 | 0.0 | 0.0 | 0.0 | nan | ### Framework versions - Transformers 4.46.3 - Pytorch 2.5.1+cu121 - Datasets 3.1.0 - Tokenizers 0.20.3