segformer-b-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: 0.7733
• Mean Iou: 0.2394
• Mean Accuracy: 0.2885
• Overall Accuracy: 0.8145
• Accuarcy Unlabeled: nan
• Accuarcy Flat-road: 0.9002
• Accuarcy Flat-sidewalk: 0.9256
• Accuarcy Flat-crosswalk: 0.6731
• Accuarcy Flat-cyclinglane: 0.7624
• Accuarcy Flat-parkingdriveway: 0.3720
• Accuarcy Flat-railtrack: nan
• Accuarcy Flat-curb: 0.3753
• Accuarcy Human-person: 0.0482
• Accuarcy Human-rider: 0.0
• Accuarcy Vehicle-car: 0.9125
• Accuarcy Vehicle-truck: 0.0
• Accuarcy Vehicle-bus: 0.0
• Accuarcy Vehicle-tramtrain: nan
• Accuarcy Vehicle-motorcycle: 0.0
• Accuarcy Vehicle-bicycle: 0.0
• Accuarcy Vehicle-caravan: 0.0
• Accuarcy Vehicle-cartrailer: 0.0
• Accuarcy Construction-building: 0.8988
• Accuarcy Construction-door: 0.0
• Accuarcy Construction-wall: 0.3240
• Accuarcy Construction-fenceguardrail: 0.0009
• Accuarcy Construction-bridge: 0.0
• Accuarcy Construction-tunnel: nan
• Accuarcy Construction-stairs: 0.0
• Accuarcy Object-pole: 0.0228
• Accuarcy Object-trafficsign: 0.0
• Accuarcy Object-trafficlight: 0.0
• Accuarcy Nature-vegetation: 0.9283
• Accuarcy Nature-terrain: 0.8528
• Accuarcy Sky: 0.9460
• Accuarcy Void-ground: 0.0
• Accuarcy Void-dynamic: 0.0
• Accuarcy Void-static: 0.0014
• Accuarcy Void-unclear: 0.0
• Iou Unlabeled: nan
• Iou Flat-road: 0.7132
• Iou Flat-sidewalk: 0.8399
• Iou Flat-crosswalk: 0.5677
• Iou Flat-cyclinglane: 0.6711
• Iou Flat-parkingdriveway: 0.2585
• Iou Flat-railtrack: nan
• Iou Flat-curb: 0.3157
• Iou Human-person: 0.0474
• Iou Human-rider: 0.0
• Iou Vehicle-car: 0.7025
• Iou Vehicle-truck: 0.0
• Iou Vehicle-bus: 0.0
• Iou Vehicle-tramtrain: nan
• Iou Vehicle-motorcycle: 0.0
• Iou Vehicle-bicycle: 0.0
• Iou Vehicle-caravan: 0.0
• Iou Vehicle-cartrailer: 0.0
• Iou Construction-building: 0.6194
• Iou Construction-door: 0.0
• Iou Construction-wall: 0.2615
• Iou Construction-fenceguardrail: 0.0009
• Iou Construction-bridge: 0.0
• Iou Construction-tunnel: nan
• Iou Construction-stairs: 0.0
• Iou Object-pole: 0.0227
• Iou Object-trafficsign: 0.0
• Iou Object-trafficlight: 0.0
• Iou Nature-vegetation: 0.7851
• Iou Nature-terrain: 0.7352
• Iou Sky: 0.8791
• Iou Void-ground: 0.0
• Iou Void-dynamic: 0.0
• Iou Void-static: 0.0014
• 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: 0.0001
• train_batch_size: 24
• eval_batch_size: 24
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 12

Training results

Training Loss	Epoch	Step	Validation Loss	Mean Iou	Mean Accuracy	Overall Accuracy	Accuarcy Unlabeled	Accuarcy Flat-road	Accuarcy Flat-sidewalk	Accuarcy Flat-crosswalk	Accuarcy Flat-cyclinglane	Accuarcy Flat-parkingdriveway	Accuarcy Flat-railtrack	Accuarcy Flat-curb	Accuarcy Human-person	Accuarcy Human-rider	Accuarcy Vehicle-car	Accuarcy Vehicle-truck	Accuarcy Vehicle-bus	Accuarcy Vehicle-tramtrain	Accuarcy Vehicle-motorcycle	Accuarcy Vehicle-bicycle	Accuarcy Vehicle-caravan	Accuarcy Vehicle-cartrailer	Accuarcy Construction-building	Accuarcy Construction-door	Accuarcy Construction-wall	Accuarcy Construction-fenceguardrail	Accuarcy Construction-bridge	Accuarcy Construction-tunnel	Accuarcy Construction-stairs	Accuarcy Object-pole	Accuarcy Object-trafficsign	Accuarcy Object-trafficlight	Accuarcy Nature-vegetation	Accuarcy Nature-terrain	Accuarcy Sky	Accuarcy Void-ground	Accuarcy Void-dynamic	Accuarcy Void-static	Accuarcy 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
2.2728	0.59	20	2.3946	0.1035	0.1549	0.6540	nan	0.6440	0.9384	0.0	0.0006	0.0001	nan	0.0001	0.0	0.0	0.9243	0.0	0.0	nan	0.0	0.0	0.0	0.0	0.6269	0.0	0.0000	0.0002	0.0	nan	0.0	0.0	0.0	0.0	0.9320	0.0116	0.7234	0.0	0.0	0.0	0.0	nan	0.4920	0.6851	0.0	0.0006	0.0001	nan	0.0001	0.0	0.0	0.3557	0.0	0.0	nan	0.0	0.0	0.0	0.0	0.4837	0.0	0.0000	0.0002	0.0	0.0	0.0	0.0	0.0	0.0	0.5828	0.0115	0.7007	0.0	0.0	0.0	0.0
1.9006	1.18	40	1.7230	0.1153	0.1706	0.6814	nan	0.8635	0.8762	0.0	0.0003	0.0003	nan	0.0	0.0	0.0	0.8614	0.0	0.0	nan	0.0	0.0	0.0	0.0	0.8115	0.0	0.0	0.0	0.0	nan	0.0	0.0	0.0	0.0	0.9315	0.0405	0.9034	0.0	0.0	0.0	0.0	nan	0.4876	0.7405	0.0	0.0003	0.0003	nan	0.0	0.0	0.0	0.5225	0.0	0.0	nan	0.0	0.0	0.0	0.0	0.5210	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.6069	0.0399	0.7696	0.0	0.0	0.0	0.0
1.6721	1.76	60	1.4574	0.1289	0.1783	0.6968	nan	0.8799	0.8822	0.0	0.0528	0.0003	nan	0.0	0.0	0.0	0.8812	0.0	0.0	nan	0.0	0.0	0.0	0.0	0.8573	0.0	0.0000	0.0	0.0	nan	0.0	0.0	0.0	0.0	0.9298	0.1473	0.8959	0.0	0.0	0.0	0.0	nan	0.4937	0.7555	0.0	0.0519	0.0003	nan	0.0	0.0	0.0	0.5454	0.0	0.0	nan	0.0	0.0	0.0	0.0	0.5547	0.0	0.0000	0.0	0.0	nan	0.0	0.0	0.0	0.0	0.6303	0.1427	0.8205	0.0	0.0	0.0	0.0
1.4066	2.35	80	1.3422	0.1589	0.2055	0.7457	nan	0.8230	0.9475	0.0	0.3015	0.0047	nan	0.0000	0.0	0.0	0.8977	0.0	0.0	nan	0.0	0.0	0.0	0.0	0.8695	0.0	0.0000	0.0	0.0	nan	0.0	0.0	0.0	0.0	0.9091	0.6841	0.9322	0.0	0.0	0.0	0.0	nan	0.6093	0.7599	0.0	0.2787	0.0046	nan	0.0000	0.0	0.0	0.5489	0.0	0.0	nan	0.0	0.0	0.0	0.0	0.5596	0.0	0.0000	0.0	0.0	nan	0.0	0.0	0.0	0.0	0.7275	0.6092	0.8285	0.0	0.0	0.0	0.0
1.3429	2.94	100	1.1795	0.1653	0.2103	0.7562	nan	0.8569	0.9495	0.0	0.3507	0.0066	nan	0.0000	0.0	0.0	0.8981	0.0	0.0	nan	0.0	0.0	0.0	0.0	0.8869	0.0	0.0001	0.0	0.0	nan	0.0	0.0	0.0	0.0	0.9026	0.7728	0.8950	0.0	0.0	0.0	0.0	nan	0.6153	0.7730	0.0	0.3326	0.0065	nan	0.0000	0.0	0.0	0.5899	0.0	0.0	nan	0.0	0.0	0.0	0.0	0.5742	0.0	0.0001	0.0	0.0	nan	0.0	0.0	0.0	0.0	0.7403	0.6481	0.8448	0.0	0.0	0.0	0.0
1.2661	3.53	120	1.1008	0.1712	0.2174	0.7629	nan	0.8484	0.9495	0.0	0.4917	0.0181	nan	0.0001	0.0	0.0	0.8996	0.0	0.0	nan	0.0	0.0	0.0	0.0	0.9043	0.0	0.0001	0.0	0.0	nan	0.0	0.0	0.0	0.0	0.8869	0.8036	0.9371	0.0	0.0	0.0	0.0	nan	0.6100	0.7894	0.0	0.4346	0.0175	nan	0.0001	0.0	0.0	0.6153	0.0	0.0	nan	0.0	0.0	0.0	0.0	0.5608	0.0	0.0001	0.0	0.0	nan	0.0	0.0	0.0	0.0	0.7533	0.6752	0.8508	0.0	0.0	0.0	0.0
1.2166	4.12	140	1.0514	0.1771	0.2232	0.7695	nan	0.8815	0.9342	0.0	0.5539	0.0713	nan	0.0030	0.0	0.0	0.9014	0.0	0.0	nan	0.0	0.0	0.0	0.0	0.9029	0.0	0.0016	0.0	0.0	nan	0.0	0.0	0.0	0.0	0.9068	0.8398	0.9225	0.0	0.0	0.0	0.0	nan	0.6195	0.7981	0.0	0.5017	0.0642	nan	0.0030	0.0	0.0	0.6222	0.0	0.0	nan	0.0	0.0	0.0	0.0	0.5694	0.0	0.0016	0.0	0.0	nan	0.0	0.0	0.0	0.0	0.7585	0.6979	0.8546	0.0	0.0	0.0	0.0
1.0262	4.71	160	1.0025	0.1782	0.2236	0.7665	nan	0.9188	0.9111	0.0	0.5462	0.1006	nan	0.0031	0.0	0.0	0.8814	0.0	0.0	nan	0.0	0.0	0.0	0.0	0.8881	0.0	0.0027	0.0	0.0	nan	0.0	0.0	0.0	0.0	0.9260	0.8130	0.9404	0.0	0.0	0.0	0.0	nan	0.5776	0.8071	0.0	0.5005	0.0888	nan	0.0031	0.0	0.0	0.6651	0.0	0.0	nan	0.0	0.0	0.0	0.0	0.5803	0.0	0.0027	0.0	0.0	nan	0.0	0.0	0.0	0.0	0.7415	0.7028	0.8558	0.0	0.0	0.0	0.0
1.0928	5.29	180	0.9698	0.1852	0.2308	0.7778	nan	0.8513	0.9428	0.0	0.6760	0.1497	nan	0.0419	0.0	0.0	0.8856	0.0	0.0	nan	0.0	0.0	0.0	0.0	0.9132	0.0	0.0056	0.0	0.0	nan	0.0	0.0002	0.0	0.0	0.9134	0.8535	0.9219	0.0	0.0	0.0	0.0	nan	0.6410	0.8062	0.0	0.5617	0.1228	nan	0.0405	0.0	0.0	0.6597	0.0	0.0	nan	0.0	0.0	0.0	0.0	0.5705	0.0	0.0056	0.0	0.0	nan	0.0	0.0002	0.0	0.0	0.7603	0.7081	0.8642	0.0	0.0	0.0	0.0
0.8736	5.88	200	0.9250	0.1906	0.2370	0.7850	nan	0.9149	0.9249	0.0001	0.7226	0.1944	nan	0.0715	0.0027	0.0	0.8853	0.0	0.0	nan	0.0	0.0	0.0	0.0	0.8917	0.0	0.0153	0.0	0.0	nan	0.0	0.0005	0.0	0.0	0.9353	0.8470	0.9402	0.0	0.0	0.0	0.0	nan	0.6511	0.8250	0.0001	0.5978	0.1516	nan	0.0682	0.0027	0.0	0.6817	0.0	0.0	nan	0.0	0.0	0.0	0.0	0.5862	0.0	0.0152	0.0	0.0	nan	0.0	0.0005	0.0	0.0	0.7477	0.7159	0.8635	0.0	0.0	0.0	0.0
0.7832	6.47	220	0.8852	0.1961	0.2421	0.7875	nan	0.8962	0.9385	0.0642	0.6975	0.2064	nan	0.1581	0.0003	0.0	0.8995	0.0	0.0	nan	0.0	0.0	0.0	0.0	0.9011	0.0	0.0392	0.0	0.0	nan	0.0	0.0009	0.0	0.0	0.8974	0.8728	0.9342	0.0	0.0	0.0	0.0	nan	0.6576	0.8222	0.0624	0.6239	0.1577	nan	0.1421	0.0003	0.0	0.6802	0.0	0.0	nan	0.0	0.0	0.0	0.0	0.5989	0.0	0.0383	0.0	0.0	nan	0.0	0.0009	0.0	0.0	0.7547	0.6706	0.8700	0.0	0.0	0.0	0.0
0.7822	7.06	240	0.8621	0.2145	0.2598	0.7992	nan	0.8827	0.9398	0.4415	0.7426	0.2656	nan	0.2218	0.0023	0.0	0.8967	0.0	0.0	nan	0.0	0.0	0.0	0.0	0.9092	0.0	0.0558	0.0000	0.0	nan	0.0	0.0020	0.0	0.0	0.9249	0.8259	0.9429	0.0	0.0	0.0	0.0	nan	0.6911	0.8250	0.3902	0.6320	0.2017	nan	0.1950	0.0023	0.0	0.6915	0.0	0.0	nan	0.0	0.0	0.0	0.0	0.5886	0.0	0.0540	0.0000	0.0	nan	0.0	0.0020	0.0	0.0	0.7732	0.7329	0.8703	0.0	0.0	0.0	0.0
0.6742	7.65	260	0.8371	0.2193	0.2667	0.8027	nan	0.8766	0.9312	0.3983	0.7724	0.2975	nan	0.2975	0.0055	0.0	0.9111	0.0	0.0	nan	0.0	0.0	0.0	0.0	0.9086	0.0	0.1602	0.0001	0.0	nan	0.0	0.0034	0.0	0.0	0.9371	0.8321	0.9353	0.0	0.0	0.0000	0.0	nan	0.6894	0.8388	0.3591	0.6398	0.2119	nan	0.2519	0.0055	0.0	0.6754	0.0	0.0	nan	0.0	0.0	0.0	0.0	0.6033	0.0	0.1492	0.0001	0.0	nan	0.0	0.0034	0.0	0.0	0.7671	0.7293	0.8750	0.0	0.0	0.0000	0.0
0.8116	8.24	280	0.8277	0.2314	0.2819	0.8087	nan	0.8894	0.9207	0.6812	0.7773	0.3594	nan	0.3120	0.0109	0.0	0.9016	0.0	0.0	nan	0.0	0.0	0.0	0.0	0.8885	0.0	0.2424	0.0005	0.0	nan	0.0	0.0107	0.0	0.0	0.9398	0.8575	0.9461	0.0	0.0	0.0003	0.0	nan	0.7112	0.8407	0.5738	0.6399	0.2424	nan	0.2666	0.0108	0.0	0.6924	0.0	0.0	nan	0.0	0.0	0.0	0.0	0.6145	0.0	0.2148	0.0005	0.0	nan	0.0	0.0106	0.0	0.0	0.7579	0.7244	0.8738	0.0	0.0	0.0003	0.0
0.7791	8.82	300	0.8059	0.2255	0.2723	0.8077	nan	0.8684	0.9414	0.4680	0.7998	0.2901	nan	0.3174	0.0107	0.0	0.8846	0.0	0.0	nan	0.0	0.0	0.0	0.0	0.9111	0.0	0.2193	0.0000	0.0	nan	0.0	0.0099	0.0	0.0	0.9290	0.8439	0.9465	0.0	0.0	0.0000	0.0	nan	0.7039	0.8383	0.4188	0.6308	0.2131	nan	0.2698	0.0106	0.0	0.7114	0.0	0.0	nan	0.0	0.0	0.0	0.0	0.6008	0.0	0.1942	0.0000	0.0	nan	0.0	0.0099	0.0	0.0	0.7791	0.7343	0.8760	0.0	0.0	0.0000	0.0
0.7334	9.41	320	0.7962	0.2342	0.2830	0.8117	nan	0.8921	0.9332	0.6837	0.7454	0.3381	nan	0.3264	0.0298	0.0	0.9198	0.0	0.0	nan	0.0	0.0	0.0	0.0	0.9018	0.0	0.2712	0.0003	0.0	nan	0.0	0.0182	0.0	0.0	0.9194	0.8508	0.9434	0.0	0.0	0.0008	0.0	nan	0.7121	0.8388	0.5627	0.6590	0.2316	nan	0.2794	0.0296	0.0	0.6884	0.0	0.0	nan	0.0	0.0	0.0	0.0	0.6204	0.0	0.2324	0.0003	0.0	nan	0.0	0.0182	0.0	0.0	0.7820	0.7278	0.8762	0.0	0.0	0.0008	0.0
0.7645	10.0	340	0.7783	0.2342	0.2809	0.8133	nan	0.8999	0.9347	0.5997	0.7491	0.3278	nan	0.3613	0.0164	0.0	0.9043	0.0	0.0	nan	0.0	0.0	0.0	0.0	0.9156	0.0	0.2684	0.0003	0.0	nan	0.0	0.0167	0.0	0.0	0.9235	0.8454	0.9455	0.0	0.0	0.0007	0.0	nan	0.7218	0.8409	0.5162	0.6738	0.2390	nan	0.3039	0.0162	0.0	0.7015	0.0	0.0	nan	0.0	0.0	0.0	0.0	0.6019	0.0	0.2260	0.0003	0.0	nan	0.0	0.0167	0.0	0.0	0.7860	0.7381	0.8764	0.0	0.0	0.0007	0.0
0.6792	10.59	360	0.7774	0.2358	0.2841	0.8141	nan	0.8954	0.9341	0.6272	0.7826	0.3543	nan	0.3360	0.0300	0.0	0.9162	0.0	0.0	nan	0.0	0.0	0.0	0.0	0.8964	0.0	0.2909	0.0005	0.0	nan	0.0	0.0199	0.0	0.0	0.9226	0.8558	0.9443	0.0	0.0	0.0010	0.0	nan	0.7198	0.8402	0.5426	0.6699	0.2489	nan	0.2900	0.0297	0.0	0.6966	0.0	0.0	nan	0.0	0.0	0.0	0.0	0.6186	0.0	0.2450	0.0005	0.0	nan	0.0	0.0199	0.0	0.0	0.7835	0.7251	0.8784	0.0	0.0	0.0010	0.0
0.8047	11.18	380	0.7734	0.2388	0.2878	0.8147	nan	0.8924	0.9265	0.6512	0.7739	0.3846	nan	0.3762	0.0383	0.0	0.9122	0.0	0.0	nan	0.0	0.0	0.0	0.0	0.9053	0.0	0.3142	0.0005	0.0	nan	0.0	0.0216	0.0	0.0	0.9303	0.8513	0.9427	0.0	0.0	0.0014	0.0	nan	0.7171	0.8421	0.5575	0.6761	0.2609	nan	0.3165	0.0376	0.0	0.6982	0.0	0.0	nan	0.0	0.0	0.0	0.0	0.6155	0.0	0.2551	0.0005	0.0	nan	0.0	0.0215	0.0	0.0	0.7854	0.7377	0.8797	0.0	0.0	0.0014	0.0
0.7136	11.76	400	0.7733	0.2394	0.2885	0.8145	nan	0.9002	0.9256	0.6731	0.7624	0.3720	nan	0.3753	0.0482	0.0	0.9125	0.0	0.0	nan	0.0	0.0	0.0	0.0	0.8988	0.0	0.3240	0.0009	0.0	nan	0.0	0.0228	0.0	0.0	0.9283	0.8528	0.9460	0.0	0.0	0.0014	0.0	nan	0.7132	0.8399	0.5677	0.6711	0.2585	nan	0.3157	0.0474	0.0	0.7025	0.0	0.0	nan	0.0	0.0	0.0	0.0	0.6194	0.0	0.2615	0.0009	0.0	nan	0.0	0.0227	0.0	0.0	0.7851	0.7352	0.8791	0.0	0.0	0.0014	0.0

Framework versions

• Transformers 4.32.1
• Pytorch 2.0.1
• Datasets 2.12.0
• Tokenizers 0.13.2