Segformer-MRIseg_Sep

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: 0.0026
• Validation Loss: 0.0116
• 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
0.1563	0.0558	0
0.0488	0.0706	1
0.0290	0.0230	2
0.0207	0.0160	3
0.0164	0.0145	4
0.0136	0.0133	5
0.0117	0.0136	6
0.0106	0.0144	7
0.0104	0.0147	8
0.0091	0.0109	9
0.0078	0.0104	10
0.0071	0.0108	11
0.0067	0.0101	12
0.0064	0.0110	13
0.0058	0.0096	14
0.0057	0.0101	15
0.0055	0.0115	16
0.0055	0.0109	17
0.0051	0.0098	18
0.0051	0.0108	19
0.0048	0.0097	20
0.0050	0.0097	21
0.0047	0.0088	22
0.0045	0.0110	23
0.0043	0.0098	24
0.0041	0.0098	25
0.0041	0.0126	26
0.0040	0.0125	27
0.0042	0.0098	28
0.0039	0.0109	29
0.0037	0.0096	30
0.0038	0.0104	31
0.0036	0.0103	32
0.0034	0.0100	33
0.0033	0.0099	34
0.0038	0.0100	35
0.0036	0.0111	36
0.0036	0.0158	37
0.0034	0.0104	38
0.0032	0.0100	39
0.0030	0.0100	40
0.0030	0.0099	41
0.0029	0.0098	42
0.0028	0.0112	43
0.0030	0.0105	44
0.0029	0.0104	45
0.0029	0.0100	46
0.0027	0.0119	47
0.0030	0.0119	48
0.0028	0.0109	49
0.0029	0.0106	50
0.0027	0.0111	51
0.0027	0.0111	52
0.0027	0.0132	53
0.0029	0.0105	54
0.0026	0.0113	55
0.0027	0.0108	56
0.0025	0.0112	57
0.0025	0.0105	58
0.0026	0.0116	59

Framework versions

• Transformers 4.31.0
• TensorFlow 2.13.0
• Datasets 2.14.5
• Tokenizers 0.13.3