segformer-b0-finetuned-segments-sidewalk-2

jericojr23/segformer-b0-finetuned-segments-sidewalk-2

segformer-b0-finetuned-segments-sidewalk-2 is a image segmentation model from jericojr23. 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

151

19% of all-time downloads

All-time downloads

794

Public

Repo size

29.9 MB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.bin15 MB · 100%

At a glance

Task: Image Segmentation
Library: transformers
License: other
Model type: segformer
Access: Public
Created: Oct 19, 2023
Updated: Oct 19, 2023
SHA: 5a2cd908

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: 1.6325
Mean Iou: 0.0535
Mean Accuracy: 0.0868
Overall Accuracy: 0.5176
Accuracy Unlabeled: nan
Accuracy Flat-road: 0.0813
Accuracy Flat-sidewalk: 0.9451
Accuracy Flat-crosswalk: 0.0
Accuracy Flat-cyclinglane: 0.0
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: 0.0017
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: 0.2409
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: 0.9096
Accuracy Nature-terrain: 0.0349
Accuracy Sky: 0.5635
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: 0.0721
Iou Flat-sidewalk: 0.4933
Iou Flat-crosswalk: 0.0
Iou Flat-cyclinglane: 0.0
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: 0.0017
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: 0.1927
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: 0.5226
Iou Nature-terrain: 0.0332
Iou Sky: 0.3971
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: 0.01
train_batch_size: 8
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss	Mean Iou	Mean Accuracy	Overall Accuracy	Accuracy Unlabeled	Accuracy Flat-road	Accuracy Flat-sidewalk	Accuracy Flat-railtrack	Accuracy Vehicle-car	Accuracy Vehicle-tramtrain	Accuracy Construction-building	Accuracy Nature-vegetation	Accuracy Nature-terrain	Accuracy Sky	Iou Unlabeled	Iou Flat-road	Iou Flat-sidewalk	Iou Flat-railtrack	Iou Vehicle-car	Iou Vehicle-tramtrain	Iou Construction-building	Iou Nature-vegetation	Iou Nature-terrain	Iou Sky
2.1406	0.2	20	3.3169	0.0250	0.0555	0.4250	nan	0.0	0.8293	nan	0.0	nan	0.0225	0.9246	0.0	0.0	nan	0.0	0.4257	nan	0.0	nan	0.0208	0.3535	0.0	0.0
1.856	0.4	40	1.9761	0.0295	0.0611	0.4511	nan	0.0	0.8624	nan	0.0	nan	0.1301	0.9616	0.0	0.0	nan	0.0	0.4700	nan	0.0	nan	0.1012	0.3725	0.0	0.0
1.9981	0.6	60	2.2395	0.0259	0.0508	0.4085	nan	0.0	0.9972	nan	0.0	nan	0.4062	0.2213	0.0000	0.0001	nan	0.0	0.4001	nan	0.0	nan	0.2248	0.2034	0.0000	0.0001
2.1244	0.8	80	1.7573	0.0401	0.0707	0.4917	nan	0.0004	0.9494	nan	0.0	nan	0.2756	0.9149	0.0540	0.0670	nan	0.0004	0.4783	nan	0.0	nan	0.1872	0.5061	0.0472	0.0636
1.8822	1.0	100	1.6325	0.0535	0.0868	0.5176	nan	0.0813	0.9451	nan	0.0017	nan	0.2409	0.9096	0.0349	0.5635	nan	0.0721	0.4933	nan	0.0017	nan	0.1927	0.5226	0.0332	0.3971

Framework versions

Transformers 4.34.1
Pytorch 2.1.0+cu118
Datasets 2.14.5
Tokenizers 0.14.1

Task: Image Segmentation
Library: transformers
Type: segformer
License: other
Created: Oct 19, 2023
Updated: Oct 19, 2023