amjadfqs commited on
Commit
db0845c
1 Parent(s): ea83fc8

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +29 -20
README.md CHANGED
@@ -1,7 +1,6 @@
1
  ---
2
  license: apache-2.0
3
  tags:
4
- - image-classification
5
  - generated_from_trainer
6
  datasets:
7
  - imagefolder
@@ -15,7 +14,7 @@ model-index:
15
  name: Image Classification
16
  type: image-classification
17
  dataset:
18
- name: Brain Tumor
19
  type: imagefolder
20
  config: default
21
  split: train
@@ -26,7 +25,7 @@ model-index:
26
  value: 0.9265375854214123
27
  - name: Precision
28
  type: precision
29
- value: 0.9269521372101541
30
  ---
31
 
32
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -34,12 +33,12 @@ should probably proofread and complete it, then remove this comment. -->
34
 
35
  # swin-base-patch4-window7-224-in22k-finetuned-brain-tumor-final
36
 
37
- 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 Brain Tumor dataset.
38
  It achieves the following results on the evaluation set:
39
- - Loss: 0.1925
40
  - Accuracy: 0.9265
41
  - F1 Score: 0.9252
42
- - Precision: 0.9270
43
 
44
  ## Model description
45
 
@@ -59,30 +58,40 @@ More information needed
59
 
60
  The following hyperparameters were used during training:
61
  - learning_rate: 1e-05
62
- - train_batch_size: 64
63
- - eval_batch_size: 64
64
  - seed: 42
65
  - gradient_accumulation_steps: 4
66
- - total_train_batch_size: 256
67
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
68
  - lr_scheduler_type: linear
69
  - lr_scheduler_warmup_ratio: 0.1
70
- - num_epochs: 10
71
 
72
  ### Training results
73
 
74
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Score | Precision |
75
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|:---------:|
76
- | 1.2212 | 0.96 | 20 | 1.1407 | 0.6429 | 0.6225 | 0.6601 |
77
- | 0.565 | 1.98 | 41 | 0.5162 | 0.8326 | 0.8311 | 0.8428 |
78
- | 0.3245 | 2.99 | 62 | 0.3265 | 0.8804 | 0.8784 | 0.8843 |
79
- | 0.2618 | 4.0 | 83 | 0.2713 | 0.9066 | 0.9054 | 0.9105 |
80
- | 0.2164 | 4.96 | 103 | 0.2812 | 0.8946 | 0.8929 | 0.8994 |
81
- | 0.1814 | 5.98 | 124 | 0.2411 | 0.9060 | 0.9043 | 0.9091 |
82
- | 0.1481 | 6.99 | 145 | 0.2345 | 0.9100 | 0.9084 | 0.9130 |
83
- | 0.1468 | 8.0 | 166 | 0.2340 | 0.9072 | 0.9055 | 0.9108 |
84
- | 0.1336 | 8.96 | 186 | 0.1925 | 0.9265 | 0.9252 | 0.9270 |
85
- | 0.133 | 9.64 | 200 | 0.2021 | 0.9220 | 0.9207 | 0.9235 |
 
 
 
 
 
 
 
 
 
 
86
 
87
 
88
  ### Framework versions
 
1
  ---
2
  license: apache-2.0
3
  tags:
 
4
  - generated_from_trainer
5
  datasets:
6
  - imagefolder
 
14
  name: Image Classification
15
  type: image-classification
16
  dataset:
17
+ name: imagefolder
18
  type: imagefolder
19
  config: default
20
  split: train
 
25
  value: 0.9265375854214123
26
  - name: Precision
27
  type: precision
28
+ value: 0.9307429809120586
29
  ---
30
 
31
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
33
 
34
  # swin-base-patch4-window7-224-in22k-finetuned-brain-tumor-final
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: 0.1955
39
  - Accuracy: 0.9265
40
  - F1 Score: 0.9252
41
+ - Precision: 0.9307
42
 
43
  ## Model description
44
 
 
58
 
59
  The following hyperparameters were used during training:
60
  - learning_rate: 1e-05
61
+ - train_batch_size: 32
62
+ - eval_batch_size: 32
63
  - seed: 42
64
  - gradient_accumulation_steps: 4
65
+ - total_train_batch_size: 128
66
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
67
  - lr_scheduler_type: linear
68
  - lr_scheduler_warmup_ratio: 0.1
69
+ - num_epochs: 20
70
 
71
  ### Training results
72
 
73
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Score | Precision |
74
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|:---------:|
75
+ | 1.1562 | 0.99 | 41 | 1.1378 | 0.6378 | 0.6191 | 0.6537 |
76
+ | 0.4878 | 1.99 | 82 | 0.6477 | 0.7591 | 0.7499 | 0.7874 |
77
+ | 0.2623 | 2.98 | 123 | 0.4410 | 0.8337 | 0.8311 | 0.8488 |
78
+ | 0.1985 | 4.0 | 165 | 0.4660 | 0.8144 | 0.8115 | 0.8455 |
79
+ | 0.1736 | 4.99 | 206 | 0.3230 | 0.8776 | 0.8760 | 0.8894 |
80
+ | 0.124 | 5.99 | 247 | 0.2684 | 0.9026 | 0.9014 | 0.9090 |
81
+ | 0.1278 | 6.98 | 288 | 0.2210 | 0.9180 | 0.9166 | 0.9210 |
82
+ | 0.0959 | 8.0 | 330 | 0.2151 | 0.9208 | 0.9195 | 0.9260 |
83
+ | 0.0849 | 8.99 | 371 | 0.2154 | 0.9220 | 0.9205 | 0.9291 |
84
+ | 0.0805 | 9.99 | 412 | 0.2112 | 0.9191 | 0.9179 | 0.9251 |
85
+ | 0.0682 | 10.98 | 453 | 0.1563 | 0.9385 | 0.9369 | 0.9402 |
86
+ | 0.0624 | 12.0 | 495 | 0.1577 | 0.9396 | 0.9385 | 0.9408 |
87
+ | 0.0415 | 12.99 | 536 | 0.1836 | 0.9305 | 0.9294 | 0.9332 |
88
+ | 0.0465 | 13.99 | 577 | 0.2145 | 0.9203 | 0.9192 | 0.9252 |
89
+ | 0.056 | 14.98 | 618 | 0.1710 | 0.9339 | 0.9325 | 0.9369 |
90
+ | 0.0545 | 16.0 | 660 | 0.2094 | 0.9248 | 0.9236 | 0.9298 |
91
+ | 0.0591 | 16.99 | 701 | 0.1752 | 0.9317 | 0.9303 | 0.9341 |
92
+ | 0.0512 | 17.99 | 742 | 0.1781 | 0.9311 | 0.9297 | 0.9342 |
93
+ | 0.0424 | 18.98 | 783 | 0.1873 | 0.9305 | 0.9293 | 0.9338 |
94
+ | 0.0438 | 19.88 | 820 | 0.1955 | 0.9265 | 0.9252 | 0.9307 |
95
 
96
 
97
  ### Framework versions