|
--- |
|
license: other |
|
base_model: nvidia/mit-b0 |
|
tags: |
|
- vision |
|
- image-segmentation |
|
- generated_from_trainer |
|
model-index: |
|
- name: segformer-b0-finetuned-segments-sidewalk-2 |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# segformer-b0-finetuned-segments-sidewalk-2 |
|
|
|
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: 1.8299 |
|
- Mean Iou: 0.1367 |
|
- Mean Accuracy: 0.1860 |
|
- Overall Accuracy: 0.6943 |
|
- Accuracy Unlabeled: nan |
|
- Accuracy Flat-road: 0.7986 |
|
- Accuracy Flat-sidewalk: 0.8984 |
|
- Accuracy Flat-crosswalk: 0.0 |
|
- Accuracy Flat-cyclinglane: 0.0233 |
|
- Accuracy Flat-parkingdriveway: 0.0008 |
|
- Accuracy Flat-railtrack: nan |
|
- Accuracy Flat-curb: 0.0 |
|
- Accuracy Human-person: 0.0 |
|
- Accuracy Human-rider: 0.0 |
|
- Accuracy Vehicle-car: 0.8604 |
|
- Accuracy Vehicle-truck: 0.0 |
|
- Accuracy Vehicle-bus: nan |
|
- Accuracy Vehicle-tramtrain: 0.0 |
|
- Accuracy Vehicle-motorcycle: 0.0 |
|
- Accuracy Vehicle-bicycle: 0.0 |
|
- Accuracy Vehicle-caravan: 0.0 |
|
- Accuracy Vehicle-cartrailer: 0.0 |
|
- Accuracy Construction-building: 0.8665 |
|
- Accuracy Construction-door: 0.0 |
|
- Accuracy Construction-wall: 0.0 |
|
- Accuracy Construction-fenceguardrail: 0.0 |
|
- Accuracy Construction-bridge: 0.0 |
|
- Accuracy Construction-tunnel: 0.0 |
|
- Accuracy Construction-stairs: 0.0 |
|
- Accuracy Object-pole: 0.0 |
|
- Accuracy Object-trafficsign: 0.0 |
|
- Accuracy Object-trafficlight: 0.0 |
|
- Accuracy Nature-vegetation: 0.9388 |
|
- Accuracy Nature-terrain: 0.7081 |
|
- Accuracy Sky: 0.8565 |
|
- Accuracy Void-ground: 0.0001 |
|
- Accuracy Void-dynamic: 0.0 |
|
- Accuracy Void-static: 0.0 |
|
- Accuracy Void-unclear: 0.0 |
|
- Iou Unlabeled: nan |
|
- Iou Flat-road: 0.4128 |
|
- Iou Flat-sidewalk: 0.7214 |
|
- Iou Flat-crosswalk: 0.0 |
|
- Iou Flat-cyclinglane: 0.0233 |
|
- Iou Flat-parkingdriveway: 0.0008 |
|
- Iou Flat-railtrack: nan |
|
- Iou Flat-curb: 0.0 |
|
- Iou Human-person: 0.0 |
|
- Iou Human-rider: 0.0 |
|
- Iou Vehicle-car: 0.6003 |
|
- Iou Vehicle-truck: 0.0 |
|
- Iou Vehicle-bus: nan |
|
- Iou Vehicle-tramtrain: 0.0 |
|
- Iou Vehicle-motorcycle: 0.0 |
|
- Iou Vehicle-bicycle: 0.0 |
|
- Iou Vehicle-caravan: 0.0 |
|
- Iou Vehicle-cartrailer: 0.0 |
|
- Iou Construction-building: 0.5461 |
|
- Iou Construction-door: 0.0 |
|
- Iou Construction-wall: 0.0 |
|
- Iou Construction-fenceguardrail: 0.0 |
|
- Iou Construction-bridge: 0.0 |
|
- Iou Construction-tunnel: 0.0 |
|
- Iou Construction-stairs: 0.0 |
|
- Iou Object-pole: 0.0 |
|
- Iou Object-trafficsign: 0.0 |
|
- Iou Object-trafficlight: 0.0 |
|
- Iou Nature-vegetation: 0.7232 |
|
- Iou Nature-terrain: 0.5549 |
|
- Iou Sky: 0.7907 |
|
- Iou Void-ground: 0.0001 |
|
- 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: 64 |
|
- eval_batch_size: 64 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 8 |
|
|
|
### 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 | |
|
|:-------------:|:------:|:----:|:---------------:|:--------:|:-------------:|:----------------:|:------------------:|:------------------:|:----------------------:|:-----------------------:|:-------------------------:|:-----------------------------:|:-----------------------:|:------------------:|:---------------------:|:--------------------:|:--------------------:|:----------------------:|:--------------------:|:--------------------------:|:---------------------------:|:------------------------:|:------------------------:|:---------------------------:|:------------------------------:|:--------------------------:|:--------------------------:|:------------------------------------:|:----------------------------:|:----------------------------:|:----------------------------:|:--------------------:|:---------------------------:|:----------------------------:|:--------------------------:|:-----------------------:|:------------:|:--------------------:|:---------------------:|:--------------------:|:---------------------:|:-------------:|:-------------:|:-----------------:|:------------------:|:--------------------:|:------------------------:|:------------------:|:-------------:|:----------------:|:---------------:|:---------------:|:-----------------:|:---------------:|:---------------------:|:----------------------:|:-------------------:|:-------------------:|:----------------------:|:-------------------------:|:---------------------:|:---------------------:|:-------------------------------:|:-----------------------:|:-----------------------:|:-----------------------:|:---------------:|:----------------------:|:-----------------------:|:---------------------:|:------------------:|:-------:|:---------------:|:----------------:|:---------------:|:----------------:| |
|
| 2.6535 | 1.5385 | 20 | 2.8741 | 0.0846 | 0.1365 | 0.6009 | nan | 0.2219 | 0.9273 | 0.0 | 0.0017 | 0.0042 | nan | 0.0000 | 0.0014 | 0.0 | 0.8438 | 0.0 | nan | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.7341 | 0.0 | 0.0015 | 0.0019 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.9709 | 0.1359 | 0.5242 | 0.0 | 0.0000 | 0.0000 | 0.0 | 0.0 | 0.1852 | 0.5896 | 0.0 | 0.0017 | 0.0041 | 0.0 | 0.0000 | 0.0013 | 0.0 | 0.4925 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.4757 | 0.0 | 0.0015 | 0.0018 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.5807 | 0.1127 | 0.5151 | 0.0 | 0.0000 | 0.0000 | 0.0 | |
|
| 2.2209 | 3.0769 | 40 | 2.1895 | 0.1089 | 0.1592 | 0.6529 | nan | 0.6642 | 0.9009 | 0.0 | 0.0020 | 0.0002 | nan | 0.0 | 0.0 | 0.0 | 0.8372 | 0.0 | nan | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.8318 | 0.0 | 0.0001 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.9586 | 0.2673 | 0.6333 | 0.0000 | 0.0 | 0.0 | 0.0 | nan | 0.3818 | 0.6832 | 0.0 | 0.0020 | 0.0002 | 0.0 | 0.0 | 0.0 | 0.0 | 0.5601 | 0.0 | nan | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.4918 | 0.0 | 0.0001 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.6325 | 0.2290 | 0.6137 | 0.0000 | 0.0 | 0.0 | 0.0 | |
|
| 1.9209 | 4.6154 | 60 | 1.9240 | 0.1295 | 0.1779 | 0.6803 | nan | 0.7491 | 0.8970 | 0.0 | 0.0037 | 0.0003 | nan | 0.0 | 0.0001 | 0.0 | 0.8615 | 0.0 | nan | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.8579 | 0.0 | 0.0000 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.9436 | 0.5907 | 0.7886 | 0.0003 | 0.0 | 0.0 | 0.0 | nan | 0.3990 | 0.7030 | 0.0 | 0.0037 | 0.0003 | nan | 0.0 | 0.0001 | 0.0 | 0.5788 | 0.0 | nan | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.5252 | 0.0 | 0.0000 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.7042 | 0.4845 | 0.7438 | 0.0003 | 0.0 | 0.0 | 0.0 | |
|
| 1.9014 | 6.1538 | 80 | 1.8370 | 0.1346 | 0.1829 | 0.6899 | nan | 0.7851 | 0.8979 | 0.0 | 0.0146 | 0.0006 | nan | 0.0 | 0.0000 | 0.0 | 0.8365 | 0.0 | nan | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.8694 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.9449 | 0.6680 | 0.8361 | 0.0001 | 0.0 | 0.0 | 0.0 | nan | 0.4097 | 0.7159 | 0.0 | 0.0145 | 0.0006 | nan | 0.0 | 0.0000 | 0.0 | 0.6037 | 0.0 | nan | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.5376 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.7130 | 0.5332 | 0.7782 | 0.0001 | 0.0 | 0.0 | 0.0 | |
|
| 1.8127 | 7.6923 | 100 | 1.8299 | 0.1367 | 0.1860 | 0.6943 | nan | 0.7986 | 0.8984 | 0.0 | 0.0233 | 0.0008 | nan | 0.0 | 0.0 | 0.0 | 0.8604 | 0.0 | nan | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.8665 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.9388 | 0.7081 | 0.8565 | 0.0001 | 0.0 | 0.0 | 0.0 | nan | 0.4128 | 0.7214 | 0.0 | 0.0233 | 0.0008 | nan | 0.0 | 0.0 | 0.0 | 0.6003 | 0.0 | nan | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.5461 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.7232 | 0.5549 | 0.7907 | 0.0001 | 0.0 | 0.0 | 0.0 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.41.2 |
|
- Pytorch 2.3.1+cu121 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.19.1 |
|
|
