mit-b0-finetuned-sidewalks

EgorGrinevich/mit-b0-finetuned-sidewalks

mit-b0-finetuned-sidewalks is a machine learning model from EgorGrinevich. 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

5% of all-time downloads

All-time downloads

141

Public

Repo size

75.8 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: Nov 16, 2023
Updated: Nov 30, 2023
SHA: 0e41cfa1

Base models

nvidia/mit-b0

Model card

From the Hugging Face model README

EgorGrinevich/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: 0.6909
Validation Loss: 0.5868
Validation Mean Iou: 0.2613
Validation Mean Accuracy: 0.3220
Validation Overall Accuracy: 0.8273
Validation Accuracy Unlabeled: 0.0
Validation Accuracy Flat-road: 0.8676
Validation Accuracy Flat-sidewalk: 0.9207
Validation Accuracy Flat-crosswalk: 0.8263
Validation Accuracy Flat-cyclinglane: 0.7711
Validation Accuracy Flat-parkingdriveway: 0.4930
Validation Accuracy Flat-railtrack: nan
Validation Accuracy Flat-curb: 0.4095
Validation Accuracy Human-person: 0.6480
Validation Accuracy Human-rider: 0.0
Validation Accuracy Vehicle-car: 0.9295
Validation Accuracy Vehicle-truck: 0.0
Validation Accuracy Vehicle-bus: 0.0
Validation Accuracy Vehicle-tramtrain: 0.0
Validation Accuracy Vehicle-motorcycle: 0.0
Validation Accuracy Vehicle-bicycle: 0.3762
Validation Accuracy Vehicle-caravan: 0.0
Validation Accuracy Vehicle-cartrailer: 0.0
Validation Accuracy Construction-building: 0.8764
Validation Accuracy Construction-door: 0.0
Validation Accuracy Construction-wall: 0.4062
Validation Accuracy Construction-fenceguardrail: 0.1756
Validation Accuracy Construction-bridge: 0.0
Validation Accuracy Construction-tunnel: nan
Validation Accuracy Construction-stairs: 0.0
Validation Accuracy Object-pole: 0.0996
Validation Accuracy Object-trafficsign: 0.0
Validation Accuracy Object-trafficlight: 0.0
Validation Accuracy Nature-vegetation: 0.9260
Validation Accuracy Nature-terrain: 0.7816
Validation Accuracy Sky: 0.9533
Validation Accuracy Void-ground: 0.0
Validation Accuracy Void-dynamic: 0.0069
Validation Accuracy Void-static: 0.1579
Validation Accuracy Void-unclear: 0.0
Validation Iou Unlabeled: 0.0
Validation Iou Flat-road: 0.7101
Validation Iou Flat-sidewalk: 0.8596
Validation Iou Flat-crosswalk: 0.6695
Validation Iou Flat-cyclinglane: 0.6535
Validation Iou Flat-parkingdriveway: 0.3411
Validation Iou Flat-railtrack: nan
Validation Iou Flat-curb: 0.3182
Validation Iou Human-person: 0.3259
Validation Iou Human-rider: 0.0
Validation Iou Vehicle-car: 0.7776
Validation Iou Vehicle-truck: 0.0
Validation Iou Vehicle-bus: 0.0
Validation Iou Vehicle-tramtrain: 0.0
Validation Iou Vehicle-motorcycle: 0.0
Validation Iou Vehicle-bicycle: 0.2912
Validation Iou Vehicle-caravan: 0.0
Validation Iou Vehicle-cartrailer: 0.0
Validation Iou Construction-building: 0.6492
Validation Iou Construction-door: 0.0
Validation Iou Construction-wall: 0.3519
Validation Iou Construction-fenceguardrail: 0.1676
Validation Iou Construction-bridge: 0.0
Validation Iou Construction-tunnel: nan
Validation Iou Construction-stairs: 0.0
Validation Iou Object-pole: 0.0863
Validation Iou Object-trafficsign: 0.0
Validation Iou Object-trafficlight: 0.0
Validation Iou Nature-vegetation: 0.7991
Validation Iou Nature-terrain: 0.6168
Validation Iou Sky: 0.8961
Validation Iou Void-ground: 0.0
Validation Iou Void-dynamic: 0.0069
Validation Iou Void-static: 0.1034
Validation Iou Void-unclear: 0.0
Epoch: 2

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': False, '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-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-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
1.3415	0.8109	0.1900	0.2324	0.7650	0.6711	0.9475	0.6314	0.7144	0.1245	nan	0.1784	0.0013	0.8892	0.0	0.8853	0.0868	0.0346	nan	0.0006	0.9018	0.6821	0.9120	0.0	0.0084	0.5714	0.7578	0.5849	0.5753	0.1077	nan	0.1464	0.0012	0.6923	0.0	0.5522	0.0843	0.0346	nan	0.0006	0.7606	0.5641	0.8300	0.0	0.0080	0
0.8317	0.7333	0.2208	0.2679	0.7828	0.8055	0.8965	0.5122	0.6911	0.3397	nan	0.2233	0.3391	0.8793	0.0263	0.7717	0.5182	0.1341	nan	0.0227	0.9423	0.7332	0.9396	0.0	0.0642	0.5536	0.8016	0.5026	0.5975	0.2511	nan	0.1826	0.2382	0.7744	0.0260	0.6104	0.3726	0.1160	nan	0.0217	0.7518	0.6109	0.8268	0.0	0.0495	1
0.6909	0.5868	0.2613	0.3220	0.8273	0.8676	0.9207	0.8263	0.7711	0.4930	nan	0.4095	0.6480	0.9295	0.3762	0.8764	0.4062	0.1756	nan	0.0996	0.9260	0.7816	0.9533	0.0069	0.1579	0.7101	0.8596	0.6695	0.6535	0.3411	nan	0.3182	0.3259	0.7776	0.2912	0.6492	0.3519	0.1676	nan	0.0863	0.7991	0.6168	0.8961	0.0069	0.1034	2

Framework versions

Transformers 4.35.2
TensorFlow 2.14.0
Datasets 2.15.0
Tokenizers 0.15.0

Library: transformers
Type: segformer
License: other
Created: Nov 16, 2023
Updated: Nov 30, 2023