segformer-b0-finetuned-segments-sidewalk-2

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: 0.5234
• Mean Iou: 0.3126
• Mean Accuracy: 0.3724
• Overall Accuracy: 0.8581
• Accuracy Unlabeled: nan
• Accuracy Flat-road: 0.8770
• Accuracy Flat-sidewalk: 0.9523
• Accuracy Flat-crosswalk: 0.8485
• Accuracy Flat-cyclinglane: 0.8272
• Accuracy Flat-parkingdriveway: 0.4816
• Accuracy Flat-railtrack: nan
• Accuracy Flat-curb: 0.4909
• Accuracy Human-person: 0.6546
• Accuracy Human-rider: 0.0
• Accuracy Vehicle-car: 0.9390
• Accuracy Vehicle-truck: 0.0
• Accuracy Vehicle-bus: nan
• Accuracy Vehicle-tramtrain: 0.0
• Accuracy Vehicle-motorcycle: 0.0
• Accuracy Vehicle-bicycle: 0.3174
• Accuracy Vehicle-caravan: 0.0
• Accuracy Vehicle-cartrailer: 0.0
• Accuracy Construction-building: 0.8992
• Accuracy Construction-door: 0.0
• Accuracy Construction-wall: 0.4759
• Accuracy Construction-fenceguardrail: 0.5201
• Accuracy Construction-bridge: 0.0
• Accuracy Construction-tunnel: nan
• Accuracy Construction-stairs: 0.0
• Accuracy Object-pole: 0.2217
• Accuracy Object-trafficsign: 0.0
• Accuracy Object-trafficlight: 0.0
• Accuracy Nature-vegetation: 0.9260
• Accuracy Nature-terrain: 0.8821
• Accuracy Sky: 0.9643
• Accuracy Void-ground: 0.0
• Accuracy Void-dynamic: 0.0
• Accuracy Void-static: 0.2678
• Accuracy Void-unclear: 0.0
• Iou Unlabeled: nan
• Iou Flat-road: 0.7316
• Iou Flat-sidewalk: 0.8854
• Iou Flat-crosswalk: 0.7310
• Iou Flat-cyclinglane: 0.7641
• Iou Flat-parkingdriveway: 0.3722
• Iou Flat-railtrack: nan
• Iou Flat-curb: 0.3550
• Iou Human-person: 0.4225
• Iou Human-rider: 0.0
• Iou Vehicle-car: 0.7847
• Iou Vehicle-truck: 0.0
• Iou Vehicle-bus: nan
• Iou Vehicle-tramtrain: 0.0
• Iou Vehicle-motorcycle: 0.0
• Iou Vehicle-bicycle: 0.2941
• Iou Vehicle-caravan: 0.0
• Iou Vehicle-cartrailer: 0.0
• Iou Construction-building: 0.7100
• Iou Construction-door: 0.0
• Iou Construction-wall: 0.3331
• Iou Construction-fenceguardrail: 0.3969
• Iou Construction-bridge: 0.0
• Iou Construction-tunnel: nan
• Iou Construction-stairs: 0.0
• Iou Object-pole: 0.1649
• Iou Object-trafficsign: 0.0
• Iou Object-trafficlight: 0.0
• Iou Nature-vegetation: 0.8508
• Iou Nature-terrain: 0.7558
• Iou Sky: 0.9201
• Iou Void-ground: 0.0
• Iou Void-dynamic: 0.0
• Iou Void-static: 0.2191
• 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: 2e-05
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 50

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
0.522	10.0	500	0.5791	0.2833	0.3397	0.8440	nan	0.8636	0.9512	0.8602	0.7964	0.4563	nan	0.4273	0.4433	0.0	0.9362	0.0	nan	0.0	0.0	0.0	0.0	0.0	0.8736	0.0	0.5360	0.3822	0.0	nan	0.0	0.1408	0.0	0.0	0.9296	0.8815	0.9592	0.0	0.0	0.0930	0.0	nan	0.7130	0.8766	0.7296	0.7177	0.3374	nan	0.3184	0.3476	0.0	0.7343	0.0	nan	0.0	0.0	0.0	0.0	0.0	0.6853	0.0	0.3241	0.3188	0.0	nan	0.0	0.1067	0.0	0.0	0.8373	0.7432	0.9067	0.0	0.0	0.0842	0.0
0.3419	20.0	1000	0.5479	0.2940	0.3564	0.8488	nan	0.8365	0.9463	0.8573	0.8328	0.4997	nan	0.4725	0.6224	0.0	0.9380	0.0	nan	0.0	0.0	0.0164	0.0	0.0	0.8911	0.0	0.4705	0.5028	0.0	nan	0.0	0.1982	0.0	0.0	0.9274	0.8762	0.9628	0.0	0.0	0.1976	0.0	nan	0.7062	0.8809	0.7043	0.7137	0.3615	nan	0.3403	0.4065	0.0	0.7574	0.0	nan	0.0	0.0	0.0164	0.0	0.0	0.7023	0.0	0.3209	0.3770	0.0	nan	0.0	0.1429	0.0	0.0	0.8473	0.7526	0.9139	0.0	0.0	0.1701	0.0
0.3486	30.0	1500	0.5321	0.3037	0.3650	0.8542	nan	0.8657	0.9479	0.8389	0.8365	0.4912	nan	0.4700	0.6601	0.0	0.9401	0.0	nan	0.0	0.0	0.1585	0.0	0.0	0.8840	0.0	0.4615	0.5186	0.0	nan	0.0	0.2152	0.0	0.0	0.9337	0.8777	0.9651	0.0	0.0	0.2518	0.0	nan	0.7256	0.8839	0.7103	0.7474	0.3673	nan	0.3427	0.4156	0.0	0.7694	0.0	nan	0.0	0.0	0.1545	0.0	0.0	0.7056	0.0	0.3170	0.3888	0.0	nan	0.0	0.1569	0.0	0.0	0.8487	0.7562	0.9172	0.0	0.0	0.2068	0.0
0.405	40.0	2000	0.5256	0.3101	0.3696	0.8569	nan	0.8635	0.9520	0.8452	0.8387	0.4748	nan	0.4860	0.6552	0.0	0.9395	0.0	nan	0.0	0.0	0.2844	0.0	0.0	0.9020	0.0	0.4572	0.5207	0.0	nan	0.0	0.2120	0.0	0.0	0.9275	0.8817	0.9647	0.0	0.0	0.2518	0.0	nan	0.7266	0.8842	0.7331	0.7556	0.3654	nan	0.3504	0.4206	0.0	0.7803	0.0	nan	0.0	0.0	0.2665	0.0	0.0	0.7098	0.0	0.3327	0.3923	0.0	nan	0.0	0.1603	0.0	0.0	0.8511	0.7559	0.9196	0.0	0.0	0.2095	0.0
0.3626	50.0	2500	0.5234	0.3126	0.3724	0.8581	nan	0.8770	0.9523	0.8485	0.8272	0.4816	nan	0.4909	0.6546	0.0	0.9390	0.0	nan	0.0	0.0	0.3174	0.0	0.0	0.8992	0.0	0.4759	0.5201	0.0	nan	0.0	0.2217	0.0	0.0	0.9260	0.8821	0.9643	0.0	0.0	0.2678	0.0	nan	0.7316	0.8854	0.7310	0.7641	0.3722	nan	0.3550	0.4225	0.0	0.7847	0.0	nan	0.0	0.0	0.2941	0.0	0.0	0.7100	0.0	0.3331	0.3969	0.0	nan	0.0	0.1649	0.0	0.0	0.8508	0.7558	0.9201	0.0	0.0	0.2191	0.0

Framework versions

• Transformers 4.53.0
• Pytorch 2.7.1+cu126
• Datasets 3.6.0
• Tokenizers 0.21.2