akar49's picture
Upload TFSegformerForSemanticSegmentation
4a92739 verified
metadata
license: other
base_model: nvidia/segformer-b0-finetuned-ade-512-512
tags:
  - generated_from_keras_callback
model-index:
  - name: Segformer-MRIseg_model_Mar24
    results: []

Segformer-MRIseg_model_Mar24

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: 0.0037
  • Validation Loss: 0.0081
  • 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
0.5861 0.0929 0
0.0953 0.0606 1
0.0509 0.0350 2
0.0308 0.0231 3
0.0253 0.0219 4
0.0202 0.0179 5
0.0162 0.0184 6
0.0152 0.0188 7
0.0135 0.0157 8
0.0119 0.0170 9
0.0110 0.0150 10
0.0102 0.0157 11
0.0097 0.0137 12
0.0095 0.0141 13
0.0087 0.0118 14
0.0079 0.0116 15
0.0075 0.0119 16
0.0072 0.0109 17
0.0069 0.0118 18
0.0068 0.0104 19
0.0065 0.0108 20
0.0064 0.0124 21
0.0062 0.0095 22
0.0058 0.0111 23
0.0058 0.0094 24
0.0056 0.0111 25
0.0055 0.0125 26
0.0057 0.0104 27
0.0053 0.0096 28
0.0051 0.0105 29
0.0050 0.0103 30
0.0048 0.0091 31
0.0047 0.0097 32
0.0044 0.0094 33
0.0045 0.0092 34
0.0045 0.0093 35
0.0047 0.0088 36
0.0048 0.0089 37
0.0045 0.0108 38
0.0043 0.0088 39
0.0043 0.0090 40
0.0044 0.0106 41
0.0053 0.0100 42
0.0051 0.0102 43
0.0044 0.0097 44
0.0039 0.0088 45
0.0040 0.0097 46
0.0040 0.0089 47
0.0037 0.0095 48
0.0034 0.0085 49
0.0041 0.0082 50
0.0054 0.0098 51
0.0053 0.0085 52
0.0044 0.0086 53
0.0040 0.0082 54
0.0038 0.0082 55
0.0035 0.0092 56
0.0034 0.0090 57
0.0035 0.0079 58
0.0037 0.0081 59

Framework versions

  • Transformers 4.38.1
  • TensorFlow 2.15.0
  • Datasets 2.18.0
  • Tokenizers 0.15.2