mit-b0-finetuned-sidewalks

ThomasLam/mit-b0-finetuned-sidewalks

mit-b0-finetuned-sidewalks is a machine learning model from ThomasLam. Use it for the machine learning 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.

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

Downloads · 30 days

3% of all-time downloads

All-time downloads

187

Public

Repo size

167 MB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.h515.2 MB · 100%

At a glance

Library: transformers
License: other
Model type: segformer
Access: Public
Created: Mar 26, 2023
Updated: Mar 27, 2023
SHA: 1a68d2b0

Model card

From the Hugging Face model README

ThomasLam/mit-b0-finetuned-sidewalks

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

Train Loss: 0.5617
Validation Loss: 0.5455
Validation Mean Iou: 0.2981
Validation Mean Accuracy: 0.3694
Validation Overall Accuracy: 0.8400
Validation Accuracy Unlabeled: 0.0
Validation Accuracy Flat-road: 0.8592
Validation Accuracy Flat-sidewalk: 0.9015
Validation Accuracy Flat-crosswalk: 0.6943
Validation Accuracy Flat-cyclinglane: 0.8471
Validation Accuracy Flat-parkingdriveway: 0.5867
Validation Accuracy Flat-railtrack: nan
Validation Accuracy Flat-curb: 0.4839
Validation Accuracy Human-person: 0.5402
Validation Accuracy Human-rider: 0.0
Validation Accuracy Vehicle-car: 0.9318
Validation Accuracy Vehicle-truck: 0.0
Validation Accuracy Vehicle-bus: 0.0
Validation Accuracy Vehicle-tramtrain: nan
Validation Accuracy Vehicle-motorcycle: 0.0
Validation Accuracy Vehicle-bicycle: 0.6756
Validation Accuracy Vehicle-caravan: 0.0
Validation Accuracy Vehicle-cartrailer: 0.0
Validation Accuracy Construction-building: 0.8796
Validation Accuracy Construction-door: 0.0
Validation Accuracy Construction-wall: 0.6019
Validation Accuracy Construction-fenceguardrail: 0.5454
Validation Accuracy Construction-bridge: 0.0
Validation Accuracy Construction-tunnel: nan
Validation Accuracy Construction-stairs: 0.0
Validation Accuracy Object-pole: 0.3915
Validation Accuracy Object-trafficsign: 0.0
Validation Accuracy Object-trafficlight: 0.0
Validation Accuracy Nature-vegetation: 0.9456
Validation Accuracy Nature-terrain: 0.7224
Validation Accuracy Sky: 0.9630
Validation Accuracy Void-ground: 0.0
Validation Accuracy Void-dynamic: 0.0005
Validation Accuracy Void-static: 0.2520
Validation Accuracy Void-unclear: 0.0
Validation Iou Unlabeled: 0.0
Validation Iou Flat-road: 0.6794
Validation Iou Flat-sidewalk: 0.8423
Validation Iou Flat-crosswalk: 0.4614
Validation Iou Flat-cyclinglane: 0.7741
Validation Iou Flat-parkingdriveway: 0.3965
Validation Iou Flat-railtrack: nan
Validation Iou Flat-curb: 0.3812
Validation Iou Human-person: 0.3313
Validation Iou Human-rider: 0.0
Validation Iou Vehicle-car: 0.7684
Validation Iou Vehicle-truck: 0.0
Validation Iou Vehicle-bus: 0.0
Validation Iou Vehicle-tramtrain: nan
Validation Iou Vehicle-motorcycle: 0.0
Validation Iou Vehicle-bicycle: 0.4625
Validation Iou Vehicle-caravan: 0.0
Validation Iou Vehicle-cartrailer: 0.0
Validation Iou Construction-building: 0.7518
Validation Iou Construction-door: 0.0
Validation Iou Construction-wall: 0.4870
Validation Iou Construction-fenceguardrail: 0.4067
Validation Iou Construction-bridge: 0.0
Validation Iou Construction-tunnel: nan
Validation Iou Construction-stairs: 0.0
Validation Iou Object-pole: 0.2774
Validation Iou Object-trafficsign: 0.0
Validation Iou Object-trafficlight: 0.0
Validation Iou Nature-vegetation: 0.8138
Validation Iou Nature-terrain: 0.5846
Validation Iou Sky: 0.9136
Validation Iou Void-ground: 0.0
Validation Iou Void-dynamic: 0.0005
Validation Iou Void-static: 0.2057
Validation Iou Void-unclear: 0.0
Epoch: 4

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:

optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': 6e-05, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
training_precision: float32

Training results

Train Loss	Validation Loss	Validation Mean Iou	Validation Mean Accuracy	Validation Overall Accuracy	Validation Accuracy Flat-road	Validation Accuracy Flat-sidewalk	Validation Accuracy Flat-crosswalk	Validation Accuracy Flat-cyclinglane	Validation Accuracy Flat-parkingdriveway	Validation Accuracy Flat-railtrack	Validation Accuracy Flat-curb	Validation Accuracy Human-person	Validation Accuracy Vehicle-car	Validation Accuracy Vehicle-tramtrain	Validation Accuracy Vehicle-bicycle	Validation Accuracy Construction-building	Validation Accuracy Construction-wall	Validation Accuracy Construction-fenceguardrail	Validation Accuracy Construction-tunnel	Validation Accuracy Object-pole	Validation Accuracy Nature-vegetation	Validation Accuracy Nature-terrain	Validation Accuracy Sky	Validation Accuracy Void-dynamic	Validation Accuracy Void-static	Validation Iou Flat-road	Validation Iou Flat-sidewalk	Validation Iou Flat-crosswalk	Validation Iou Flat-cyclinglane	Validation Iou Flat-parkingdriveway	Validation Iou Flat-railtrack	Validation Iou Flat-curb	Validation Iou Human-person	Validation Iou Vehicle-car	Validation Iou Vehicle-tramtrain	Validation Iou Vehicle-bicycle	Validation Iou Construction-building	Validation Iou Construction-wall	Validation Iou Construction-fenceguardrail	Validation Iou Construction-tunnel	Validation Iou Object-pole	Validation Iou Nature-vegetation	Validation Iou Nature-terrain	Validation Iou Sky	Validation Iou Void-dynamic	Validation Iou Void-static	Epoch
1.4680	0.9066	0.1798	0.2394	0.7547	0.8669	0.8589	0.0	0.6786	0.0989	nan	0.0247	0.2642	0.8952	nan	0.0006	0.7945	0.4156	0.1067	nan	0.0810	0.9131	0.7232	0.9213	0.0	0.0180	0.4849	0.7637	0.0	0.6063	0.0951	nan	0.0240	0.1986	0.6356	0.0	0.0006	0.6237	0.3020	0.0966	nan	0.0755	0.7648	0.5032	0.7422	0.0	0.0170	0
0.8567	0.6646	0.2541	0.3119	0.8124	0.8596	0.9440	0.5084	0.6331	0.3103	nan	0.2047	0.5405	0.9264	nan	0.3220	0.8516	0.6289	0.3390	nan	0.2700	0.9158	0.7236	0.9357	0.0	0.0672	0.6107	0.8259	0.4541	0.6072	0.2645	nan	0.1822	0.2658	0.7033	nan	0.2866	0.6977	0.3962	0.2965	nan	0.2208	0.8041	0.5809	0.8706	0.0	0.0630	1
0.7002	0.6058	0.2747	0.3411	0.8279	0.8420	0.9339	0.5835	0.7672	0.4334	nan	0.4080	0.5484	0.9257	nan	0.4079	0.8439	0.6765	0.4692	nan	0.3434	0.9179	0.7872	0.9486	0.0	0.0798	0.6316	0.8505	0.4997	0.6888	0.3585	nan	0.3261	0.2850	0.7418	nan	0.3474	0.7019	0.3816	0.3688	nan	0.2469	0.8183	0.5924	0.8755	0.0	0.0744	2
0.6213	0.5759	0.2858	0.3589	0.8276	0.8817	0.8784	0.7087	0.8404	0.5910	nan	0.3922	0.5252	0.9485	nan	0.5948	0.8582	0.6432	0.4867	nan	0.3592	0.9287	0.7635	0.9531	0.0000	0.1312	0.6807	0.8223	0.4667	0.7441	0.3268	nan	0.3356	0.3185	0.7325	nan	0.4012	0.7425	0.4686	0.3947	nan	0.2611	0.8176	0.6067	0.9076	0.0000	0.1194	3
0.5617	0.5455	0.2981	0.3694	0.8400	0.8592	0.9015	0.6943	0.8471	0.5867	nan	0.4839	0.5402	0.9318	nan	0.6756	0.8796	0.6019	0.5454	nan	0.3915	0.9456	0.7224	0.9630	0.0005	0.2520	0.6794	0.8423	0.4614	0.7741	0.3965	nan	0.3812	0.3313	0.7684	nan	0.4625	0.7518	0.4870	0.4067	nan	0.2774	0.8138	0.5846	0.9136	0.0005	0.2057	4

Framework versions

Transformers 4.27.3
TensorFlow 2.11.0
Datasets 2.10.1
Tokenizers 0.13.2

Library: transformers
Type: segformer
License: other
Created: Mar 26, 2023
Updated: Mar 27, 2023