itistamtran commited on
Commit
cfeefae
·
verified ·
1 Parent(s): 4f4318e

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +0 -8
README.md CHANGED
@@ -22,7 +22,6 @@ tags:
22
  ---
23
 
24
  # Vision Transformer for Brain Tumor Multiclass Classification (v2)
25
-
26
  This model is a fine-tuned Vision Transformer (ViT) for multiclass brain tumor MRI classification. It predicts one of the following five classes:
27
 
28
  • Glioma
@@ -34,7 +33,6 @@ This model is a fine-tuned Vision Transformer (ViT) for multiclass brain tumor M
34
  The model is integrated into an online diagnostic support platform at https://www.medscanai.net/.
35
 
36
  ---
37
-
38
  ## Model Details
39
 
40
  - **Base Model:** google/vit-base-patch16-224-in21k
@@ -46,14 +44,12 @@ The model is integrated into an online diagnostic support platform at https://ww
46
  - **Not for clinical diagnosis**
47
 
48
  ---
49
-
50
  ## Dataset
51
 
52
  The primary dataset is sourced from the Kaggle "Brain Tumor MRI Dataset" by Masoud Nickparvar.
53
  Additional "unknown" category samples were collected from publicly available online sources to evaluate robustness.
54
 
55
  ---
56
-
57
  ## Training
58
 
59
  - 20 epochs using Hugging Face Trainer
@@ -63,9 +59,6 @@ Additional "unknown" category samples were collected from publicly available onl
63
  - Evaluation metric: Accuracy
64
 
65
  ---
66
-
67
- ## Performance
68
-
69
  ## Performance
70
 
71
  | Class | Precision | Recall | F1-score |
@@ -79,7 +72,6 @@ Additional "unknown" category samples were collected from publicly available onl
79
  **Overall accuracy: 98 percent**
80
 
81
  ---
82
-
83
  ## How to Use
84
 
85
  ```python
 
22
  ---
23
 
24
  # Vision Transformer for Brain Tumor Multiclass Classification (v2)
 
25
  This model is a fine-tuned Vision Transformer (ViT) for multiclass brain tumor MRI classification. It predicts one of the following five classes:
26
 
27
  • Glioma
 
33
  The model is integrated into an online diagnostic support platform at https://www.medscanai.net/.
34
 
35
  ---
 
36
  ## Model Details
37
 
38
  - **Base Model:** google/vit-base-patch16-224-in21k
 
44
  - **Not for clinical diagnosis**
45
 
46
  ---
 
47
  ## Dataset
48
 
49
  The primary dataset is sourced from the Kaggle "Brain Tumor MRI Dataset" by Masoud Nickparvar.
50
  Additional "unknown" category samples were collected from publicly available online sources to evaluate robustness.
51
 
52
  ---
 
53
  ## Training
54
 
55
  - 20 epochs using Hugging Face Trainer
 
59
  - Evaluation metric: Accuracy
60
 
61
  ---
 
 
 
62
  ## Performance
63
 
64
  | Class | Precision | Recall | F1-score |
 
72
  **Overall accuracy: 98 percent**
73
 
74
  ---
 
75
  ## How to Use
76
 
77
  ```python