Hugging Face's logo

dgrinwald
/
swin-tiny-patch4-window7-224-finetuned-eurosat

Image Classification
Transformers
PyTorch
TensorBoard
swin
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
Dennis G commited on
Commit
bbd3546
·
1 Parent(s): 0b18017

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +69 -8
README.md CHANGED
@@ -2,11 +2,24 @@
2
  license: apache-2.0
3
  tags:
4
  - generated_from_trainer
 
 
5
  metrics:
6
  - accuracy
7
  model-index:
8
  - name: swin-tiny-patch4-window7-224-finetuned-eurosat
9
- results: []
 
 
 
 
 
 
 
 
 
 
 
10
  ---
11
 
12
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -14,10 +27,10 @@ should probably proofread and complete it, then remove this comment. -->
14
 
15
  # swin-tiny-patch4-window7-224-finetuned-eurosat
16
 
17
- This model is a fine-tuned version of [microsoft/swin-tiny-patch4-window7-224](https://huggingface.co/microsoft/swin-tiny-patch4-window7-224) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 0.5530
20
- - Accuracy: 0.7593
21
 
22
  ## Model description
23
 
@@ -45,19 +58,67 @@ The following hyperparameters were used during training:
45
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
  - lr_scheduler_type: linear
47
  - lr_scheduler_warmup_ratio: 0.1
48
- - num_epochs: 3
49
 
50
  ### Training results
51
 
52
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
53
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
54
- | 1.2124 | 1.0 | 17 | 0.8832 | 0.6971 |
55
- | 0.8782 | 2.0 | 34 | 0.6065 | 0.7635 |
56
- | 0.7307 | 3.0 | 51 | 0.5530 | 0.7593 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
57
 
58
 
59
  ### Framework versions
60
 
61
  - Transformers 4.20.1
62
  - Pytorch 1.11.0+cu113
 
63
  - Tokenizers 0.12.1
 
2
  license: apache-2.0
3
  tags:
4
  - generated_from_trainer
5
+ datasets:
6
+ - imagefolder
7
  metrics:
8
  - accuracy
9
  model-index:
10
  - name: swin-tiny-patch4-window7-224-finetuned-eurosat
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: 0.8464730290456431
23
  ---
24
 
25
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
27
 
28
  # swin-tiny-patch4-window7-224-finetuned-eurosat
29
 
30
+ This model is a fine-tuned version of [microsoft/swin-tiny-patch4-window7-224](https://huggingface.co/microsoft/swin-tiny-patch4-window7-224) on the imagefolder dataset.
31
  It achieves the following results on the evaluation set:
32
+ - Loss: 0.3266
33
+ - Accuracy: 0.8465
34
 
35
  ## Model description
36
 
 
58
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
59
  - lr_scheduler_type: linear
60
  - lr_scheduler_warmup_ratio: 0.1
61
+ - num_epochs: 50
62
 
63
  ### Training results
64
 
65
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
66
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
67
+ | 1.2941 | 1.0 | 17 | 1.1717 | 0.4689 |
68
+ | 1.0655 | 2.0 | 34 | 0.9397 | 0.5560 |
69
+ | 0.8008 | 3.0 | 51 | 0.6153 | 0.7303 |
70
+ | 0.7204 | 4.0 | 68 | 0.5665 | 0.7427 |
71
+ | 0.6931 | 5.0 | 85 | 0.4670 | 0.7801 |
72
+ | 0.6277 | 6.0 | 102 | 0.4328 | 0.8465 |
73
+ | 0.5689 | 7.0 | 119 | 0.4078 | 0.8174 |
74
+ | 0.6103 | 8.0 | 136 | 0.4060 | 0.8091 |
75
+ | 0.5501 | 9.0 | 153 | 0.4842 | 0.7884 |
76
+ | 0.6018 | 10.0 | 170 | 0.3780 | 0.8423 |
77
+ | 0.5668 | 11.0 | 187 | 0.3551 | 0.8631 |
78
+ | 0.5192 | 12.0 | 204 | 0.4514 | 0.8216 |
79
+ | 0.5133 | 13.0 | 221 | 0.3598 | 0.8174 |
80
+ | 0.5753 | 14.0 | 238 | 0.4172 | 0.8091 |
81
+ | 0.4833 | 15.0 | 255 | 0.4685 | 0.8050 |
82
+ | 0.5546 | 16.0 | 272 | 0.4474 | 0.7842 |
83
+ | 0.5179 | 17.0 | 289 | 0.4570 | 0.7884 |
84
+ | 0.5017 | 18.0 | 306 | 0.4218 | 0.8050 |
85
+ | 0.4808 | 19.0 | 323 | 0.4094 | 0.8050 |
86
+ | 0.4708 | 20.0 | 340 | 0.4693 | 0.7759 |
87
+ | 0.5033 | 21.0 | 357 | 0.3141 | 0.8672 |
88
+ | 0.4859 | 22.0 | 374 | 0.3687 | 0.8257 |
89
+ | 0.516 | 23.0 | 391 | 0.3819 | 0.8216 |
90
+ | 0.4822 | 24.0 | 408 | 0.3391 | 0.8506 |
91
+ | 0.4748 | 25.0 | 425 | 0.3281 | 0.8506 |
92
+ | 0.4914 | 26.0 | 442 | 0.3308 | 0.8631 |
93
+ | 0.4354 | 27.0 | 459 | 0.3859 | 0.8133 |
94
+ | 0.4297 | 28.0 | 476 | 0.3761 | 0.8133 |
95
+ | 0.4747 | 29.0 | 493 | 0.2914 | 0.8672 |
96
+ | 0.4395 | 30.0 | 510 | 0.3025 | 0.8548 |
97
+ | 0.4279 | 31.0 | 527 | 0.3314 | 0.8506 |
98
+ | 0.4327 | 32.0 | 544 | 0.4626 | 0.7842 |
99
+ | 0.446 | 33.0 | 561 | 0.3499 | 0.8382 |
100
+ | 0.4011 | 34.0 | 578 | 0.3408 | 0.8465 |
101
+ | 0.4418 | 35.0 | 595 | 0.3159 | 0.8589 |
102
+ | 0.484 | 36.0 | 612 | 0.3130 | 0.8548 |
103
+ | 0.4119 | 37.0 | 629 | 0.2899 | 0.8589 |
104
+ | 0.4453 | 38.0 | 646 | 0.3200 | 0.8465 |
105
+ | 0.4074 | 39.0 | 663 | 0.3493 | 0.8465 |
106
+ | 0.3937 | 40.0 | 680 | 0.3003 | 0.8672 |
107
+ | 0.4222 | 41.0 | 697 | 0.3547 | 0.8299 |
108
+ | 0.3922 | 42.0 | 714 | 0.3206 | 0.8589 |
109
+ | 0.3973 | 43.0 | 731 | 0.4074 | 0.8133 |
110
+ | 0.4118 | 44.0 | 748 | 0.3147 | 0.8589 |
111
+ | 0.4088 | 45.0 | 765 | 0.3393 | 0.8506 |
112
+ | 0.3635 | 46.0 | 782 | 0.3584 | 0.8257 |
113
+ | 0.403 | 47.0 | 799 | 0.3240 | 0.8506 |
114
+ | 0.3943 | 48.0 | 816 | 0.3536 | 0.8216 |
115
+ | 0.4085 | 49.0 | 833 | 0.3270 | 0.8465 |
116
+ | 0.3865 | 50.0 | 850 | 0.3266 | 0.8465 |
117
 
118
 
119
  ### Framework versions
120
 
121
  - Transformers 4.20.1
122
  - Pytorch 1.11.0+cu113
123
+ - Datasets 2.3.2
124
  - Tokenizers 0.12.1