|
|
--- |
|
|
license: other |
|
|
base_model: nvidia/segformer-b0-finetuned-ade-512-512 |
|
|
tags: |
|
|
- generated_from_keras_callback |
|
|
model-index: |
|
|
- name: akar49/MRI_segmentation-1 |
|
|
results: [] |
|
|
--- |
|
|
|
|
|
<!-- This model card has been generated automatically according to the information Keras had access to. You should |
|
|
probably proofread and complete it, then remove this comment. --> |
|
|
|
|
|
# akar49/MRI_segmentation-1 |
|
|
|
|
|
This model is a fine-tuned version of [nvidia/segformer-b0-finetuned-ade-512-512](https://huggingface.co/nvidia/segformer-b0-finetuned-ade-512-512) on an unknown dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Train Loss: 0.0034 |
|
|
- Validation Loss: 0.0098 |
|
|
- 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 | |
|
|
|:----------:|:---------------:|:-----:| |
|
|
| 0.3300 | 0.0731 | 0 | |
|
|
| 0.0881 | 0.0651 | 1 | |
|
|
| 0.0660 | 0.0632 | 2 | |
|
|
| 0.0573 | 0.0463 | 3 | |
|
|
| 0.0525 | 0.0495 | 4 | |
|
|
| 0.0475 | 0.0431 | 5 | |
|
|
| 0.0379 | 0.0367 | 6 | |
|
|
| 0.0318 | 0.0319 | 7 | |
|
|
| 0.0280 | 0.0260 | 8 | |
|
|
| 0.0246 | 0.0253 | 9 | |
|
|
| 0.0235 | 0.0267 | 10 | |
|
|
| 0.0205 | 0.0205 | 11 | |
|
|
| 0.0182 | 0.0227 | 12 | |
|
|
| 0.0182 | 0.0234 | 13 | |
|
|
| 0.0169 | 0.0197 | 14 | |
|
|
| 0.0163 | 0.0200 | 15 | |
|
|
| 0.0173 | 0.0192 | 16 | |
|
|
| 0.0130 | 0.0179 | 17 | |
|
|
| 0.0123 | 0.0123 | 18 | |
|
|
| 0.0103 | 0.0137 | 19 | |
|
|
| 0.0098 | 0.0121 | 20 | |
|
|
| 0.0114 | 0.0115 | 21 | |
|
|
| 0.0097 | 0.0116 | 22 | |
|
|
| 0.0083 | 0.0108 | 23 | |
|
|
| 0.0078 | 0.0116 | 24 | |
|
|
| 0.0074 | 0.0102 | 25 | |
|
|
| 0.0071 | 0.0121 | 26 | |
|
|
| 0.0073 | 0.0104 | 27 | |
|
|
| 0.0071 | 0.0128 | 28 | |
|
|
| 0.0066 | 0.0110 | 29 | |
|
|
| 0.0061 | 0.0103 | 30 | |
|
|
| 0.0067 | 0.0115 | 31 | |
|
|
| 0.0071 | 0.0246 | 32 | |
|
|
| 0.0091 | 0.0106 | 33 | |
|
|
| 0.0079 | 0.0107 | 34 | |
|
|
| 0.0066 | 0.0109 | 35 | |
|
|
| 0.0059 | 0.0104 | 36 | |
|
|
| 0.0057 | 0.0092 | 37 | |
|
|
| 0.0055 | 0.0096 | 38 | |
|
|
| 0.0052 | 0.0099 | 39 | |
|
|
| 0.0051 | 0.0102 | 40 | |
|
|
| 0.0057 | 0.0108 | 41 | |
|
|
| 0.0049 | 0.0097 | 42 | |
|
|
| 0.0048 | 0.0093 | 43 | |
|
|
| 0.0047 | 0.0095 | 44 | |
|
|
| 0.0045 | 0.0115 | 45 | |
|
|
| 0.0047 | 0.0114 | 46 | |
|
|
| 0.0048 | 0.0105 | 47 | |
|
|
| 0.0049 | 0.0093 | 48 | |
|
|
| 0.0050 | 0.0093 | 49 | |
|
|
| 0.0044 | 0.0097 | 50 | |
|
|
| 0.0040 | 0.0101 | 51 | |
|
|
| 0.0041 | 0.0098 | 52 | |
|
|
| 0.0041 | 0.0099 | 53 | |
|
|
| 0.0039 | 0.0109 | 54 | |
|
|
| 0.0040 | 0.0099 | 55 | |
|
|
| 0.0038 | 0.0112 | 56 | |
|
|
| 0.0037 | 0.0096 | 57 | |
|
|
| 0.0035 | 0.0106 | 58 | |
|
|
| 0.0034 | 0.0098 | 59 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.31.0 |
|
|
- TensorFlow 2.12.0 |
|
|
- Datasets 2.14.2 |
|
|
- Tokenizers 0.13.3 |
|
|
|
