segformer-b0-finetuned-segments-sidewalk-2

Bramwel/segformer-b0-finetuned-segments-sidewalk-2

segformer-b0-finetuned-segments-sidewalk-2 is a image segmentation model from Bramwel. Use it for the image segmentation task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as other.

should probably proofread and complete it, then remove this comment. --

Downloads · 30 days

5% of all-time downloads

All-time downloads

Public

Parameters

3.7M

59.7 MB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors14.9 MB · 100%

At a glance

Task: Image Segmentation
Library: transformers
License: other
Model type: segformer
Access: Public
Created: Jul 2, 2024
Updated: Jul 5, 2024
SHA: e7b2a649

Base models

nvidia/mit-b0

Model card

From the Hugging Face model README

segformer-b0-finetuned-segments-sidewalk-2

This model is a fine-tuned version of nvidia/mit-b0 on the segments/sidewalk-semantic dataset. It achieves the following results on the evaluation set:

Loss: 1.2030
Mean Iou: 0.1619
Mean Accuracy: 0.2092
Overall Accuracy: 0.7485
Accuracy Unlabeled: nan
Accuracy Flat-road: 0.8436
Accuracy Flat-sidewalk: 0.9312
Accuracy Flat-crosswalk: 0.0
Accuracy Flat-cyclinglane: 0.4507
Accuracy Flat-parkingdriveway: 0.0198
Accuracy Flat-railtrack: nan
Accuracy Flat-curb: 0.0
Accuracy Human-person: 0.0
Accuracy Human-rider: 0.0
Accuracy Vehicle-car: 0.9019
Accuracy Vehicle-truck: 0.0
Accuracy Vehicle-bus: 0.0
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: 0.8988
Accuracy Construction-door: 0.0
Accuracy Construction-wall: 0.0004
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: 0.9346
Accuracy Nature-terrain: 0.7865
Accuracy Sky: 0.9277
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: 0.5666
Iou Flat-sidewalk: 0.7709
Iou Flat-crosswalk: 0.0
Iou Flat-cyclinglane: 0.4018
Iou Flat-parkingdriveway: 0.0192
Iou Flat-railtrack: nan
Iou Flat-curb: 0.0
Iou Human-person: 0.0
Iou Human-rider: 0.0
Iou Vehicle-car: 0.6148
Iou Vehicle-truck: 0.0
Iou Vehicle-bus: 0.0
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: 0.5632
Iou Construction-door: 0.0
Iou Construction-wall: 0.0004
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: 0.7501
Iou Nature-terrain: 0.6356
Iou Sky: 0.8596
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: 4
eval_batch_size: 4
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
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-cyclinglane	Accuracy Flat-parkingdriveway	Accuracy Flat-railtrack	Accuracy Flat-curb	Accuracy Vehicle-car	Accuracy Construction-building	Accuracy Construction-wall	Accuracy Construction-tunnel	Accuracy Nature-vegetation	Accuracy Nature-terrain	Accuracy Sky	Iou Unlabeled	Iou Flat-road	Iou Flat-sidewalk	Iou Flat-cyclinglane	Iou Flat-parkingdriveway	Iou Flat-railtrack	Iou Flat-curb	Iou Vehicle-car	Iou Construction-building	Iou Construction-wall	Iou Construction-tunnel	Iou Nature-vegetation	Iou Nature-terrain	Iou Sky
2.3674	0.5	100	1.6720	0.1214	0.1717	0.6859	nan	0.8443	0.9140	0.0013	0.0016	nan	0.0000	0.9316	0.8364	0.0003	nan	0.9363	0.1751	0.8520	nan	0.4679	0.7424	0.0013	0.0016	nan	0.0000	0.4884	0.5352	0.0003	nan	0.6734	0.1662	0.8072
1.6248	1.0	200	1.3491	0.1433	0.1884	0.7207	nan	0.8164	0.9497	0.1026	0.0029	nan	0.0	0.8847	0.8799	0.0003	nan	0.9487	0.5417	0.9021	nan	0.5258	0.7439	0.1022	0.0029	nan	0.0	0.6004	0.5538	0.0003	nan	0.7135	0.4965	0.8474
1.3902	1.5	300	1.2406	0.1583	0.2052	0.7431	nan	0.8351	0.9301	0.4278	0.0119	nan	0.0	0.8945	0.8936	0.0002	nan	0.9464	0.6912	0.9360	nan	0.5562	0.7694	0.3883	0.0117	nan	0.0	0.5991	0.5557	0.0002	nan	0.7361	0.5997	0.8479
1.2893	2.0	400	1.2030	0.1619	0.2092	0.7485	nan	0.8436	0.9312	0.4507	0.0198	nan	0.0	0.9019	0.8988	0.0004	nan	0.9346	0.7865	0.9277	nan	0.5666	0.7709	0.4018	0.0192	nan	0.0	0.6148	0.5632	0.0004	nan	0.7501	0.6356	0.8596

Framework versions

Transformers 4.42.3
Pytorch 2.1.0+rocm5.6
Datasets 2.20.0
Tokenizers 0.19.1

Task: Image Segmentation
Library: transformers
Type: segformer
License: other
Created: Jul 2, 2024
Updated: Jul 5, 2024