Commit
·
b5ecb1e
1
Parent(s):
2a72784
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,85 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
datasets:
|
| 6 |
+
- imagefolder
|
| 7 |
+
metrics:
|
| 8 |
+
- accuracy
|
| 9 |
+
model-index:
|
| 10 |
+
- name: vit-base-mri
|
| 11 |
+
results:
|
| 12 |
+
- task:
|
| 13 |
+
name: Image Classification
|
| 14 |
+
type: image-classification
|
| 15 |
+
dataset:
|
| 16 |
+
name: imagefolder
|
| 17 |
+
type: imagefolder
|
| 18 |
+
args: default
|
| 19 |
+
metrics:
|
| 20 |
+
- name: Accuracy
|
| 21 |
+
type: accuracy
|
| 22 |
+
value: 0.987944228954817
|
| 23 |
+
---
|
| 24 |
+
|
| 25 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 26 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 27 |
+
|
| 28 |
+
# vit-base-mri
|
| 29 |
+
|
| 30 |
+
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the imagefolder dataset.
|
| 31 |
+
It achieves the following results on the evaluation set:
|
| 32 |
+
- Loss: 0.0690
|
| 33 |
+
- Accuracy: 0.9879
|
| 34 |
+
|
| 35 |
+
## Model description
|
| 36 |
+
|
| 37 |
+
More information needed
|
| 38 |
+
|
| 39 |
+
## Intended uses & limitations
|
| 40 |
+
|
| 41 |
+
More information needed
|
| 42 |
+
|
| 43 |
+
## Training and evaluation data
|
| 44 |
+
|
| 45 |
+
More information needed
|
| 46 |
+
|
| 47 |
+
## Training procedure
|
| 48 |
+
|
| 49 |
+
### Training hyperparameters
|
| 50 |
+
|
| 51 |
+
The following hyperparameters were used during training:
|
| 52 |
+
- learning_rate: 3e-05
|
| 53 |
+
- train_batch_size: 32
|
| 54 |
+
- eval_batch_size: 8
|
| 55 |
+
- seed: 42
|
| 56 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 57 |
+
- lr_scheduler_type: linear
|
| 58 |
+
- num_epochs: 4
|
| 59 |
+
- mixed_precision_training: Native AMP
|
| 60 |
+
|
| 61 |
+
### Training results
|
| 62 |
+
|
| 63 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 64 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 65 |
+
| 0.04 | 0.3 | 500 | 0.0828 | 0.9690 |
|
| 66 |
+
| 0.0765 | 0.59 | 1000 | 0.0623 | 0.9750 |
|
| 67 |
+
| 0.0479 | 0.89 | 1500 | 0.0453 | 0.9827 |
|
| 68 |
+
| 0.0199 | 1.18 | 2000 | 0.0524 | 0.9857 |
|
| 69 |
+
| 0.0114 | 1.48 | 2500 | 0.0484 | 0.9861 |
|
| 70 |
+
| 0.008 | 1.78 | 3000 | 0.0566 | 0.9852 |
|
| 71 |
+
| 0.0051 | 2.07 | 3500 | 0.0513 | 0.9874 |
|
| 72 |
+
| 0.0008 | 2.37 | 4000 | 0.0617 | 0.9874 |
|
| 73 |
+
| 0.0021 | 2.66 | 4500 | 0.0664 | 0.9870 |
|
| 74 |
+
| 0.0005 | 2.96 | 5000 | 0.0639 | 0.9872 |
|
| 75 |
+
| 0.001 | 3.25 | 5500 | 0.0644 | 0.9879 |
|
| 76 |
+
| 0.0004 | 3.55 | 6000 | 0.0672 | 0.9875 |
|
| 77 |
+
| 0.0003 | 3.85 | 6500 | 0.0690 | 0.9879 |
|
| 78 |
+
|
| 79 |
+
|
| 80 |
+
### Framework versions
|
| 81 |
+
|
| 82 |
+
- Transformers 4.20.0
|
| 83 |
+
- Pytorch 1.11.0+cu113
|
| 84 |
+
- Datasets 2.3.2
|
| 85 |
+
- Tokenizers 0.12.1
|