Hugging Face's logo

redbioma
/
swin-base-simmim-window6-192-cemede-redbioma-ct-fewer-classes

Image Classification
Transformers
TensorBoard
Safetensors
swin
Generated from Trainer
Model card Files
xet
Metrics Community
redbioma commited on
Commit
0f3b762
·
verified ·
1 Parent(s): 8328d53

Model save

Browse files
Files changed (2) hide show
  1. README.md +48 -31
  2. model.safetensors +1 -1
README.md CHANGED
@@ -3,7 +3,6 @@ library_name: transformers
3
  license: apache-2.0
4
  base_model: microsoft/swin-base-simmim-window6-192
5
  tags:
6
- - image-classification
7
  - generated_from_trainer
8
  metrics:
9
  - accuracy
@@ -18,11 +17,11 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  # swin-CEMEDE-og
20
 
21
- This model is a fine-tuned version of [microsoft/swin-base-simmim-window6-192](https://huggingface.co/microsoft/swin-base-simmim-window6-192) on the cemede dataset.
22
  It achieves the following results on the evaluation set:
23
- - Loss: 1.2532
24
- - Accuracy: 0.7230
25
- - F1: 0.5583
26
 
27
  ## Model description
28
 
@@ -47,38 +46,56 @@ The following hyperparameters were used during training:
47
  - seed: 42
48
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
49
  - lr_scheduler_type: linear
50
- - num_epochs: 5
51
  - mixed_precision_training: Native AMP
52
 
53
  ### Training results
54
 
55
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
56
  |:-------------:|:------:|:----:|:---------------:|:--------:|:------:|
57
- | 2.0393 | 0.0878 | 100 | 2.5107 | 0.3236 | 0.1026 |
58
- | 1.8391 | 0.1756 | 200 | 2.5567 | 0.3218 | 0.0991 |
59
- | 1.5823 | 0.2634 | 300 | 2.3310 | 0.3720 | 0.1768 |
60
- | 1.0746 | 0.3512 | 400 | 2.2149 | 0.4299 | 0.1598 |
61
- | 1.0537 | 0.4390 | 500 | 2.0965 | 0.4263 | 0.1996 |
62
- | 1.0265 | 0.5268 | 600 | 2.0171 | 0.4563 | 0.2955 |
63
- | 1.4582 | 0.6146 | 700 | 1.7061 | 0.5787 | 0.3996 |
64
- | 0.9523 | 0.7024 | 800 | 1.8517 | 0.5137 | 0.3831 |
65
- | 0.6337 | 0.7902 | 900 | 1.9887 | 0.5370 | 0.3938 |
66
- | 0.725 | 0.8780 | 1000 | 1.8860 | 0.5639 | 0.4078 |
67
- | 0.7052 | 0.9658 | 1100 | 1.8908 | 0.5594 | 0.3950 |
68
- | 0.4509 | 1.0536 | 1200 | 1.6617 | 0.6401 | 0.4587 |
69
- | 0.5311 | 1.1414 | 1300 | 1.5974 | 0.6607 | 0.5504 |
70
- | 0.427 | 1.2291 | 1400 | 1.7896 | 0.6074 | 0.5357 |
71
- | 0.3824 | 1.3169 | 1500 | 1.2532 | 0.7230 | 0.5583 |
72
- | 0.369 | 1.4047 | 1600 | 1.6739 | 0.6311 | 0.5291 |
73
- | 0.3733 | 1.4925 | 1700 | 1.7065 | 0.6329 | 0.4761 |
74
- | 0.362 | 1.5803 | 1800 | 1.3902 | 0.7028 | 0.5837 |
75
- | 0.702 | 1.6681 | 1900 | 1.4199 | 0.7127 | 0.5632 |
76
- | 0.6351 | 1.7559 | 2000 | 1.6125 | 0.6853 | 0.5561 |
77
- | 0.2508 | 1.8437 | 2100 | 1.3501 | 0.7158 | 0.5877 |
78
- | 0.5023 | 1.9315 | 2200 | 1.3937 | 0.7225 | 0.5888 |
79
- | 0.3035 | 2.0193 | 2300 | 1.4046 | 0.7396 | 0.6178 |
80
- | 0.2108 | 2.1071 | 2400 | 1.3595 | 0.7727 | 0.6444 |
81
- | 0.5197 | 2.1949 | 2500 | 1.4296 | 0.7544 | 0.6292 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
82
 
83
 
84
  ### Framework versions
 
3
  license: apache-2.0
4
  base_model: microsoft/swin-base-simmim-window6-192
5
  tags:
 
6
  - generated_from_trainer
7
  metrics:
8
  - accuracy
 
17
 
18
  # swin-CEMEDE-og
19
 
20
+ This model is a fine-tuned version of [microsoft/swin-base-simmim-window6-192](https://huggingface.co/microsoft/swin-base-simmim-window6-192) on an unknown dataset.
21
  It achieves the following results on the evaluation set:
22
+ - Loss: 1.0976
23
+ - Accuracy: 0.8041
24
+ - F1: 0.7406
25
 
26
  ## Model description
27
 
 
46
  - seed: 42
47
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
48
  - lr_scheduler_type: linear
49
+ - num_epochs: 10
50
  - mixed_precision_training: Native AMP
51
 
52
  ### Training results
53
 
54
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
55
  |:-------------:|:------:|:----:|:---------------:|:--------:|:------:|
56
+ | 2.2296 | 0.0840 | 100 | 2.1836 | 0.2570 | 0.0825 |
57
+ | 1.8921 | 0.1679 | 200 | 2.2063 | 0.3080 | 0.1300 |
58
+ | 1.682 | 0.2519 | 300 | 2.4050 | 0.3862 | 0.1449 |
59
+ | 1.8146 | 0.3359 | 400 | 1.9343 | 0.4253 | 0.2199 |
60
+ | 1.423 | 0.4198 | 500 | 1.9058 | 0.4579 | 0.2335 |
61
+ | 1.5637 | 0.5038 | 600 | 1.6756 | 0.5085 | 0.3331 |
62
+ | 1.0535 | 0.5877 | 700 | 1.4023 | 0.5641 | 0.3791 |
63
+ | 1.0955 | 0.6717 | 800 | 1.3086 | 0.6069 | 0.4426 |
64
+ | 0.8927 | 0.7557 | 900 | 1.2083 | 0.6377 | 0.5108 |
65
+ | 0.8035 | 0.8396 | 1000 | 1.3281 | 0.6340 | 0.4921 |
66
+ | 0.8517 | 0.9236 | 1100 | 1.2840 | 0.6492 | 0.5175 |
67
+ | 0.6035 | 1.0076 | 1200 | 1.2919 | 0.6446 | 0.5013 |
68
+ | 0.7727 | 1.0915 | 1300 | 1.0839 | 0.6878 | 0.5742 |
69
+ | 0.625 | 1.1755 | 1400 | 1.1132 | 0.7034 | 0.5552 |
70
+ | 0.554 | 1.2594 | 1500 | 1.2120 | 0.6492 | 0.5758 |
71
+ | 0.4117 | 1.3434 | 1600 | 1.1343 | 0.7030 | 0.5748 |
72
+ | 0.7557 | 1.4274 | 1700 | 1.1490 | 0.6975 | 0.5751 |
73
+ | 0.4841 | 1.5113 | 1800 | 0.9364 | 0.7756 | 0.6364 |
74
+ | 0.4899 | 1.5953 | 1900 | 1.1162 | 0.6929 | 0.5657 |
75
+ | 0.6598 | 1.6793 | 2000 | 0.9602 | 0.7402 | 0.6597 |
76
+ | 0.2826 | 1.7632 | 2100 | 1.2618 | 0.7044 | 0.6255 |
77
+ | 0.4785 | 1.8472 | 2200 | 1.0743 | 0.7269 | 0.6488 |
78
+ | 0.4427 | 1.9312 | 2300 | 0.8803 | 0.7641 | 0.6690 |
79
+ | 0.5305 | 2.0151 | 2400 | 0.8739 | 0.7830 | 0.6996 |
80
+ | 0.3814 | 2.0991 | 2500 | 0.9660 | 0.7789 | 0.6873 |
81
+ | 0.2273 | 2.1830 | 2600 | 1.0271 | 0.7789 | 0.7071 |
82
+ | 0.232 | 2.2670 | 2700 | 0.9957 | 0.7724 | 0.6961 |
83
+ | 0.2101 | 2.3510 | 2800 | 0.9729 | 0.7798 | 0.7196 |
84
+ | 0.4029 | 2.4349 | 2900 | 1.0296 | 0.7526 | 0.6911 |
85
+ | 0.2645 | 2.5189 | 3000 | 1.0878 | 0.7747 | 0.7058 |
86
+ | 0.3111 | 2.6029 | 3100 | 1.0745 | 0.7623 | 0.7072 |
87
+ | 0.1767 | 2.6868 | 3200 | 0.8820 | 0.7913 | 0.7424 |
88
+ | 0.167 | 2.7708 | 3300 | 0.8707 | 0.8018 | 0.7127 |
89
+ | 0.2523 | 2.8547 | 3400 | 1.0131 | 0.8046 | 0.7418 |
90
+ | 0.0786 | 2.9387 | 3500 | 1.0026 | 0.7807 | 0.7249 |
91
+ | 0.259 | 3.0227 | 3600 | 0.9817 | 0.7922 | 0.7109 |
92
+ | 0.3004 | 3.1066 | 3700 | 1.0838 | 0.7977 | 0.7341 |
93
+ | 0.1594 | 3.1906 | 3800 | 0.9184 | 0.8078 | 0.7323 |
94
+ | 0.1957 | 3.2746 | 3900 | 0.8777 | 0.8248 | 0.7255 |
95
+ | 0.1107 | 3.3585 | 4000 | 0.9186 | 0.8216 | 0.7360 |
96
+ | 0.1389 | 3.4425 | 4100 | 0.9996 | 0.8032 | 0.7358 |
97
+ | 0.1273 | 3.5264 | 4200 | 1.0062 | 0.8147 | 0.7604 |
98
+ | 0.2635 | 3.6104 | 4300 | 1.0976 | 0.8041 | 0.7406 |
99
 
100
 
101
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9dd93ac2993d84833dc095ac62c87b2f91331eca82e5ce22cfceda5ffe136f84
3
  size 347308740
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c8351fd2563c83529d2763c945dedaa58b61bf905b629670d3e76b0f256be2e
3
  size 347308740