segformer-b0-scene-parse-150-MASKED

This model is a fine-tuned version of nvidia/mit-b0 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 4.1526
• Mean Iou: 0.0217
• Mean Accuracy: 0.0580
• Overall Accuracy: 0.2746
• Per Category Iou: [0.2638779780993535, 0.24032657224553952, 0.28498201974847515, 0.1075812162299665, 0.14745268628426467, 0.048342869965219346, 0.0, 0.007290688724806103, 0.04780558672261605, 0.06559620777139805, 0.0, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, nan, 0.0, nan, 0.0, nan, nan, nan, nan, 0.0, nan, 0.0, 0.0, nan, 0.0, 0.0, 0.0, nan, nan, nan, 0.0, nan, 0.0, nan, 0.0, 0.0, 0.0, nan, 0.0, nan, 0.0, 0.0, nan, nan, nan, nan, 0.0, 0.0, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan]
• Per Category Accuracy: [0.5551073389128427, 0.47540841261768607, 0.4280130098767642, 0.6449145007547091, 0.4263212952616438, 0.051559171951657295, 0.0, 0.008099600657740192, 0.06573971674217831, 0.0695452132365953, 0.0, 0.0, 0.0, nan, 0.0, 0.0, nan, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, 0.0, nan, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, 0.0, 0.0, nan, 0.0, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, 0.0, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan]

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: 6e-05
• train_batch_size: 2
• eval_batch_size: 2
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Mean Iou	Mean Accuracy	Overall Accuracy	Per Category Iou	Per Category Accuracy
4.7792	1.0	20	4.7294	0.0082	0.0454	0.1893	[0.2263585397369742, 0.13770136142176356, 0.08295638586455376, 0.08510788870213735, 0.12573291455024074, 0.02435003944847278, 0.0, 0.004065480375718896, 0.0017733053903393038, 0.09547671544063606, 0.0, 0.0, 0.00046794942973620344, 0.0, 0.0, 0.0, 0.0, 0.0003653809493550232, 0.0, 0.0, nan, 0.0, 0.0, 0.008303859757035214, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, 0.0, 0.0, nan, 0.0, 0.0, nan, 0.0, nan, 0.0, nan, 0.0, nan, nan, nan, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, nan, 0.0, 0.0, 0.0, nan, nan, 0.0, nan, 0.0, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, nan, nan, 0.0, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, 0.0]	[0.4716825785763388, 0.2136232639104242, 0.09227762360874885, 0.6465273039306908, 0.5643826822947624, 0.024817518248175182, 0.0, 0.0042377260981912145, 0.0018640077057543434, 0.10115023889577066, 0.0, 0.0, 0.0004903142166191589, nan, 0.0, 0.0, nan, 0.001218026796589525, 0.0, 0.0, nan, nan, 0.0, 0.010582425335110135, 0.0, nan, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, 0.0, 0.0, nan, 0.0, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, 0.0, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan]
4.6816	2.0	40	4.3777	0.0172	0.0508	0.2436	[0.2348784161662965, 0.1780159659740713, 0.1725553209314372, 0.11519214696920146, 0.1519642591474354, 0.05501165920088421, 0.008008356545961003, 0.003268125562869637, 0.06320147075839194, 0.033278833708018256, 0.0, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, 0.0, 0.0, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, 0.0, 0.0, nan, 0.0, 0.0, nan, 0.0, 0.0, 0.0, nan, nan, nan, 0.0, nan, 0.0, nan, 0.0, 0.0, 0.0, nan, 0.0, nan, 0.0, 0.0, nan, nan, nan, 0.0, 0.0, 0.0, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan]	[0.49203944919252063, 0.5863196761642498, 0.24353236057649272, 0.45883216508487895, 0.4128408739687597, 0.05860476247457221, 0.010855884203901826, 0.0033074935400516795, 0.08768863044486462, 0.03457795080516723, 0.0, 0.0, 0.0, nan, 0.0, 0.0, nan, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, 0.0, nan, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, 0.0, 0.0, nan, 0.0, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, 0.0, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan]
4.3571	3.0	60	4.2442	0.0166	0.0524	0.2571	[0.25585106151712383, 0.22004710007836228, 0.22139639459642338, 0.10209920082512318, 0.1575995748489595, 0.017118189937481394, 0.0, 0.007236489870641267, 0.03938333712881877, 0.008957958671236131, 0.0, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, nan, 0.0, 0.0, 0.0, nan, nan, nan, nan, 0.0, nan, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, nan, 0.0, nan, 0.0, 0.0, 0.0, nan, 0.0, nan, 0.0, 0.0, nan, nan, nan, 0.0, 0.0, 0.0, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan]	[0.5795454321624768, 0.44004779802440347, 0.3099841852415481, 0.6467961044600211, 0.40188060198283443, 0.017613976307287303, 0.0, 0.00787408973455485, 0.05089900467339731, 0.009343479030260131, 0.0, 0.0, 0.0, nan, 0.0, 0.0, nan, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, 0.0, nan, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, 0.0, 0.0, nan, 0.0, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, 0.0, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan]
3.9658	4.0	80	4.1981	0.0207	0.0555	0.2731	[0.26863872743436906, 0.26573623577278954, 0.2321627542307547, 0.10446031518997217, 0.16009038296656186, 0.046391399460182774, 0.0, 0.004261499526016889, 0.04043589899112432, 0.01742889012827663, 0.0, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, nan, 0.0, nan, 0.0, nan, nan, nan, nan, 0.0, nan, 0.0, 0.0, nan, 0.0, 0.0, 0.0, nan, nan, nan, 0.0, nan, 0.0, nan, 0.0, 0.0, 0.0, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, 0.0, 0.0, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan]	[0.6207791747342379, 0.47583015989183425, 0.2976531495240653, 0.6644438930587433, 0.4261667578041416, 0.04862031829603925, 0.0, 0.0046041813483673946, 0.05351218294031608, 0.01769598301185631, 0.0, 0.0, 0.0, nan, 0.0, 0.0, nan, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, 0.0, nan, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, 0.0, 0.0, nan, 0.0, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, 0.0, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan]
4.0603	5.0	100	4.1526	0.0217	0.0580	0.2746	[0.2638779780993535, 0.24032657224553952, 0.28498201974847515, 0.1075812162299665, 0.14745268628426467, 0.048342869965219346, 0.0, 0.007290688724806103, 0.04780558672261605, 0.06559620777139805, 0.0, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, nan, 0.0, nan, 0.0, nan, nan, nan, nan, 0.0, nan, 0.0, 0.0, nan, 0.0, 0.0, 0.0, nan, nan, nan, 0.0, nan, 0.0, nan, 0.0, 0.0, 0.0, nan, 0.0, nan, 0.0, 0.0, nan, nan, nan, nan, 0.0, 0.0, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan]	[0.5551073389128427, 0.47540841261768607, 0.4280130098767642, 0.6449145007547091, 0.4263212952616438, 0.051559171951657295, 0.0, 0.008099600657740192, 0.06573971674217831, 0.0695452132365953, 0.0, 0.0, 0.0, nan, 0.0, 0.0, nan, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, 0.0, nan, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, 0.0, 0.0, nan, 0.0, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, 0.0, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan]

Framework versions

• Transformers 4.28.1
• Pytorch 2.0.0+cu118
• Datasets 2.12.0
• Tokenizers 0.13.3