mit-b0-finetuned-sidewalks

Razi78/mit-b0-finetuned-sidewalks

mit-b0-finetuned-sidewalks is a machine learning model from Razi78. 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

18% of all-time downloads

All-time downloads

Public

Repo size

152 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: Feb 16, 2023
Updated: Feb 16, 2023
SHA: e772ba5a

Model card

From the Hugging Face model README

Razi78/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: 0.3834
Validation Loss: 0.5143
Validation Mean Iou: 0.3111
Validation Mean Accuracy: 0.3771
Validation Overall Accuracy: 0.8584
Validation Accuracy Unlabeled: 0.0
Validation Accuracy Flat-road: 0.9192
Validation Accuracy Flat-sidewalk: 0.9577
Validation Accuracy Flat-crosswalk: 0.7640
Validation Accuracy Flat-cyclinglane: 0.7293
Validation Accuracy Flat-parkingdriveway: 0.5706
Validation Accuracy Flat-railtrack: nan
Validation Accuracy Flat-curb: 0.5961
Validation Accuracy Human-person: 0.4335
Validation Accuracy Human-rider: 0.0004
Validation Accuracy Vehicle-car: 0.9314
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: 0.7297
Validation Accuracy Vehicle-caravan: 0.0
Validation Accuracy Vehicle-cartrailer: 0.0
Validation Accuracy Construction-building: 0.8770
Validation Accuracy Construction-door: 0.1184
Validation Accuracy Construction-wall: 0.6003
Validation Accuracy Construction-fenceguardrail: 0.2523
Validation Accuracy Construction-bridge: 0.0
Validation Accuracy Construction-tunnel: nan
Validation Accuracy Construction-stairs: 0.0002
Validation Accuracy Object-pole: 0.4300
Validation Accuracy Object-trafficsign: 0.0086
Validation Accuracy Object-trafficlight: 0.0
Validation Accuracy Nature-vegetation: 0.9272
Validation Accuracy Nature-terrain: 0.9108
Validation Accuracy Sky: 0.9451
Validation Accuracy Void-ground: 0.0191
Validation Accuracy Void-dynamic: 0.1244
Validation Accuracy Void-static: 0.2207
Validation Accuracy Void-unclear: 0.0
Validation Iou Unlabeled: 0.0
Validation Iou Flat-road: 0.8166
Validation Iou Flat-sidewalk: 0.8868
Validation Iou Flat-crosswalk: 0.6819
Validation Iou Flat-cyclinglane: 0.6879
Validation Iou Flat-parkingdriveway: 0.4524
Validation Iou Flat-railtrack: nan
Validation Iou Flat-curb: 0.4954
Validation Iou Human-person: 0.2162
Validation Iou Human-rider: 0.0004
Validation Iou Vehicle-car: 0.7937
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: 0.3137
Validation Iou Vehicle-caravan: 0.0
Validation Iou Vehicle-cartrailer: 0.0
Validation Iou Construction-building: 0.6885
Validation Iou Construction-door: 0.1172
Validation Iou Construction-wall: 0.3928
Validation Iou Construction-fenceguardrail: 0.2309
Validation Iou Construction-bridge: 0.0
Validation Iou Construction-tunnel: nan
Validation Iou Construction-stairs: 0.0002
Validation Iou Object-pole: 0.3417
Validation Iou Object-trafficsign: 0.0086
Validation Iou Object-trafficlight: 0.0
Validation Iou Nature-vegetation: 0.8341
Validation Iou Nature-terrain: 0.7970
Validation Iou Sky: 0.9032
Validation Iou Void-ground: 0.0129
Validation Iou Void-dynamic: 0.1139
Validation Iou Void-static: 0.1678
Validation Iou Void-unclear: 0.0
Epoch: 9

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', 'learning_rate': 6e-05, 'decay': 0.0, '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 Human-rider	Validation Accuracy Vehicle-car	Validation Accuracy Vehicle-tramtrain	Validation Accuracy Vehicle-bicycle	Validation Accuracy Construction-building	Validation Accuracy Construction-door	Validation Accuracy Construction-wall	Validation Accuracy Construction-fenceguardrail	Validation Accuracy Construction-tunnel	Validation Accuracy Construction-stairs	Validation Accuracy Object-pole	Validation Accuracy Object-trafficsign	Validation Accuracy Nature-vegetation	Validation Accuracy Nature-terrain	Validation Accuracy Sky	Validation Accuracy Void-ground	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 Human-rider	Validation Iou Vehicle-car	Validation Iou Vehicle-tramtrain	Validation Iou Vehicle-bicycle	Validation Iou Construction-building	Validation Iou Construction-door	Validation Iou Construction-wall	Validation Iou Construction-fenceguardrail	Validation Iou Construction-tunnel	Validation Iou Construction-stairs	Validation Iou Object-pole	Validation Iou Object-trafficsign	Validation Iou Nature-vegetation	Validation Iou Nature-terrain	Validation Iou Sky	Validation Iou Void-ground	Validation Iou Void-dynamic	Validation Iou Void-static	Epoch
0.9317	0.8154	0.2102	0.2560	0.7682	0.6893	0.9604	0.0692	0.5295	0.2461	nan	0.1561	0.3200	0.0	0.8354	nan	0.2425	0.9131	0.0	0.4341	0.0393	nan	0.0	0.1490	0.0	0.8925	0.7949	0.8907	0.0	0.0	0.0312	0.6025	0.7613	0.0592	0.4972	0.1904	nan	0.1381	0.1729	0.0	0.6829	nan	0.2326	0.6065	0.0	0.2748	0.0373	nan	0.0	0.1290	0.0	0.7610	0.7122	0.8379	0.0	0.0	0.0290	0
0.7608	0.6595	0.2548	0.3136	0.8171	0.8941	0.9522	0.6912	0.6050	0.3030	nan	0.3367	0.2592	0.0	0.9338	nan	0.6196	0.9157	0.0	0.3823	0.1128	nan	0.0	0.3210	0.0	0.8806	0.8924	0.9015	0.0	0.0000	0.0333	0.7420	0.8433	0.5403	0.5702	0.2545	nan	0.2746	0.1762	0.0	0.6919	nan	0.3429	0.6498	0.0	0.3327	0.1042	nan	0.0	0.2434	0.0	0.7779	0.7237	0.8541	0.0	0.0000	0.0310	1
0.6681	0.6072	0.2674	0.3272	0.8280	0.9032	0.9567	0.7278	0.6428	0.3220	nan	0.4555	0.3397	0.0	0.9113	nan	0.6286	0.9198	0.0	0.4124	0.1341	nan	0.0	0.3081	0.0	0.8981	0.8786	0.9243	0.0	0.0017	0.1065	0.7533	0.8546	0.5263	0.5791	0.2720	nan	0.3614	0.2103	0.0	0.7452	nan	0.3554	0.6599	0.0	0.3313	0.1224	nan	0.0	0.2514	0.0	0.8025	0.7572	0.8844	0.0	0.0017	0.0872	2
0.5925	0.6026	0.2648	0.3393	0.8274	0.9012	0.9596	0.7587	0.4868	0.3931	nan	0.4939	0.4798	0.0	0.9305	nan	0.6949	0.8788	0.0055	0.4856	0.2068	nan	0.0	0.3218	0.0	0.9225	0.8065	0.9463	0.0	0.0088	0.1775	0.7554	0.8616	0.4355	0.4717	0.3184	nan	0.3968	0.1662	0.0	0.7466	nan	0.3030	0.6735	0.0055	0.3466	0.1850	nan	0.0	0.2647	0.0	0.7979	0.7236	0.8846	0.0	0.0087	0.1272	3
0.5490	0.5696	0.2851	0.3592	0.8332	0.9047	0.9542	0.7587	0.8163	0.2408	nan	0.4944	0.4919	0.0	0.9378	nan	0.6285	0.7944	0.0154	0.6766	0.2609	nan	0.0	0.3746	0.0	0.9297	0.8885	0.9420	0.0	0.0162	0.3688	0.7889	0.8429	0.5208	0.6443	0.2243	nan	0.4038	0.2429	0.0	0.7563	nan	0.3698	0.6685	0.0154	0.3882	0.2469	nan	0.0	0.2997	0.0	0.8193	0.7808	0.8957	0.0	0.0162	0.1978	4
0.5087	0.6074	0.2757	0.3621	0.8352	0.8976	0.9445	0.7794	0.8244	0.4367	nan	0.5158	0.3467	0.0	0.9435	nan	0.6765	0.8456	0.0	0.6933	0.3127	nan	0.0	0.3967	0.0	0.8398	0.9282	0.9458	0.0009	0.0311	0.2278	0.8265	0.8780	0.2240	0.6742	0.3488	nan	0.4169	0.2292	0.0	0.7495	nan	0.3271	0.6755	0.0	0.3241	0.2429	nan	0.0	0.3127	0.0	0.7884	0.7138	0.8980	0.0009	0.0307	0.1622	5
0.4645	0.5448	0.2833	0.3577	0.8448	0.9011	0.9398	0.7623	0.8812	0.4475	nan	0.5125	0.2508	0.0	0.9112	nan	0.7279	0.8911	0.0069	0.4498	0.2347	nan	0.0	0.4219	0.0	0.9311	0.8977	0.9586	0.0047	0.0537	0.2607	0.7907	0.8723	0.3294	0.6963	0.3712	nan	0.4011	0.1708	0.0	0.7812	nan	0.2907	0.6882	0.0069	0.3945	0.2080	nan	0.0	0.3297	0.0	0.8056	0.7819	0.8986	0.0044	0.0524	0.1915	6
0.4400	0.5322	0.2999	0.3816	0.8484	0.9128	0.9403	0.7752	0.7936	0.5206	nan	0.5800	0.4537	0.0008	0.9363	nan	0.7218	0.8411	0.0992	0.5054	0.3913	nan	0.0	0.4708	0.0036	0.9403	0.8654	0.9578	0.0094	0.2155	0.2765	0.8172	0.8728	0.3442	0.6603	0.3949	nan	0.4461	0.2232	0.0008	0.7795	nan	0.3286	0.6937	0.0992	0.3885	0.3025	nan	0.0	0.3416	0.0036	0.8251	0.8025	0.8911	0.0083	0.1864	0.1852	7
0.4155	0.5094	0.3081	0.3776	0.8558	0.9018	0.9694	0.7703	0.8377	0.4270	nan	0.5865	0.4399	0.0	0.9361	nan	0.7080	0.8763	0.0578	0.5485	0.2927	nan	0.0	0.4487	0.0054	0.9042	0.9128	0.9492	0.0099	0.1807	0.3193	0.8330	0.8773	0.5168	0.7730	0.3741	nan	0.4799	0.2673	0.0	0.7888	nan	0.3382	0.6906	0.0578	0.4031	0.2381	nan	0.0	0.3486	0.0054	0.8227	0.7534	0.9091	0.0066	0.1631	0.2111	8
0.3834	0.5143	0.3111	0.3771	0.8584	0.9192	0.9577	0.7640	0.7293	0.5706	nan	0.5961	0.4335	0.0004	0.9314	nan	0.7297	0.8770	0.1184	0.6003	0.2523	nan	0.0002	0.4300	0.0086	0.9272	0.9108	0.9451	0.0191	0.1244	0.2207	0.8166	0.8868	0.6819	0.6879	0.4524	nan	0.4954	0.2162	0.0004	0.7937	nan	0.3137	0.6885	0.1172	0.3928	0.2309	nan	0.0002	0.3417	0.0086	0.8341	0.7970	0.9032	0.0129	0.1139	0.1678	9

Framework versions

Transformers 4.26.1
TensorFlow 2.11.0
Datasets 2.9.0
Tokenizers 0.13.2

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