segformer-finetuned-fingertip-10-steps

Gregghe/segformer-finetuned-fingertip-10-steps

segformer-finetuned-fingertip-10-steps is a image segmentation model from Gregghe. 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

14.9 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: Dec 29, 2023
Updated: Dec 29, 2023
SHA: 882ad7d0

Base models

nvidia/mit-b0

Model card

From the Hugging Face model README

segformer-finetuned-fingertip-10-steps

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: 3.5204
Mean Iou: 0.0132
Mean Accuracy: 0.0688
Overall Accuracy: 0.0956
Accuracy Unlabeled: nan
Accuracy Flat-road: 0.0201
Accuracy Flat-sidewalk: 0.1177
Accuracy Flat-crosswalk: 0.0014
Accuracy Flat-cyclinglane: 0.4426
Accuracy Flat-parkingdriveway: 0.0021
Accuracy Flat-railtrack: nan
Accuracy Flat-curb: 0.0008
Accuracy Human-person: 0.0010
Accuracy Human-rider: 0.0077
Accuracy Vehicle-car: 0.1566
Accuracy Vehicle-truck: 0.0040
Accuracy Vehicle-bus: 0.0
Accuracy Vehicle-tramtrain: nan
Accuracy Vehicle-motorcycle: 0.5317
Accuracy Vehicle-bicycle: 0.0892
Accuracy Vehicle-caravan: 0.0
Accuracy Vehicle-cartrailer: nan
Accuracy Construction-building: 0.0578
Accuracy Construction-door: 0.0682
Accuracy Construction-wall: 0.0002
Accuracy Construction-fenceguardrail: 0.0000
Accuracy Construction-bridge: 0.0
Accuracy Construction-tunnel: nan
Accuracy Construction-stairs: 0.0055
Accuracy Object-pole: 0.0162
Accuracy Object-trafficsign: 0.0
Accuracy Object-trafficlight: 0.3811
Accuracy Nature-vegetation: 0.0756
Accuracy Nature-terrain: 0.0010
Accuracy Sky: 0.0038
Accuracy Void-ground: 0.0400
Accuracy Void-dynamic: 0.0002
Accuracy Void-static: 0.0386
Accuracy Void-unclear: 0.0
Iou Unlabeled: 0.0
Iou Flat-road: 0.0193
Iou Flat-sidewalk: 0.1141
Iou Flat-crosswalk: 0.0013
Iou Flat-cyclinglane: 0.0702
Iou Flat-parkingdriveway: 0.0019
Iou Flat-railtrack: 0.0
Iou Flat-curb: 0.0007
Iou Human-person: 0.0005
Iou Human-rider: 0.0001
Iou Vehicle-car: 0.1087
Iou Vehicle-truck: 0.0003
Iou Vehicle-bus: 0.0
Iou Vehicle-tramtrain: 0.0
Iou Vehicle-motorcycle: 0.0004
Iou Vehicle-bicycle: 0.0085
Iou Vehicle-caravan: 0.0
Iou Vehicle-cartrailer: 0.0
Iou Construction-building: 0.0413
Iou Construction-door: 0.0067
Iou Construction-wall: 0.0002
Iou Construction-fenceguardrail: 0.0000
Iou Construction-bridge: 0.0
Iou Construction-tunnel: 0.0
Iou Construction-stairs: 0.0021
Iou Object-pole: 0.0036
Iou Object-trafficsign: 0.0
Iou Object-trafficlight: 0.0001
Iou Nature-vegetation: 0.0663
Iou Nature-terrain: 0.0009
Iou Sky: 0.0038
Iou Void-ground: 0.0049
Iou Void-dynamic: 0.0000
Iou Void-static: 0.0046
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: 8
eval_batch_size: 8
seed: 1337
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
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	0.09	10	3.5204	0.0132	0.0688	0.0956	nan	0.0201	0.1177	0.0014	0.4426	0.0021	nan	0.0008	0.0010	0.0077	0.1566	0.0040	0.0	nan	0.5317	0.0892	0.0	nan	0.0578	0.0682	0.0002	0.0000	0.0	nan	0.0055	0.0162	0.0	0.3811	0.0756	0.0010	0.0038	0.0400	0.0002	0.0386	0.0	0.0	0.0193	0.1141	0.0013	0.0702	0.0019	0.0	0.0007	0.0005	0.0001	0.1087	0.0003	0.0	0.0	0.0004	0.0085	0.0	0.0	0.0413	0.0067	0.0002	0.0000	0.0	0.0	0.0021	0.0036	0.0	0.0001	0.0663	0.0009	0.0038	0.0049	0.0000	0.0046	0.0

Framework versions

Transformers 4.37.0.dev0
Pytorch 2.1.1+cu118
Datasets 2.16.0
Tokenizers 0.15.0

Task: Image Segmentation
Library: transformers
Type: segformer
License: other
Created: Dec 29, 2023
Updated: Dec 29, 2023