Segformer-MRIseg_model

This model is a fine-tuned version of nvidia/segformer-b0-finetuned-ade-512-512 on an unknown dataset. It achieves the following results on the evaluation set:

• Train Loss: 0.0049
• Validation Loss: 0.0133
• Epoch: 59

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', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': 0.001, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
• training_precision: float32

Training results

Train Loss	Validation Loss	Epoch
0.2537	0.0685	0
0.0849	0.0639	1
0.0664	0.0532	2
0.0580	0.0503	3
0.0536	0.0497	4
0.0476	0.0396	5
0.0437	0.0477	6
0.0359	0.0397	7
0.0312	0.0289	8
0.0256	0.0322	9
0.0241	0.0279	10
0.0220	0.0229	11
0.0180	0.0226	12
0.0160	0.0192	13
0.0165	0.0227	14
0.0151	0.0194	15
0.0146	0.0184	16
0.0132	0.0177	17
0.0121	0.0211	18
0.0111	0.0197	19
0.0107	0.0175	20
0.0116	0.0131	21
0.0115	0.0181	22
0.0094	0.0153	23
0.0099	0.0140	24
0.0098	0.0151	25
0.0084	0.0126	26
0.0080	0.0140	27
0.0071	0.0128	28
0.0067	0.0169	29
0.0061	0.0131	30
0.0063	0.0207	31
0.0067	0.0129	32
0.0062	0.0152	33
0.0056	0.0148	34
0.0056	0.0171	35
0.0051	0.0154	36
0.0049	0.0172	37
0.0049	0.0180	38
0.0056	0.0168	39
0.0050	0.0142	40
0.0048	0.0165	41
0.0051	0.0195	42
0.0048	0.0232	43
0.0042	0.0208	44
0.0041	0.0249	45
0.0044	0.0220	46
0.0041	0.0234	47
0.0042	0.0198	48
0.0040	0.0282	49
0.0039	0.0251	50
0.0039	0.0302	51
0.0041	0.0219	52
0.0040	0.0187	53
0.0039	0.0203	54
0.0043	0.0180	55
0.0051	0.0150	56
0.0079	0.0205	57
0.0052	0.0152	58
0.0049	0.0133	59

Framework versions

• Transformers 4.31.0
• TensorFlow 2.12.0
• Datasets 2.14.4
• Tokenizers 0.13.3