segformer-finetuned-sidewalk-10k-steps

brandyDolly/segformer-finetuned-sidewalk-10k-steps

segformer-finetuned-sidewalk-10k-steps is a image segmentation model from brandyDolly. 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 apache-2.0.

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

Downloads · 30 days

5% of all-time downloads

All-time downloads

598

Public

Parameters

60.2M

5.2 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors241 MB · 100%

At a glance

Task: Image Segmentation
Library: transformers
License: apache-2.0
Model type: upernet
Access: Public
Created: Nov 20, 2024
Updated: Nov 30, 2024
SHA: c56a704f

Base models

microsoft/beit-base-finetuned-ade-640-640

Model card

From the Hugging Face model README

segformer-finetuned-sidewalk-10k-steps

This model is a fine-tuned version of microsoft/beit-base-finetuned-ade-640-640 on the segments/sidewalk-semantic dataset. It achieves the following results on the evaluation set:

Loss: 3.7903
Mean Iou: 0.0583
Mean Accuracy: 0.1188
Overall Accuracy: 0.5138
Accuracy Unlabeled: nan
Accuracy Flat-road: 0.3738
Accuracy Flat-sidewalk: 0.8070
Accuracy Flat-crosswalk: 0.2760
Accuracy Flat-cyclinglane: 0.0412
Accuracy Flat-parkingdriveway: 0.0002
Accuracy Flat-railtrack: nan
Accuracy Flat-curb: 0.0013
Accuracy Human-person: 0.0073
Accuracy Human-rider: 0.0
Accuracy Vehicle-car: 0.9825
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: 0.0098
Accuracy Construction-door: 0.1165
Accuracy Construction-wall: 0.0000
Accuracy Construction-fenceguardrail: 0.0
Accuracy Construction-bridge: 0.0
Accuracy Construction-tunnel: nan
Accuracy Construction-stairs: 0.0659
Accuracy Object-pole: 0.0438
Accuracy Object-trafficsign: 0.0
Accuracy Object-trafficlight: 0.0
Accuracy Nature-vegetation: 0.9260
Accuracy Nature-terrain: 0.0287
Accuracy Sky: 0.0
Accuracy Void-ground: 0.0
Accuracy Void-dynamic: 0.0
Accuracy Void-static: 0.0036
Accuracy Void-unclear: 0.0
Iou Unlabeled: 0.0
Iou Flat-road: 0.2457
Iou Flat-sidewalk: 0.6862
Iou Flat-crosswalk: 0.0806
Iou Flat-cyclinglane: 0.0394
Iou Flat-parkingdriveway: 0.0001
Iou Flat-railtrack: 0.0
Iou Flat-curb: 0.0013
Iou Human-person: 0.0044
Iou Human-rider: 0.0
Iou Vehicle-car: 0.3160
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: 0.0096
Iou Construction-door: 0.0317
Iou Construction-wall: 0.0000
Iou Construction-fenceguardrail: 0.0
Iou Construction-bridge: 0.0
Iou Construction-tunnel: 0.0
Iou Construction-stairs: 0.0103
Iou Object-pole: 0.0226
Iou Object-trafficsign: 0.0
Iou Object-trafficlight: 0.0
Iou Nature-vegetation: 0.5656
Iou Nature-terrain: 0.0255
Iou Sky: 0.0
Iou Void-ground: 0.0
Iou Void-dynamic: 0.0
Iou Void-static: 0.0031
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: 2
eval_batch_size: 2
seed: 1337
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: polynomial
training_steps: 10

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
No log	0.0235	10	3.7903	0.0583	0.1188	0.5138	nan	0.3738	0.8070	0.2760	0.0412	0.0002	nan	0.0013	0.0073	0.0	0.9825	0.0	0.0	nan	0.0	0.0	0.0	0.0	0.0098	0.1165	0.0000	0.0	0.0	nan	0.0659	0.0438	0.0	0.0	0.9260	0.0287	0.0	0.0	0.0	0.0036	0.0	0.0	0.2457	0.6862	0.0806	0.0394	0.0001	0.0	0.0013	0.0044	0.0	0.3160	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0096	0.0317	0.0000	0.0	0.0	0.0	0.0103	0.0226	0.0	0.0	0.5656	0.0255	0.0	0.0	0.0	0.0031	0.0

Framework versions

Transformers 4.47.0.dev0
Pytorch 2.5.1+cu124
Datasets 3.1.0
Tokenizers 0.20.3

Task: Image Segmentation
Library: transformers
Type: upernet
License: apache-2.0
Created: Nov 20, 2024
Updated: Nov 30, 2024