segformer-b0-finetuned-segments-sidewalk-2

bilal01/segformer-b0-finetuned-segments-sidewalk-2

segformer-b0-finetuned-segments-sidewalk-2 is a image segmentation model from bilal01. 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

1% of all-time downloads

All-time downloads

985

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: Apr 29, 2023
Updated: May 13, 2023
SHA: 24abf5ee

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 pixel_values, the label and the {'pixel_values': <PIL.JpegImagePlugin.JpegImageFile image mode=RGB size=1920x1080 at 0x7FCAFB662B60>, 'label': <PIL.PngImagePlugin.PngImageFile image mode=RGB size=1x1 at 0x7FCAFB662B30>} datasets. It achieves the following results on the evaluation set:

Loss: 3.5116
Mean Iou: 0.0268
Mean Accuracy: 0.0661
Overall Accuracy: 0.2418
Accuracy Unlabeled: nan
Accuracy Flat-road: 0.0351
Accuracy Flat-sidewalk: 0.5938
Accuracy Flat-crosswalk: 0.3236
Accuracy Flat-cyclinglane: 0.0338
Accuracy Flat-parkingdriveway: 0.0555
Accuracy Flat-railtrack: nan
Accuracy Flat-curb: 0.0006
Accuracy Human-person: 0.0
Accuracy Human-rider: 0.0003
Accuracy Vehicle-car: 0.3388
Accuracy Vehicle-truck: 0.0016
Accuracy Vehicle-bus: 0.0
Accuracy Vehicle-tramtrain: 0.2141
Accuracy Vehicle-motorcycle: 0.0053
Accuracy Vehicle-bicycle: 0.0
Accuracy Vehicle-caravan: 0.0
Accuracy Vehicle-cartrailer: 0.0888
Accuracy Construction-building: 0.0391
Accuracy Construction-door: 0.0
Accuracy Construction-wall: 0.0074
Accuracy Construction-fenceguardrail: 0.0239
Accuracy Construction-bridge: 0.0
Accuracy Construction-tunnel: nan
Accuracy Construction-stairs: 0.0006
Accuracy Object-pole: 0.0593
Accuracy Object-trafficsign: 0.0
Accuracy Object-trafficlight: 0.0665
Accuracy Nature-vegetation: 0.0846
Accuracy Nature-terrain: 0.0002
Accuracy Sky: 0.0030
Accuracy Void-ground: 0.0635
Accuracy Void-dynamic: 0.0004
Accuracy Void-static: 0.0720
Accuracy Void-unclear: 0.0022
Iou Unlabeled: 0.0
Iou Flat-road: 0.0297
Iou Flat-sidewalk: 0.4826
Iou Flat-crosswalk: 0.0624
Iou Flat-cyclinglane: 0.0279
Iou Flat-parkingdriveway: 0.0203
Iou Flat-railtrack: 0.0
Iou Flat-curb: 0.0005
Iou Human-person: 0.0
Iou Human-rider: 0.0001
Iou Vehicle-car: 0.1389
Iou Vehicle-truck: 0.0000
Iou Vehicle-bus: 0.0
Iou Vehicle-tramtrain: 0.0013
Iou Vehicle-motorcycle: 0.0007
Iou Vehicle-bicycle: 0.0
Iou Vehicle-caravan: 0.0
Iou Vehicle-cartrailer: 0.0004
Iou Construction-building: 0.0383
Iou Construction-door: 0.0
Iou Construction-wall: 0.0057
Iou Construction-fenceguardrail: 0.0127
Iou Construction-bridge: 0.0
Iou Construction-tunnel: 0.0
Iou Construction-stairs: 0.0001
Iou Object-pole: 0.0085
Iou Object-trafficsign: 0.0
Iou Object-trafficlight: 0.0002
Iou Nature-vegetation: 0.0818
Iou Nature-terrain: 0.0002
Iou Sky: 0.0027
Iou Void-ground: 0.0115
Iou Void-dynamic: 0.0001
Iou Void-static: 0.0102
Iou Void-unclear: 0.0021

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: 2
eval_batch_size: 2
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 0.025

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
3.5028	0.01	5	3.5307	0.0194	0.0486	0.1779	nan	0.0150	0.4721	0.2351	0.0249	0.0409	nan	0.0003	0.0	0.0003	0.1461	0.0231	0.0	0.2163	0.0047	0.0	0.0	0.0318	0.0223	0.0003	0.0136	0.0166	0.0	nan	0.0008	0.0511	0.0	0.0665	0.0261	0.0005	0.0010	0.0697	0.0014	0.0720	0.0020	0.0	0.0128	0.3979	0.0509	0.0221	0.0166	0.0	0.0003	0.0	0.0001	0.0769	0.0000	0.0	0.0015	0.0003	0.0	0.0	0.0001	0.0219	0.0001	0.0089	0.0103	0.0	0.0	0.0001	0.0070	0.0	0.0001	0.0257	0.0005	0.0009	0.0109	0.0004	0.0099	0.0019
3.3613	0.03	10	3.5116	0.0268	0.0661	0.2418	nan	0.0351	0.5938	0.3236	0.0338	0.0555	nan	0.0006	0.0	0.0003	0.3388	0.0016	0.0	0.2141	0.0053	0.0	0.0	0.0888	0.0391	0.0	0.0074	0.0239	0.0	nan	0.0006	0.0593	0.0	0.0665	0.0846	0.0002	0.0030	0.0635	0.0004	0.0720	0.0022	0.0	0.0297	0.4826	0.0624	0.0279	0.0203	0.0	0.0005	0.0	0.0001	0.1389	0.0000	0.0	0.0013	0.0007	0.0	0.0	0.0004	0.0383	0.0	0.0057	0.0127	0.0	0.0	0.0001	0.0085	0.0	0.0002	0.0818	0.0002	0.0027	0.0115	0.0001	0.0102	0.0021

Framework versions

Transformers 4.28.0
Pytorch 2.0.0+cu118
Datasets 2.12.0
Tokenizers 0.13.3

Task: Image Segmentation
Library: transformers
Type: segformer
License: other
Created: Apr 29, 2023
Updated: May 13, 2023