metadata
license: other
base_model: nvidia/mit-b0
tags:
- generated_from_keras_callback
model-index:
- name: lalla123/mit-b0-finetuned-sidewalks
results: []
lalla123/mit-b0-finetuned-sidewalks
This model is a fine-tuned version of nvidia/mit-b0 on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 1.3346
- Validation Loss: 1.1664
- Validation Mean Iou: 0.1412
- Validation Mean Accuracy: 0.1958
- Validation Overall Accuracy: 0.7144
- Validation Accuracy Unlabeled: 0.0
- Validation Accuracy Flat-road: 0.8177
- Validation Accuracy Flat-sidewalk: 0.8998
- Validation Accuracy Flat-crosswalk: 0.0009
- Validation Accuracy Flat-cyclinglane: 0.4161
- Validation Accuracy Flat-parkingdriveway: 0.0254
- Validation Accuracy Flat-railtrack: nan
- Validation Accuracy Flat-curb: 0.0
- Validation Accuracy Human-person: 0.0159
- Validation Accuracy Human-rider: 0.0
- Validation Accuracy Vehicle-car: 0.8980
- Validation Accuracy Vehicle-truck: 0.0
- Validation Accuracy Vehicle-bus: 0.0
- Validation Accuracy Vehicle-tramtrain: nan
- Validation Accuracy Vehicle-motorcycle: 0.0
- Validation Accuracy Vehicle-bicycle: 0.0094
- Validation Accuracy Vehicle-caravan: 0.0
- Validation Accuracy Vehicle-cartrailer: 0.0
- Validation Accuracy Construction-building: 0.8424
- Validation Accuracy Construction-door: 0.0
- Validation Accuracy Construction-wall: 0.0179
- Validation Accuracy Construction-fenceguardrail: 0.0007
- Validation Accuracy Construction-bridge: 0.0
- Validation Accuracy Construction-tunnel: nan
- Validation Accuracy Construction-stairs: 0.0
- Validation Accuracy Object-pole: 0.0039
- Validation Accuracy Object-trafficsign: 0.0
- Validation Accuracy Object-trafficlight: 0.0
- Validation Accuracy Nature-vegetation: 0.9113
- Validation Accuracy Nature-terrain: 0.5713
- Validation Accuracy Sky: 0.8346
- Validation Accuracy Void-ground: 0.0
- Validation Accuracy Void-dynamic: 0.0
- Validation Accuracy Void-static: 0.0017
- Validation Accuracy Void-unclear: 0.0
- Validation Iou Unlabeled: 0.0
- Validation Iou Flat-road: 0.5710
- Validation Iou Flat-sidewalk: 0.6881
- Validation Iou Flat-crosswalk: 0.0009
- Validation Iou Flat-cyclinglane: 0.3661
- Validation Iou Flat-parkingdriveway: 0.0228
- Validation Iou Flat-railtrack: nan
- Validation Iou Flat-curb: 0.0
- Validation Iou Human-person: 0.0155
- Validation Iou Human-rider: 0.0
- Validation Iou Vehicle-car: 0.6173
- Validation Iou Vehicle-truck: 0.0
- Validation Iou Vehicle-bus: 0.0
- Validation Iou Vehicle-tramtrain: 0.0
- Validation Iou Vehicle-motorcycle: 0.0
- Validation Iou Vehicle-bicycle: 0.0082
- Validation Iou Vehicle-caravan: 0.0
- Validation Iou Vehicle-cartrailer: 0.0
- Validation Iou Construction-building: 0.5245
- Validation Iou Construction-door: 0.0
- Validation Iou Construction-wall: 0.0173
- Validation Iou Construction-fenceguardrail: 0.0007
- Validation Iou Construction-bridge: 0.0
- Validation Iou Construction-tunnel: 0.0
- Validation Iou Construction-stairs: 0.0
- Validation Iou Object-pole: 0.0036
- Validation Iou Object-trafficsign: 0.0
- Validation Iou Object-trafficlight: 0.0
- Validation Iou Nature-vegetation: 0.7286
- Validation Iou Nature-terrain: 0.4534
- Validation Iou Sky: 0.7817
- Validation Iou Void-ground: 0.0
- Validation Iou Void-dynamic: 0.0
- Validation Iou Void-static: 0.0016
- Validation Iou Void-unclear: 0.0
- Epoch: 4
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:
- optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': False, 'is_legacy_optimizer': False, 'learning_rate': 6e-05, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
- training_precision: float32
Training results
Train Loss | Validation Loss | Validation Mean Iou | Validation Mean Accuracy | Validation Overall Accuracy | Validation Accuracy Unlabeled | Validation Accuracy Flat-road | Validation Accuracy Flat-sidewalk | Validation Accuracy Flat-crosswalk | Validation Accuracy Flat-cyclinglane | Validation Accuracy Flat-parkingdriveway | Validation Accuracy Flat-railtrack | Validation Accuracy Flat-curb | Validation Accuracy Human-person | Validation Accuracy Human-rider | Validation Accuracy Vehicle-car | Validation Accuracy Vehicle-truck | Validation Accuracy Vehicle-bus | Validation Accuracy Vehicle-tramtrain | Validation Accuracy Vehicle-motorcycle | Validation Accuracy Vehicle-bicycle | Validation Accuracy Vehicle-caravan | Validation Accuracy Vehicle-cartrailer | Validation Accuracy Construction-building | Validation Accuracy Construction-door | Validation Accuracy Construction-wall | Validation Accuracy Construction-fenceguardrail | Validation Accuracy Construction-bridge | Validation Accuracy Construction-tunnel | Validation Accuracy Construction-stairs | Validation Accuracy Object-pole | Validation Accuracy Object-trafficsign | Validation Accuracy Object-trafficlight | Validation Accuracy Nature-vegetation | Validation Accuracy Nature-terrain | Validation Accuracy Sky | Validation Accuracy Void-ground | Validation Accuracy Void-dynamic | Validation Accuracy Void-static | Validation Accuracy Void-unclear | Validation Iou Unlabeled | Validation Iou Flat-road | Validation Iou Flat-sidewalk | Validation Iou Flat-crosswalk | Validation Iou Flat-cyclinglane | Validation Iou Flat-parkingdriveway | Validation Iou Flat-railtrack | Validation Iou Flat-curb | Validation Iou Human-person | Validation Iou Human-rider | Validation Iou Vehicle-car | Validation Iou Vehicle-truck | Validation Iou Vehicle-bus | Validation Iou Vehicle-tramtrain | Validation Iou Vehicle-motorcycle | Validation Iou Vehicle-bicycle | Validation Iou Vehicle-caravan | Validation Iou Vehicle-cartrailer | Validation Iou Construction-building | Validation Iou Construction-door | Validation Iou Construction-wall | Validation Iou Construction-fenceguardrail | Validation Iou Construction-bridge | Validation Iou Construction-tunnel | Validation Iou Construction-stairs | Validation Iou Object-pole | Validation Iou Object-trafficsign | Validation Iou Object-trafficlight | Validation Iou Nature-vegetation | Validation Iou Nature-terrain | Validation Iou Sky | Validation Iou Void-ground | Validation Iou Void-dynamic | Validation Iou Void-static | Validation Iou Void-unclear | Epoch |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
3.2668 | 2.2005 | 0.0769 | 0.1266 | 0.5045 | 0.0 | 0.1022 | 0.8700 | 0.0002 | 0.0030 | 0.0004 | nan | 0.0001 | 0.0056 | 0.0 | 0.7906 | 0.0 | 0.0 | nan | 0.0 | 0.1304 | 0.0 | 0.0 | 0.1840 | 0.0361 | 0.0005 | 0.1705 | 0.0 | nan | 0.0194 | 0.0012 | 0.0048 | 0.0 | 0.8954 | 0.0633 | 0.7360 | 0.0061 | 0.0 | 0.0307 | 0.0 | 0.0 | 0.0940 | 0.5718 | 0.0002 | 0.0030 | 0.0004 | 0.0 | 0.0001 | 0.0046 | 0.0 | 0.4853 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0100 | 0.0 | 0.0 | 0.1710 | 0.0016 | 0.0005 | 0.0985 | 0.0 | 0.0 | 0.0004 | 0.0012 | 0.0001 | 0.0 | 0.6556 | 0.0588 | 0.5173 | 0.0015 | 0.0 | 0.0150 | 0.0 | 0 |
2.0643 | 1.6749 | 0.1030 | 0.1583 | 0.6241 | 0.0 | 0.5562 | 0.8974 | 0.0000 | 0.0126 | 0.0053 | nan | 0.0001 | 0.0002 | 0.0 | 0.8013 | 0.0 | 0.0 | nan | 0.0 | 0.0928 | 0.0 | 0.0 | 0.7299 | 0.0000 | 0.0023 | 0.0522 | 0.0 | nan | 0.0137 | 0.0006 | 0.0 | 0.0 | 0.9393 | 0.1737 | 0.7552 | 0.0105 | 0.0001 | 0.0214 | 0.0 | 0.0 | 0.4201 | 0.5989 | 0.0000 | 0.0125 | 0.0052 | 0.0 | 0.0001 | 0.0002 | 0.0 | 0.5466 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0256 | 0.0 | 0.0 | 0.4609 | 0.0000 | 0.0022 | 0.0450 | 0.0 | 0.0 | 0.0022 | 0.0006 | 0.0 | 0.0 | 0.6592 | 0.1499 | 0.6526 | 0.0060 | 0.0001 | 0.0171 | 0.0 | 1 |
1.7439 | 1.4214 | 0.1264 | 0.1860 | 0.6745 | 0.0 | 0.8063 | 0.8609 | 0.0 | 0.1874 | 0.0075 | nan | 0.0000 | 0.0008 | 0.0 | 0.8652 | 0.0 | 0.0 | nan | 0.0 | 0.1508 | 0.0 | 0.0 | 0.7206 | 0.0008 | 0.0019 | 0.0062 | 0.0 | nan | 0.0282 | 0.0022 | 0.0 | 0.0 | 0.9237 | 0.4783 | 0.8933 | 0.0006 | 0.0 | 0.0170 | 0.0 | 0.0 | 0.4746 | 0.6616 | 0.0 | 0.1848 | 0.0073 | nan | 0.0000 | 0.0008 | 0.0 | 0.5882 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0407 | 0.0 | 0.0 | 0.4779 | 0.0006 | 0.0019 | 0.0060 | 0.0 | 0.0 | 0.0056 | 0.0021 | 0.0 | 0.0 | 0.7045 | 0.3983 | 0.7282 | 0.0006 | 0.0 | 0.0150 | 0.0 | 2 |
1.3795 | 1.2564 | 0.1365 | 0.1987 | 0.7068 | 0.0 | 0.7505 | 0.9141 | 0.0000 | 0.4222 | 0.0106 | nan | 0.0001 | 0.0031 | 0.0 | 0.8707 | 0.0 | 0.0 | nan | 0.0 | 0.0642 | 0.0 | 0.0 | 0.8057 | 0.0003 | 0.0290 | 0.0011 | 0.0 | nan | 0.0 | 0.0027 | 0.0 | 0.0 | 0.8671 | 0.6862 | 0.9098 | 0.0002 | 0.0 | 0.0217 | 0.0 | 0.0 | 0.5495 | 0.6821 | 0.0000 | 0.3661 | 0.0102 | 0.0 | 0.0001 | 0.0031 | 0.0 | 0.6154 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0327 | 0.0 | 0.0 | 0.4963 | 0.0003 | 0.0267 | 0.0011 | 0.0 | 0.0 | 0.0 | 0.0026 | 0.0 | 0.0 | 0.7200 | 0.4961 | 0.7580 | 0.0002 | 0.0 | 0.0177 | 0.0 | 3 |
1.3346 | 1.1664 | 0.1412 | 0.1958 | 0.7144 | 0.0 | 0.8177 | 0.8998 | 0.0009 | 0.4161 | 0.0254 | nan | 0.0 | 0.0159 | 0.0 | 0.8980 | 0.0 | 0.0 | nan | 0.0 | 0.0094 | 0.0 | 0.0 | 0.8424 | 0.0 | 0.0179 | 0.0007 | 0.0 | nan | 0.0 | 0.0039 | 0.0 | 0.0 | 0.9113 | 0.5713 | 0.8346 | 0.0 | 0.0 | 0.0017 | 0.0 | 0.0 | 0.5710 | 0.6881 | 0.0009 | 0.3661 | 0.0228 | nan | 0.0 | 0.0155 | 0.0 | 0.6173 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0082 | 0.0 | 0.0 | 0.5245 | 0.0 | 0.0173 | 0.0007 | 0.0 | 0.0 | 0.0 | 0.0036 | 0.0 | 0.0 | 0.7286 | 0.4534 | 0.7817 | 0.0 | 0.0 | 0.0016 | 0.0 | 4 |
Framework versions
- Transformers 4.42.4
- TensorFlow 2.17.0
- Datasets 2.20.0
- Tokenizers 0.19.1