--- library_name: transformers license: other base_model: nvidia/segformer-b1-finetuned-ade-512-512 tags: - vision - image-segmentation - generated_from_trainer model-index: - name: my-fine-tuned-model results: [] --- # my-fine-tuned-model This model is a fine-tuned version of [nvidia/segformer-b1-finetuned-ade-512-512](https://huggingface.co/nvidia/segformer-b1-finetuned-ade-512-512) on the segments/sidewalk-semantic dataset. It achieves the following results on the evaluation set: - Loss: 1.6885 - Mean Iou: 0.1644 - Mean Accuracy: 0.2067 - Overall Accuracy: 0.7604 - Accuracy Unlabeled: nan - Accuracy Flat-road: 0.9243 - Accuracy Flat-sidewalk: 0.9308 - Accuracy Flat-crosswalk: 0.0 - Accuracy Flat-cyclinglane: 0.3658 - Accuracy Flat-parkingdriveway: 0.0 - Accuracy Flat-railtrack: nan - Accuracy Flat-curb: 0.0 - Accuracy Human-person: 0.0 - Accuracy Human-rider: 0.0 - Accuracy Vehicle-car: 0.8785 - Accuracy Vehicle-truck: 0.0 - Accuracy Vehicle-bus: 0.0 - Accuracy Vehicle-tramtrain: nan - Accuracy Vehicle-motorcycle: 0.0 - Accuracy Vehicle-bicycle: 0.0 - Accuracy Vehicle-caravan: 0.0 - Accuracy Vehicle-cartrailer: 0.0 - Accuracy Construction-building: 0.8929 - Accuracy Construction-door: 0.0 - Accuracy Construction-wall: 0.0 - Accuracy Construction-fenceguardrail: 0.0 - Accuracy Construction-bridge: 0.0 - Accuracy Construction-tunnel: nan - Accuracy Construction-stairs: 0.0 - Accuracy Object-pole: 0.0 - Accuracy Object-trafficsign: 0.0 - Accuracy Object-trafficlight: 0.0 - Accuracy Nature-vegetation: 0.9517 - Accuracy Nature-terrain: 0.5597 - Accuracy Sky: 0.9033 - Accuracy Void-ground: 0.0 - Accuracy Void-dynamic: 0.0 - Accuracy Void-static: 0.0 - Accuracy Void-unclear: 0.0 - Iou Unlabeled: nan - Iou Flat-road: 0.5694 - Iou Flat-sidewalk: 0.7974 - Iou Flat-crosswalk: 0.0 - Iou Flat-cyclinglane: 0.3462 - Iou Flat-parkingdriveway: 0.0 - Iou Flat-railtrack: nan - Iou Flat-curb: 0.0 - Iou Human-person: 0.0 - Iou Human-rider: 0.0 - Iou Vehicle-car: 0.6909 - Iou Vehicle-truck: 0.0 - Iou Vehicle-bus: 0.0 - Iou Vehicle-tramtrain: nan - Iou Vehicle-motorcycle: 0.0 - Iou Vehicle-bicycle: 0.0 - Iou Vehicle-caravan: 0.0 - Iou Vehicle-cartrailer: 0.0 - Iou Construction-building: 0.5876 - Iou Construction-door: 0.0 - Iou Construction-wall: 0.0 - Iou Construction-fenceguardrail: 0.0 - Iou Construction-bridge: 0.0 - Iou Construction-tunnel: nan - Iou Construction-stairs: 0.0 - Iou Object-pole: 0.0 - Iou Object-trafficsign: 0.0 - Iou Object-trafficlight: 0.0 - Iou Nature-vegetation: 0.7378 - Iou Nature-terrain: 0.5221 - Iou Sky: 0.8453 - Iou Void-ground: 0.0 - Iou Void-dynamic: 0.0 - Iou Void-static: 0.0 - Iou Void-unclear: 0.0 ## 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: 8 - eval_batch_size: 8 - 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: 2 ### 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 | |:-------------:|:-----:|:----:|:---------------:|:--------:|:-------------:|:----------------:|:------------------:|:------------------:|:----------------------:|:-----------------------:|:-------------------------:|:-----------------------------:|:-----------------------:|:------------------:|:---------------------:|:--------------------:|:--------------------:|:----------------------:|:--------------------:|:--------------------------:|:---------------------------:|:------------------------:|:------------------------:|:---------------------------:|:------------------------------:|:--------------------------:|:--------------------------:|:------------------------------------:|:----------------------------:|:----------------------------:|:----------------------------:|:--------------------:|:---------------------------:|:----------------------------:|:--------------------------:|:-----------------------:|:------------:|:--------------------:|:---------------------:|:--------------------:|:---------------------:|:-------------:|:-------------:|:-----------------:|:------------------:|:--------------------:|:------------------------:|:------------------:|:-------------:|:----------------:|:---------------:|:---------------:|:-----------------:|:---------------:|:---------------------:|:----------------------:|:-------------------:|:-------------------:|:----------------------:|:-------------------------:|:---------------------:|:---------------------:|:-------------------------------:|:-----------------------:|:-----------------------:|:-----------------------:|:---------------:|:----------------------:|:-----------------------:|:---------------------:|:------------------:|:-------:|:---------------:|:----------------:|:---------------:|:----------------:| | 2.9927 | 0.2 | 20 | 2.8323 | 0.0790 | 0.1384 | 0.6032 | nan | 0.7510 | 0.9017 | 0.0000 | 0.0002 | 0.0000 | nan | 0.0000 | 0.4465 | 0.0 | 0.3131 | 0.0304 | 0.0 | nan | 0.0007 | 0.0 | 0.0 | 0.0776 | 0.4690 | 0.0051 | 0.0233 | 0.0 | 0.0 | nan | 0.0 | 0.0102 | 0.0 | 0.0 | 0.9462 | 0.0001 | 0.2894 | 0.0 | 0.0006 | 0.0253 | 0.0 | 0.0 | 0.4130 | 0.7047 | 0.0000 | 0.0002 | 0.0000 | 0.0 | 0.0000 | 0.0393 | 0.0 | 0.2934 | 0.0044 | 0.0 | 0.0 | 0.0002 | 0.0 | 0.0 | 0.0062 | 0.3769 | 0.0005 | 0.0210 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0088 | 0.0 | 0.0 | 0.5968 | 0.0001 | 0.2841 | 0.0 | 0.0004 | 0.0145 | 0.0 | | 2.7054 | 0.4 | 40 | 2.4661 | 0.1140 | 0.1677 | 0.6892 | nan | 0.8508 | 0.9033 | 0.0 | 0.0000 | 0.0 | nan | 0.0 | 0.1089 | 0.0 | 0.7446 | 0.0 | 0.0 | nan | 0.0 | 0.0 | 0.0 | 0.0 | 0.7878 | 0.0 | 0.0152 | 0.0 | 0.0 | nan | 0.0 | 0.0 | 0.0 | 0.0 | 0.9695 | 0.0012 | 0.7824 | 0.0 | 0.0 | 0.0353 | 0.0 | 0.0 | 0.4629 | 0.7392 | 0.0 | 0.0000 | 0.0 | 0.0 | 0.0 | 0.0480 | 0.0 | 0.6429 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.5762 | 0.0 | 0.0150 | 0.0 | 0.0 | nan | 0.0 | 0.0 | 0.0 | 0.0 | 0.6004 | 0.0012 | 0.7581 | 0.0 | 0.0 | 0.0316 | 0.0 | | 2.3703 | 0.6 | 60 | 2.2220 | 0.1307 | 0.1726 | 0.7091 | nan | 0.8602 | 0.9235 | 0.0 | 0.0087 | 0.0 | nan | 0.0 | 0.0078 | 0.0 | 0.8029 | 0.0 | 0.0 | nan | 0.0 | 0.0 | 0.0 | 0.0 | 0.8432 | 0.0 | 0.0032 | 0.0 | 0.0 | nan | 0.0 | 0.0 | 0.0 | 0.0 | 0.9634 | 0.0720 | 0.8469 | 0.0 | 0.0 | 0.0175 | 0.0 | nan | 0.4991 | 0.7506 | 0.0 | 0.0087 | 0.0 | nan | 0.0 | 0.0066 | 0.0 | 0.6632 | 0.0 | 0.0 | nan | 0.0 | 0.0 | 0.0 | 0.0 | 0.5803 | 0.0 | 0.0032 | 0.0 | 0.0 | nan | 0.0 | 0.0 | 0.0 | 0.0 | 0.6381 | 0.0711 | 0.8138 | 0.0 | 0.0 | 0.0169 | 0.0 | | 2.1115 | 0.8 | 80 | 2.0338 | 0.1408 | 0.1832 | 0.7268 | nan | 0.8785 | 0.9295 | 0.0 | 0.0351 | 0.0 | nan | 0.0000 | 0.0009 | 0.0 | 0.8476 | 0.0 | 0.0 | nan | 0.0 | 0.0 | 0.0 | 0.0 | 0.8966 | 0.0 | 0.0 | 0.0 | 0.0 | nan | 0.0 | 0.0 | 0.0 | 0.0 | 0.9472 | 0.2668 | 0.8725 | 0.0 | 0.0 | 0.0061 | 0.0 | nan | 0.5161 | 0.7578 | 0.0 | 0.0350 | 0.0 | nan | 0.0000 | 0.0008 | 0.0 | 0.6755 | 0.0 | 0.0 | nan | 0.0 | 0.0 | 0.0 | 0.0 | 0.5838 | 0.0 | 0.0 | 0.0 | 0.0 | nan | 0.0 | 0.0 | 0.0 | 0.0 | 0.7029 | 0.2587 | 0.8285 | 0.0 | 0.0 | 0.0061 | 0.0 | | 2.0943 | 1.0 | 100 | 1.9439 | 0.1409 | 0.1883 | 0.7309 | nan | 0.9316 | 0.9111 | 0.0 | 0.0606 | 0.0 | nan | 0.0 | 0.0000 | 0.0 | 0.8286 | 0.0 | 0.0 | nan | 0.0 | 0.0 | 0.0 | 0.0 | 0.9048 | 0.0 | 0.0 | 0.0 | 0.0 | nan | 0.0 | 0.0 | 0.0 | 0.0 | 0.9431 | 0.3701 | 0.8879 | 0.0 | 0.0 | 0.0005 | 0.0 | nan | 0.4925 | 0.7839 | 0.0 | 0.0605 | 0.0 | 0.0 | 0.0 | 0.0000 | 0.0 | 0.6885 | 0.0 | 0.0 | nan | 0.0 | 0.0 | 0.0 | 0.0 | 0.5688 | 0.0 | 0.0 | 0.0 | 0.0 | nan | 0.0 | 0.0 | 0.0 | 0.0 | 0.7221 | 0.3542 | 0.8377 | 0.0 | 0.0 | 0.0005 | 0.0 | | 1.962 | 1.2 | 120 | 1.8278 | 0.1523 | 0.1943 | 0.7457 | nan | 0.8894 | 0.9411 | 0.0 | 0.2402 | 0.0 | nan | 0.0 | 0.0 | 0.0 | 0.8845 | 0.0 | 0.0 | nan | 0.0 | 0.0 | 0.0 | 0.0 | 0.8780 | 0.0 | 0.0 | 0.0 | 0.0 | nan | 0.0 | 0.0 | 0.0 | 0.0 | 0.9544 | 0.3342 | 0.9011 | 0.0 | 0.0 | 0.0003 | 0.0 | nan | 0.5553 | 0.7789 | 0.0 | 0.2357 | 0.0 | nan | 0.0 | 0.0 | 0.0 | 0.6855 | 0.0 | 0.0 | nan | 0.0 | 0.0 | 0.0 | 0.0 | 0.5929 | 0.0 | 0.0 | 0.0 | 0.0 | nan | 0.0 | 0.0 | 0.0 | 0.0 | 0.7078 | 0.3194 | 0.8442 | 0.0 | 0.0 | 0.0003 | 0.0 | | 1.8545 | 1.4 | 140 | 1.7513 | 0.1615 | 0.2032 | 0.7568 | nan | 0.9153 | 0.9350 | 0.0 | 0.3471 | 0.0 | nan | 0.0 | 0.0 | 0.0 | 0.8702 | 0.0 | 0.0 | nan | 0.0 | 0.0 | 0.0 | 0.0 | 0.8852 | 0.0 | 0.0 | 0.0 | 0.0 | nan | 0.0 | 0.0 | 0.0 | 0.0 | 0.9552 | 0.4967 | 0.8943 | 0.0 | 0.0 | 0.0000 | 0.0 | nan | 0.5723 | 0.7897 | 0.0 | 0.3290 | 0.0 | nan | 0.0 | 0.0 | 0.0 | 0.6881 | 0.0 | 0.0 | nan | 0.0 | 0.0 | 0.0 | 0.0 | 0.5908 | 0.0 | 0.0 | 0.0 | 0.0 | nan | 0.0 | 0.0 | 0.0 | 0.0 | 0.7264 | 0.4707 | 0.8396 | 0.0 | 0.0 | 0.0000 | 0.0 | | 1.8784 | 1.6 | 160 | 1.7246 | 0.1600 | 0.2014 | 0.7559 | nan | 0.9107 | 0.9375 | 0.0 | 0.3514 | 0.0 | nan | 0.0 | 0.0 | 0.0 | 0.8730 | 0.0 | 0.0 | nan | 0.0 | 0.0 | 0.0 | 0.0 | 0.8984 | 0.0 | 0.0 | 0.0 | 0.0 | nan | 0.0 | 0.0 | 0.0 | 0.0 | 0.9522 | 0.4351 | 0.8847 | 0.0 | 0.0 | 0.0 | 0.0 | nan | 0.5759 | 0.7914 | 0.0 | 0.3336 | 0.0 | nan | 0.0 | 0.0 | 0.0 | 0.6908 | 0.0 | 0.0 | nan | 0.0 | 0.0 | 0.0 | 0.0 | 0.5874 | 0.0 | 0.0 | 0.0 | 0.0 | nan | 0.0 | 0.0 | 0.0 | 0.0 | 0.7221 | 0.4148 | 0.8429 | 0.0 | 0.0 | 0.0 | 0.0 | | 1.9631 | 1.8 | 180 | 1.7066 | 0.1627 | 0.2047 | 0.7573 | nan | 0.9303 | 0.9268 | 0.0 | 0.3374 | 0.0 | nan | 0.0 | 0.0 | 0.0 | 0.8747 | 0.0 | 0.0 | nan | 0.0 | 0.0 | 0.0 | 0.0 | 0.8908 | 0.0 | 0.0 | 0.0 | 0.0 | nan | 0.0 | 0.0 | 0.0 | 0.0 | 0.9549 | 0.5359 | 0.8947 | 0.0 | 0.0 | 0.0 | 0.0 | nan | 0.5559 | 0.7977 | 0.0 | 0.3210 | 0.0 | nan | 0.0 | 0.0 | 0.0 | 0.6966 | 0.0 | 0.0 | nan | 0.0 | 0.0 | 0.0 | 0.0 | 0.5896 | 0.0 | 0.0 | 0.0 | 0.0 | nan | 0.0 | 0.0 | 0.0 | 0.0 | 0.7321 | 0.5057 | 0.8436 | 0.0 | 0.0 | 0.0 | 0.0 | | 1.8769 | 2.0 | 200 | 1.6885 | 0.1644 | 0.2067 | 0.7604 | nan | 0.9243 | 0.9308 | 0.0 | 0.3658 | 0.0 | nan | 0.0 | 0.0 | 0.0 | 0.8785 | 0.0 | 0.0 | nan | 0.0 | 0.0 | 0.0 | 0.0 | 0.8929 | 0.0 | 0.0 | 0.0 | 0.0 | nan | 0.0 | 0.0 | 0.0 | 0.0 | 0.9517 | 0.5597 | 0.9033 | 0.0 | 0.0 | 0.0 | 0.0 | nan | 0.5694 | 0.7974 | 0.0 | 0.3462 | 0.0 | nan | 0.0 | 0.0 | 0.0 | 0.6909 | 0.0 | 0.0 | nan | 0.0 | 0.0 | 0.0 | 0.0 | 0.5876 | 0.0 | 0.0 | 0.0 | 0.0 | nan | 0.0 | 0.0 | 0.0 | 0.0 | 0.7378 | 0.5221 | 0.8453 | 0.0 | 0.0 | 0.0 | 0.0 | ### Framework versions - Transformers 4.48.0 - Pytorch 2.1.1+cu118 - Datasets 3.2.0 - Tokenizers 0.21.0