update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,94 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
datasets:
|
6 |
+
- imagefolder
|
7 |
+
metrics:
|
8 |
+
- accuracy
|
9 |
+
- precision
|
10 |
+
model-index:
|
11 |
+
- name: swin-base-patch4-window7-224-in22k-finetuned-brain-tumor-final_11
|
12 |
+
results:
|
13 |
+
- task:
|
14 |
+
name: Image Classification
|
15 |
+
type: image-classification
|
16 |
+
dataset:
|
17 |
+
name: imagefolder
|
18 |
+
type: imagefolder
|
19 |
+
config: default
|
20 |
+
split: train
|
21 |
+
args: default
|
22 |
+
metrics:
|
23 |
+
- name: Accuracy
|
24 |
+
type: accuracy
|
25 |
+
value: 0.8566378633150039
|
26 |
+
- name: Precision
|
27 |
+
type: precision
|
28 |
+
value: 0.8916086530475995
|
29 |
+
---
|
30 |
+
|
31 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
32 |
+
should probably proofread and complete it, then remove this comment. -->
|
33 |
+
|
34 |
+
# swin-base-patch4-window7-224-in22k-finetuned-brain-tumor-final_11
|
35 |
+
|
36 |
+
This model is a fine-tuned version of [microsoft/swin-base-patch4-window7-224-in22k](https://huggingface.co/microsoft/swin-base-patch4-window7-224-in22k) on the imagefolder dataset.
|
37 |
+
It achieves the following results on the evaluation set:
|
38 |
+
- Loss: 0.5327
|
39 |
+
- Accuracy: 0.8566
|
40 |
+
- F1 Score: 0.8626
|
41 |
+
- Precision: 0.8916
|
42 |
+
- Sensitivity: 0.8582
|
43 |
+
- Specificity: 0.9636
|
44 |
+
|
45 |
+
## Model description
|
46 |
+
|
47 |
+
More information needed
|
48 |
+
|
49 |
+
## Intended uses & limitations
|
50 |
+
|
51 |
+
More information needed
|
52 |
+
|
53 |
+
## Training and evaluation data
|
54 |
+
|
55 |
+
More information needed
|
56 |
+
|
57 |
+
## Training procedure
|
58 |
+
|
59 |
+
### Training hyperparameters
|
60 |
+
|
61 |
+
The following hyperparameters were used during training:
|
62 |
+
- learning_rate: 0.001
|
63 |
+
- train_batch_size: 100
|
64 |
+
- eval_batch_size: 100
|
65 |
+
- seed: 42
|
66 |
+
- gradient_accumulation_steps: 4
|
67 |
+
- total_train_batch_size: 400
|
68 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
69 |
+
- lr_scheduler_type: linear
|
70 |
+
- lr_scheduler_warmup_ratio: 0.1
|
71 |
+
- num_epochs: 10
|
72 |
+
|
73 |
+
### Training results
|
74 |
+
|
75 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Score | Precision | Sensitivity | Specificity |
|
76 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|:---------:|:-----------:|:-----------:|
|
77 |
+
| 1.2738 | 0.99 | 19 | 3.6805 | 0.3606 | 0.2878 | 0.6974 | 0.3569 | 0.8381 |
|
78 |
+
| 0.8184 | 1.97 | 38 | 2.2141 | 0.5196 | 0.4842 | 0.8085 | 0.5311 | 0.8793 |
|
79 |
+
| 0.3966 | 2.96 | 57 | 0.6808 | 0.8009 | 0.7976 | 0.8463 | 0.8029 | 0.9491 |
|
80 |
+
| 0.2336 | 4.0 | 77 | 0.5914 | 0.7946 | 0.8011 | 0.8170 | 0.7978 | 0.9461 |
|
81 |
+
| 0.1196 | 4.99 | 96 | 0.4851 | 0.8606 | 0.8606 | 0.8779 | 0.8645 | 0.9644 |
|
82 |
+
| 0.1003 | 5.97 | 115 | 0.5353 | 0.8413 | 0.8475 | 0.8716 | 0.8442 | 0.9593 |
|
83 |
+
| 0.0876 | 6.96 | 134 | 0.6691 | 0.8032 | 0.8151 | 0.8766 | 0.8051 | 0.9503 |
|
84 |
+
| 0.0569 | 8.0 | 154 | 0.4531 | 0.8570 | 0.8610 | 0.8776 | 0.8614 | 0.9634 |
|
85 |
+
| 0.0329 | 8.99 | 173 | 0.8581 | 0.7977 | 0.8081 | 0.8692 | 0.8023 | 0.9488 |
|
86 |
+
| 0.0262 | 9.87 | 190 | 0.5327 | 0.8566 | 0.8626 | 0.8916 | 0.8582 | 0.9636 |
|
87 |
+
|
88 |
+
|
89 |
+
### Framework versions
|
90 |
+
|
91 |
+
- Transformers 4.29.2
|
92 |
+
- Pytorch 2.0.1+cu117
|
93 |
+
- Datasets 2.12.0
|
94 |
+
- Tokenizers 0.13.3
|