mask2former-swin-base-apple-dms-run2

AllanK24/mask2former-swin-base-apple-dms-run2

mask2former-swin-base-apple-dms-run2 is a image segmentation model from AllanK24. Use it for the image segmentation 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.

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

Downloads · 30 days

4% of all-time downloads

All-time downloads

Public

Parameters

107M

432 MB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors432 MB · 100%

Parameter types

How the weights are stored.

F32107M · 100%

Base models

facebook/mask2former-swin-base-ade-semantic

Model card

From the Hugging Face model README

mask2former-swin-base-apple-dms-run2

This model is a fine-tuned version of facebook/mask2former-swin-base-ade-semantic on the AllanK24/apple-dms-materials dataset. It achieves the following results on the evaluation set:

Mean Iou: 0.2000
Mean Accuracy: 0.2253
Overall Accuracy: 0.5354
Iou Animal Skin: 0.0885
Accuracy Animal Skin: 0.1232
Iou Bone Teeth Horn: 0.1004
Accuracy Bone Teeth Horn: 0.1064
Iou Brickwork: 0.1755
Accuracy Brickwork: 0.1795
Iou Cardboard: 0.1072
Accuracy Cardboard: 0.1144
Iou Carpet Rug: 0.1953
Accuracy Carpet Rug: 0.2001
Iou Ceiling Tile: 0.1732
Accuracy Ceiling Tile: 0.1743
Iou Ceramic: 0.2784
Accuracy Ceramic: 0.3092
Iou Chalkboard Blackboard: 0.1048
Accuracy Chalkboard Blackboard: 0.1050
Iou Clutter: 0.0
Accuracy Clutter: 0.0
Iou Concrete: 0.0381
Accuracy Concrete: 0.0412
Iou Cork Corkboard: 0.0
Accuracy Cork Corkboard: 0.0
Iou Engineered Stone: 0.0
Accuracy Engineered Stone: 0.0
Iou Fabric Cloth: 0.6299
Accuracy Fabric Cloth: 0.6986
Iou Fiberglass Wool: 0.0
Accuracy Fiberglass Wool: 0.0
Iou Fire: 0.0
Accuracy Fire: 0.0
Iou Foliage: 0.6785
Accuracy Foliage: 0.7633
Iou Food: 0.5707
Accuracy Food: 0.7716
Iou Fur: 0.5094
Accuracy Fur: 0.5670
Iou Gemstone Quartz: 0.0
Accuracy Gemstone Quartz: 0.0
Iou Glass: 0.3757
Accuracy Glass: 0.4174
Iou Hair: 0.6654
Accuracy Hair: 0.7275
Iou Ice: 0.0
Accuracy Ice: 0.0
Iou Leather: 0.0890
Accuracy Leather: 0.0931
Iou Liquid Non-water: 0.0158
Accuracy Liquid Non-water: 0.0176
Iou Metal: 0.1629
Accuracy Metal: 0.1895
Iou Mirror: 0.1728
Accuracy Mirror: 0.1887
Iou Paint Plaster Enamel: 0.5946
Accuracy Paint Plaster Enamel: 0.6543
Iou Paper: 0.3728
Accuracy Paper: 0.4310
Iou Pearl: 0.0
Accuracy Pearl: 0.0
Iou Photograph Painting: 0.0685
Accuracy Photograph Painting: 0.0715
Iou Plastic Clear: 0.0419
Accuracy Plastic Clear: 0.0446
Iou Plastic Non-clear: 0.1156
Accuracy Plastic Non-clear: 0.1280
Iou Rubber Latex: 0.0609
Accuracy Rubber Latex: 0.0633
Iou Sand: 0.0117
Accuracy Sand: 0.0117
Iou Skin Lips: 0.6568
Accuracy Skin Lips: 0.7325
Iou Sky: 0.8409
Accuracy Sky: 0.8789
Iou Snow: 0.0674
Accuracy Snow: 0.0827
Iou Soap: 0.0
Accuracy Soap: 0.0
Iou Soil Mud: 0.1942
Accuracy Soil Mud: 0.2627
Iou Sponge: 0.0
Accuracy Sponge: 0.0
Iou Stone Natural: 0.2693
Accuracy Stone Natural: 0.3687
Iou Stone Polished: 0.0420
Accuracy Stone Polished: 0.0427
Iou Styrofoam: 0.0
Accuracy Styrofoam: 0.0
Iou Tile: 0.2992
Accuracy Tile: 0.3196
Iou Wallpaper: 0.0845
Accuracy Wallpaper: 0.0859
Iou Water: 0.5056
Accuracy Water: 0.6269
Iou Wax: 0.0000
Accuracy Wax: 0.0000
Iou Whiteboard: 0.2573
Accuracy Whiteboard: 0.2673
Iou Wicker: 0.0913
Accuracy Wicker: 0.0961
Iou Wood: 0.5410
Accuracy Wood: 0.5841
Iou Wood Tree: 0.0976
Accuracy Wood Tree: 0.1159
Iou Asphalt: 0.0578
Accuracy Asphalt: 0.0606
Loss: 296.6433
Eval Runtime: 36.7542
Eval Samples Per Second: 32.214
Eval Steps Per Second: 16.107

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: 0.001
train_batch_size: 32
eval_batch_size: 16
seed: 42
distributed_type: multi-GPU
num_devices: 8
total_train_batch_size: 256
total_eval_batch_size: 128
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 20

Training results

Training Loss	Epoch	Step	Mean Iou	Mean Accuracy	Overall Accuracy	Iou Animal Skin	Accuracy Animal Skin	Iou Bone Teeth Horn	Accuracy Bone Teeth Horn	Iou Brickwork	Accuracy Brickwork	Iou Cardboard	Accuracy Cardboard	Iou Carpet Rug	Accuracy Carpet Rug	Iou Ceiling Tile	Accuracy Ceiling Tile	Iou Ceramic	Accuracy Ceramic	Iou Chalkboard Blackboard	Accuracy Chalkboard Blackboard	Iou Concrete	Accuracy Concrete	Iou Fabric Cloth	Accuracy Fabric Cloth	Iou Foliage	Accuracy Foliage	Iou Food	Accuracy Food	Iou Fur	Accuracy Fur	Iou Glass	Accuracy Glass	Iou Hair	Accuracy Hair	Iou Leather	Accuracy Leather	Iou Liquid Non-water	Accuracy Liquid Non-water	Iou Metal	Accuracy Metal	Iou Mirror	Accuracy Mirror	Iou Paint Plaster Enamel	Accuracy Paint Plaster Enamel	Iou Paper	Accuracy Paper	Iou Photograph Painting	Accuracy Photograph Painting	Iou Plastic Clear	Accuracy Plastic Clear	Iou Plastic Non-clear	Accuracy Plastic Non-clear	Iou Rubber Latex	Accuracy Rubber Latex	Iou Sand	Accuracy Sand	Iou Skin Lips	Accuracy Skin Lips	Iou Sky	Accuracy Sky	Iou Snow	Accuracy Snow	Iou Soil Mud	Accuracy Soil Mud	Iou Stone Natural	Accuracy Stone Natural	Iou Stone Polished	Accuracy Stone Polished	Iou Tile	Accuracy Tile	Iou Wallpaper	Accuracy Wallpaper	Iou Water	Accuracy Water	Iou Wax	Accuracy Wax	Iou Whiteboard	Accuracy Whiteboard	Iou Wicker	Accuracy Wicker	Iou Wood	Accuracy Wood	Iou Wood Tree	Accuracy Wood Tree	Iou Asphalt	Accuracy Asphalt	Validation Loss	Eval Runtime	Eval Samples Per Second	Eval Steps Per Second
436.5989	1.7045	150	0.0413	0.0587	0.2913	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.1650	0.2410	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.2837	0.3964	0.0024	0.0024	0.0	0.0	0.0	0.0	0.1503	0.1893	0.3278	0.6406	0.0003	0.0003	0.0	0.0	0.0019	0.0019	0.0	0.0	0.4485	0.6146	0.0482	0.0575	0.0	0.0	0.0	0.0	0.0000	0.0000	0.0	0.0	0.0	0.0	0.4310	0.5656	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.1261	0.1605	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.1631	0.1813	0.0	0.0	0.0	0.0	378.3662	42.381	27.937	13.969
436.5989	1.7045	150	0.0413	0.0587	0.2913	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.1650	0.2410	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.2837	0.3964	0.0024	0.0024	0.0	0.0	0.0	0.0	0.1503	0.1893	0.3278	0.6406	0.0003	0.0003	0.0	0.0	0.0019	0.0019	0.0	0.0	0.4485	0.6146	0.0482	0.0575	0.0	0.0	0.0	0.0	0.0000	0.0000	0.0	0.0	0.0	0.0	0.4310	0.5656	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.1261	0.1605	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.1631	0.1813	0.0	0.0	0.0	0.0	378.3662	42.381	27.937	13.969
357.5705	3.4091	300	0.0767	0.0884	0.4027	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.1937	0.2257	0.0974	0.0982	0.0000	0.0000	0.0	0.0	0.0	0.0	0.5193	0.6731	0.5283	0.5748	0.0001	0.0001	0.1533	0.1644	0.1617	0.1746	0.5221	0.5589	0.0093	0.0094	0.0	0.0	0.0000	0.0000	0.0	0.0	0.5304	0.6803	0.0672	0.0707	0.0035	0.0035	0.0012	0.0012	0.0050	0.0050	0.0000	0.0000	0.0	0.0	0.5700	0.6801	0.2159	0.2269	0.0	0.0	0.0000	0.0000	0.0	0.0	0.0	0.0	0.0051	0.0051	0.0	0.0	0.0245	0.0252	0.0	0.0	0.0	0.0	0.0	0.0	0.3819	0.4185	0.0	0.0	0.0	0.0	338.1806	37.0424	31.963	15.982
357.5705	3.4091	300	0.0767	0.0884	0.4027	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.1937	0.2257	0.0974	0.0982	0.0000	0.0000	0.0	0.0	0.0	0.0	0.5193	0.6731	0.5283	0.5748	0.0001	0.0001	0.1533	0.1644	0.1617	0.1746	0.5221	0.5589	0.0093	0.0094	0.0	0.0	0.0000	0.0000	0.0	0.0	0.5304	0.6803	0.0672	0.0707	0.0035	0.0035	0.0012	0.0012	0.0050	0.0050	0.0000	0.0000	0.0	0.0	0.5700	0.6801	0.2159	0.2269	0.0	0.0	0.0000	0.0000	0.0	0.0	0.0	0.0	0.0051	0.0051	0.0	0.0	0.0245	0.0252	0.0	0.0	0.0	0.0	0.0	0.0	0.3819	0.4185	0.0	0.0	0.0	0.0	338.1806	37.0424	31.963	15.982
324.7154	5.1136	450	0.1110	0.1272	0.4335	0.0	0.0	0.0036	0.0036	0.0147	0.0147	0.0002	0.0002	0.1016	0.1051	0.4359	0.4456	0.1050	0.1213	0.0	0.0	0.0000	0.0000	0.5482	0.6440	0.5755	0.6296	0.0720	0.0741	0.3315	0.4794	0.2787	0.3275	0.6244	0.7262	0.0052	0.0054	0.0	0.0	0.0181	0.0185	0.0015	0.0015	0.5172	0.5955	0.1734	0.1890	0.0931	0.1100	0.0183	0.0198	0.0617	0.0689	0.0013	0.0013	0.0	0.0	0.5892	0.6542	0.4409	0.4506	0.0	0.0	0.0030	0.0030	0.0818	0.0856	0.0	0.0	0.0232	0.0233	0.0	0.0	0.0714	0.0725	0.0	0.0	0.0597	0.0638	0.0047	0.0048	0.5171	0.6730	0.0011	0.0011	0.0	0.0	317.4770	36.9948	32.004	16.002
324.7154	5.1136	450	0.1110	0.1272	0.4335	0.0	0.0	0.0036	0.0036	0.0147	0.0147	0.0002	0.0002	0.1016	0.1051	0.4359	0.4456	0.1050	0.1213	0.0	0.0	0.0000	0.0000	0.5482	0.6440	0.5755	0.6296	0.0720	0.0741	0.3315	0.4794	0.2787	0.3275	0.6244	0.7262	0.0052	0.0054	0.0	0.0	0.0181	0.0185	0.0015	0.0015	0.5172	0.5955	0.1734	0.1890	0.0931	0.1100	0.0183	0.0198	0.0617	0.0689	0.0013	0.0013	0.0	0.0	0.5892	0.6542	0.4409	0.4506	0.0	0.0	0.0030	0.0030	0.0818	0.0856	0.0	0.0	0.0232	0.0233	0.0	0.0	0.0714	0.0725	0.0	0.0	0.0597	0.0638	0.0047	0.0048	0.5171	0.6730	0.0011	0.0011	0.0	0.0	317.4770	36.9948	32.004	16.002
305.1586	6.8182	600	0.1626	0.1969	0.5317	0.0011	0.0011	0.0327	0.0344	0.2029	0.2534	0.0232	0.0238	0.1403	0.1493	0.5299	0.5522	0.1128	0.1341	0.0644	0.0647	0.0094	0.0096	0.5822	0.7204	0.6084	0.6767	0.4158	0.5529	0.4668	0.6248	0.3408	0.4283	0.6448	0.7313	0.0445	0.0465	0.0	0.0	0.0597	0.0636	0.0103	0.0104	0.5773	0.6511	0.2505	0.2915	0.0441	0.0448	0.0571	0.0722	0.0917	0.1074	0.0125	0.0134	0.0	0.0	0.6193	0.7040	0.7493	0.8245	0.0	0.0	0.0614	0.0665	0.1837	0.2427	0.0	0.0	0.3494	0.5571	0.1267	0.1488	0.3576	0.6513	0.0	0.0	0.0859	0.0877	0.0306	0.0316	0.5417	0.6414	0.0247	0.0255	0.0	0.0	310.3910	35.8142	33.06	16.53
305.1586	6.8182	600	0.1626	0.1969	0.5317	0.0011	0.0011	0.0327	0.0344	0.2029	0.2534	0.0232	0.0238	0.1403	0.1493	0.5299	0.5522	0.1128	0.1341	0.0644	0.0647	0.0094	0.0096	0.5822	0.7204	0.6084	0.6767	0.4158	0.5529	0.4668	0.6248	0.3408	0.4283	0.6448	0.7313	0.0445	0.0465	0.0	0.0	0.0597	0.0636	0.0103	0.0104	0.5773	0.6511	0.2505	0.2915	0.0441	0.0448	0.0571	0.0722	0.0917	0.1074	0.0125	0.0134	0.0	0.0	0.6193	0.7040	0.7493	0.8245	0.0	0.0	0.0614	0.0665	0.1837	0.2427	0.0	0.0	0.3494	0.5571	0.1267	0.1488	0.3576	0.6513	0.0	0.0	0.0859	0.0877	0.0306	0.0316	0.5417	0.6414	0.0247	0.0255	0.0	0.0	310.3910	35.8142	33.06	16.53
290.6089	8.5227	750	0.1373	0.1599	0.4727	0.1286	0.2632	0.0734	0.0783	0.0329	0.0330	0.0017	0.0017	0.0445	0.0448	0.0241	0.0242	0.0398	0.0403	0.0	0.0	0.0028	0.0029	0.5641	0.6047	0.6451	0.7296	0.5049	0.7142	0.3563	0.3945	0.1903	0.1983	0.6365	0.7055	0.0090	0.0091	0.0	0.0	0.0419	0.0430	0.0226	0.0227	0.5938	0.7114	0.2996	0.3542	0.0480	0.0494	0.0391	0.0439	0.0294	0.0299	0.0098	0.0100	0.0	0.0	0.6114	0.6709	0.7832	0.8262	0.0	0.0	0.0740	0.0816	0.1900	0.2285	0.0	0.0	0.1741	0.1809	0.0305	0.0308	0.4245	0.6513	0.0	0.0	0.0854	0.0863	0.0142	0.0142	0.3829	0.4005	0.0325	0.0337	0.0	0.0	302.5561	34.6878	34.133	17.067
290.6089	8.5227	750	0.1373	0.1599	0.4727	0.1286	0.2632	0.0734	0.0783	0.0329	0.0330	0.0017	0.0017	0.0445	0.0448	0.0241	0.0242	0.0398	0.0403	0.0	0.0	0.0028	0.0029	0.5641	0.6047	0.6451	0.7296	0.5049	0.7142	0.3563	0.3945	0.1903	0.1983	0.6365	0.7055	0.0090	0.0091	0.0	0.0	0.0419	0.0430	0.0226	0.0227	0.5938	0.7114	0.2996	0.3542	0.0480	0.0494	0.0391	0.0439	0.0294	0.0299	0.0098	0.0100	0.0	0.0	0.6114	0.6709	0.7832	0.8262	0.0	0.0	0.0740	0.0816	0.1900	0.2285	0.0	0.0	0.1741	0.1809	0.0305	0.0308	0.4245	0.6513	0.0	0.0	0.0854	0.0863	0.0142	0.0142	0.3829	0.4005	0.0325	0.0337	0.0	0.0	302.5561	34.6878	34.133	17.067
277.6828	10.2273	900	0.1494	0.1735	0.4566	0.0578	0.1232	0.0806	0.0877	0.0575	0.0576	0.0438	0.0439	0.0516	0.0518	0.0274	0.0274	0.1697	0.1889	0.0047	0.0047	0.0009	0.0009	0.5572	0.5953	0.6476	0.7080	0.5055	0.7479	0.4794	0.6994	0.3037	0.3318	0.6564	0.7356	0.0563	0.0584	0.0	0.0	0.0860	0.0918	0.0449	0.0453	0.5709	0.6535	0.2810	0.3157	0.0106	0.0107	0.0233	0.0241	0.0561	0.0583	0.0202	0.0203	0.0	0.0	0.6440	0.7306	0.7224	0.7563	0.0	0.0	0.0888	0.1006	0.2708	0.4092	0.0020	0.0020	0.1237	0.1283	0.0634	0.0657	0.3795	0.4514	0.0	0.0	0.2774	0.2779	0.0410	0.0415	0.3282	0.3408	0.0351	0.0361	0.0004	0.0004	299.9430	35.8068	33.066	16.533
277.6828	10.2273	900	0.1494	0.1735	0.4566	0.0578	0.1232	0.0806	0.0877	0.0575	0.0576	0.0438	0.0439	0.0516	0.0518	0.0274	0.0274	0.1697	0.1889	0.0047	0.0047	0.0009	0.0009	0.5572	0.5953	0.6476	0.7080	0.5055	0.7479	0.4794	0.6994	0.3037	0.3318	0.6564	0.7356	0.0563	0.0584	0.0	0.0	0.0860	0.0918	0.0449	0.0453	0.5709	0.6535	0.2810	0.3157	0.0106	0.0107	0.0233	0.0241	0.0561	0.0583	0.0202	0.0203	0.0	0.0	0.6440	0.7306	0.7224	0.7563	0.0	0.0	0.0888	0.1006	0.2708	0.4092	0.0020	0.0020	0.1237	0.1283	0.0634	0.0657	0.3795	0.4514	0.0	0.0	0.2774	0.2779	0.0410	0.0415	0.3282	0.3408	0.0351	0.0361	0.0004	0.0004	299.9430	35.8068	33.066	16.533
266.7051	11.9318	1050	0.1865	0.2135	0.5225	0.0153	0.0156	0.0581	0.0595	0.1121	0.1136	0.1273	0.1346	0.1525	0.1552	0.3963	0.4022	0.1759	0.1876	0.0107	0.0107	0.0070	0.0072	0.6247	0.7172	0.6958	0.7974	0.5624	0.7606	0.4432	0.5194	0.3495	0.3932	0.6653	0.7621	0.0656	0.0680	0.0	0.0	0.0815	0.0863	0.1556	0.1791	0.5771	0.6259	0.3813	0.5135	0.0758	0.0789	0.0778	0.0913	0.1512	0.1853	0.0459	0.0483	0.0	0.0	0.6408	0.7086	0.7962	0.8473	0.0	0.0	0.1354	0.1695	0.2451	0.3122	0.0111	0.0112	0.2409	0.2631	0.0450	0.0450	0.4594	0.6229	0.0	0.0	0.3447	0.3565	0.1113	0.1206	0.5245	0.5682	0.1082	0.1380	0.0274	0.0276	295.9863	36.4316	32.499	16.25
266.7051	11.9318	1050	0.1865	0.2135	0.5225	0.0153	0.0156	0.0581	0.0595	0.1121	0.1136	0.1273	0.1346	0.1525	0.1552	0.3963	0.4022	0.1759	0.1876	0.0107	0.0107	0.0070	0.0072	0.6247	0.7172	0.6958	0.7974	0.5624	0.7606	0.4432	0.5194	0.3495	0.3932	0.6653	0.7621	0.0656	0.0680	0.0	0.0	0.0815	0.0863	0.1556	0.1791	0.5771	0.6259	0.3813	0.5135	0.0758	0.0789	0.0778	0.0913	0.1512	0.1853	0.0459	0.0483	0.0	0.0	0.6408	0.7086	0.7962	0.8473	0.0	0.0	0.1354	0.1695	0.2451	0.3122	0.0111	0.0112	0.2409	0.2631	0.0450	0.0450	0.4594	0.6229	0.0	0.0	0.3447	0.3565	0.1113	0.1206	0.5245	0.5682	0.1082	0.1380	0.0274	0.0276	295.9863	36.4316	32.499	16.25
255.6580	13.6364	1200	0.1621	0.1793	0.4761	0.0729	0.1311	0.0776	0.0829	0.1597	0.1642	0.0839	0.0872	0.0892	0.0903	0.0880	0.0884	0.1324	0.1391	0.0104	0.0105	0.0109	0.0112	0.6001	0.6482	0.6537	0.7095	0.5225	0.5866	0.3030	0.3160	0.3434	0.3835	0.6527	0.7178	0.0227	0.0234	0.0	0.0	0.1015	0.1099	0.1331	0.1449	0.5686	0.6184	0.3072	0.3385	0.0401	0.0410	0.0365	0.0388	0.0805	0.0851	0.0493	0.0509	0.0	0.0	0.6507	0.7229	0.7641	0.7907	0.0098	0.0098	0.1444	0.1915	0.2889	0.4195	0.0113	0.0113	0.2078	0.2184	0.0464	0.0466	0.4177	0.4964	0.0	0.0	0.0613	0.0614	0.1168	0.1247	0.4572	0.4813	0.0915	0.1122	0.0208	0.0212	294.2896	37.3176	31.728	15.864
255.6580	13.6364	1200	0.1621	0.1793	0.4761	0.0729	0.1311	0.0776	0.0829	0.1597	0.1642	0.0839	0.0872	0.0892	0.0903	0.0880	0.0884	0.1324	0.1391	0.0104	0.0105	0.0109	0.0112	0.6001	0.6482	0.6537	0.7095	0.5225	0.5866	0.3030	0.3160	0.3434	0.3835	0.6527	0.7178	0.0227	0.0234	0.0	0.0	0.1015	0.1099	0.1331	0.1449	0.5686	0.6184	0.3072	0.3385	0.0401	0.0410	0.0365	0.0388	0.0805	0.0851	0.0493	0.0509	0.0	0.0	0.6507	0.7229	0.7641	0.7907	0.0098	0.0098	0.1444	0.1915	0.2889	0.4195	0.0113	0.0113	0.2078	0.2184	0.0464	0.0466	0.4177	0.4964	0.0	0.0	0.0613	0.0614	0.1168	0.1247	0.4572	0.4813	0.0915	0.1122	0.0208	0.0212	294.2896	37.3176	31.728	15.864
246.0549	15.3409	1350	0.1838	0.2078	0.4954	0.0748	0.0921	0.0757	0.0794	0.2244	0.2388	0.0911	0.0945	0.0961	0.0973	0.0638	0.0641	0.2109	0.2241	0.0384	0.0384	0.0078	0.0080	0.6243	0.6897	0.6937	0.7733	0.5871	0.7564	0.5160	0.5952	0.3619	0.4070	0.6744	0.7556	0.0541	0.0560	0.0001	0.0001	0.1471	0.1702	0.1546	0.1701	0.5485	0.5893	0.3566	0.4183	0.0857	0.0884	0.0541	0.0596	0.1142	0.1265	0.0665	0.0712	0.0	0.0	0.6602	0.7438	0.8042	0.8464	0.0000	0.0000	0.2199	0.2953	0.2837	0.3763	0.0181	0.0182	0.2143	0.2219	0.0407	0.0408	0.4547	0.5987	0.0	0.0	0.2609	0.2706	0.0813	0.0855	0.4744	0.5023	0.1048	0.1183	0.0210	0.0214	294.5585	37.7824	31.337	15.669
246.0549	15.3409	1350	0.1838	0.2078	0.4954	0.0748	0.0921	0.0757	0.0794	0.2244	0.2388	0.0911	0.0945	0.0961	0.0973	0.0638	0.0641	0.2109	0.2241	0.0384	0.0384	0.0078	0.0080	0.6243	0.6897	0.6937	0.7733	0.5871	0.7564	0.5160	0.5952	0.3619	0.4070	0.6744	0.7556	0.0541	0.0560	0.0001	0.0001	0.1471	0.1702	0.1546	0.1701	0.5485	0.5893	0.3566	0.4183	0.0857	0.0884	0.0541	0.0596	0.1142	0.1265	0.0665	0.0712	0.0	0.0	0.6602	0.7438	0.8042	0.8464	0.0000	0.0000	0.2199	0.2953	0.2837	0.3763	0.0181	0.0182	0.2143	0.2219	0.0407	0.0408	0.4547	0.5987	0.0	0.0	0.2609	0.2706	0.0813	0.0855	0.4744	0.5023	0.1048	0.1183	0.0210	0.0214	294.5585	37.7824	31.337	15.669
237.3320	17.0455	1500	0.1863	0.2098	0.5203	0.0791	0.1055	0.1021	0.1119	0.1458	0.1496	0.0639	0.0656	0.1552	0.1584	0.2510	0.2533	0.1509	0.1584	0.0349	0.0354	0.0045	0.0045	0.6445	0.7443	0.6807	0.7919	0.5572	0.6963	0.5336	0.6336	0.3564	0.3939	0.6821	0.7661	0.0796	0.0842	0.0048	0.0053	0.1104	0.1206	0.1443	0.1538	0.5848	0.6378	0.3686	0.4235	0.1156	0.1241	0.0452	0.0476	0.0997	0.1074	0.0586	0.0605	0.0212	0.0212	0.6668	0.7529	0.8359	0.8916	0.0241	0.0296	0.1679	0.2102	0.2433	0.2988	0.0124	0.0125	0.2257	0.2364	0.1064	0.1093	0.4636	0.5860	0.0	0.0	0.1663	0.1669	0.0903	0.0943	0.4966	0.5266	0.1075	0.1349	0.0066	0.0067	296.4626	34.8379	33.986	16.993
237.3320	17.0455	1500	0.1863	0.2098	0.5203	0.0791	0.1055	0.1021	0.1119	0.1458	0.1496	0.0639	0.0656	0.1552	0.1584	0.2510	0.2533	0.1509	0.1584	0.0349	0.0354	0.0045	0.0045	0.6445	0.7443	0.6807	0.7919	0.5572	0.6963	0.5336	0.6336	0.3564	0.3939	0.6821	0.7661	0.0796	0.0842	0.0048	0.0053	0.1104	0.1206	0.1443	0.1538	0.5848	0.6378	0.3686	0.4235	0.1156	0.1241	0.0452	0.0476	0.0997	0.1074	0.0586	0.0605	0.0212	0.0212	0.6668	0.7529	0.8359	0.8916	0.0241	0.0296	0.1679	0.2102	0.2433	0.2988	0.0124	0.0125	0.2257	0.2364	0.1064	0.1093	0.4636	0.5860	0.0	0.0	0.1663	0.1669	0.0903	0.0943	0.4966	0.5266	0.1075	0.1349	0.0066	0.0067	296.4626	34.8379	33.986	16.993
228.5443	18.75	1650	0.2000	0.2253	0.5354	0.0885	0.1232	0.1004	0.1064	0.1755	0.1795	0.1072	0.1144	0.1953	0.2001	0.1732	0.1743	0.2784	0.3092	0.1048	0.1050	0.0381	0.0412	0.6299	0.6986	0.6785	0.7633	0.5707	0.7716	0.5094	0.5670	0.3757	0.4174	0.6654	0.7275	0.0890	0.0931	0.0158	0.0176	0.1629	0.1895	0.1728	0.1887	0.5946	0.6543	0.3728	0.4310	0.0685	0.0715	0.0419	0.0446	0.1156	0.1280	0.0609	0.0633	0.0117	0.0117	0.6568	0.7325	0.8409	0.8789	0.0674	0.0827	0.1942	0.2627	0.2693	0.3687	0.0420	0.0427	0.2992	0.3196	0.0845	0.0859	0.5056	0.6269	0.0000	0.0000	0.2573	0.2673	0.0913	0.0961	0.5410	0.5841	0.0976	0.1159	0.0578	0.0606	296.6433	36.7542	32.214	16.107
228.5443	18.75	1650	0.2000	0.2253	0.5354	0.0885	0.1232	0.1004	0.1064	0.1755	0.1795	0.1072	0.1144	0.1953	0.2001	0.1732	0.1743	0.2784	0.3092	0.1048	0.1050	0.0381	0.0412	0.6299	0.6986	0.6785	0.7633	0.5707	0.7716	0.5094	0.5670	0.3757	0.4174	0.6654	0.7275	0.0890	0.0931	0.0158	0.0176	0.1629	0.1895	0.1728	0.1887	0.5946	0.6543	0.3728	0.4310	0.0685	0.0715	0.0419	0.0446	0.1156	0.1280	0.0609	0.0633	0.0117	0.0117	0.6568	0.7325	0.8409	0.8789	0.0674	0.0827	0.1942	0.2627	0.2693	0.3687	0.0420	0.0427	0.2992	0.3196	0.0845	0.0859	0.5056	0.6269	0.0000	0.0000	0.2573	0.2673	0.0913	0.0961	0.5410	0.5841	0.0976	0.1159	0.0578	0.0606	296.6433	36.7542	32.214	16.107

Framework versions

Transformers 5.0.0
Pytorch 2.9.1+cu128
Datasets 4.5.0
Tokenizers 0.22.2

Task: Image Segmentation
Library: transformers
Type: mask2former
License: other
Created: Feb 8, 2026
Updated: Feb 8, 2026