Hugging Face's logo

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

Image Classification
Transformers
TensorBoard
Safetensors
swin
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
happybot commited on
Commit
e0d41fe
•
1 Parent(s): 572b0a4

Model save

Browse files
Files changed (3) hide show
  1. README.md +15 -55
  2. model.safetensors +1 -1
  3. runs/Mar01_04-04-16_a2ca3ccf826b/events.out.tfevents.1709266087.a2ca3ccf826b.460.0 +2 -2
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.8803088803088803
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,8 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
32
 
33
  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.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 0.5056
36
- - Accuracy: 0.8803
37
 
38
  ## Model description
39
 
@@ -61,67 +61,27 @@ The following hyperparameters were used during training:
61
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
62
  - lr_scheduler_type: linear
63
  - lr_scheduler_warmup_ratio: 0.1
64
- - num_epochs: 50
65
 
66
  ### Training results
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
- | 2.1952 | 0.99 | 18 | 1.5914 | 0.5985 |
71
- | 1.3705 | 1.97 | 36 | 1.2164 | 0.6873 |
72
- | 1.026 | 2.96 | 54 | 0.9974 | 0.7375 |
73
- | 0.829 | 4.0 | 73 | 0.7667 | 0.7722 |
74
- | 0.6513 | 4.99 | 91 | 0.6674 | 0.8224 |
75
- | 0.5516 | 5.97 | 109 | 0.5810 | 0.8378 |
76
- | 0.4978 | 6.96 | 127 | 0.5498 | 0.8263 |
77
- | 0.4568 | 8.0 | 146 | 0.5999 | 0.8185 |
78
- | 0.4047 | 8.99 | 164 | 0.5211 | 0.8494 |
79
- | 0.3696 | 9.97 | 182 | 0.5201 | 0.8571 |
80
- | 0.3479 | 10.96 | 200 | 0.5310 | 0.8263 |
81
- | 0.329 | 12.0 | 219 | 0.5439 | 0.8494 |
82
- | 0.3376 | 12.99 | 237 | 0.5050 | 0.8494 |
83
- | 0.2804 | 13.97 | 255 | 0.5709 | 0.8263 |
84
- | 0.2941 | 14.96 | 273 | 0.6376 | 0.8147 |
85
- | 0.3026 | 16.0 | 292 | 0.5447 | 0.8494 |
86
- | 0.2578 | 16.99 | 310 | 0.5056 | 0.8803 |
87
- | 0.219 | 17.97 | 328 | 0.5620 | 0.8610 |
88
- | 0.2403 | 18.96 | 346 | 0.5582 | 0.8456 |
89
- | 0.2258 | 20.0 | 365 | 0.5458 | 0.8494 |
90
- | 0.2265 | 20.99 | 383 | 0.5411 | 0.8533 |
91
- | 0.1893 | 21.97 | 401 | 0.5477 | 0.8494 |
92
- | 0.1896 | 22.96 | 419 | 0.5125 | 0.8494 |
93
- | 0.1976 | 24.0 | 438 | 0.5672 | 0.8340 |
94
- | 0.1725 | 24.99 | 456 | 0.5581 | 0.8456 |
95
- | 0.168 | 25.97 | 474 | 0.5965 | 0.8456 |
96
- | 0.1821 | 26.96 | 492 | 0.5567 | 0.8610 |
97
- | 0.1805 | 28.0 | 511 | 0.5998 | 0.8533 |
98
- | 0.1616 | 28.99 | 529 | 0.5451 | 0.8533 |
99
- | 0.1467 | 29.97 | 547 | 0.5574 | 0.8494 |
100
- | 0.1439 | 30.96 | 565 | 0.5707 | 0.8571 |
101
- | 0.13 | 32.0 | 584 | 0.6019 | 0.8378 |
102
- | 0.1353 | 32.99 | 602 | 0.5952 | 0.8610 |
103
- | 0.1329 | 33.97 | 620 | 0.6262 | 0.8378 |
104
- | 0.1258 | 34.96 | 638 | 0.6314 | 0.8456 |
105
- | 0.1408 | 36.0 | 657 | 0.5761 | 0.8494 |
106
- | 0.1197 | 36.99 | 675 | 0.5703 | 0.8610 |
107
- | 0.1208 | 37.97 | 693 | 0.6247 | 0.8456 |
108
- | 0.1197 | 38.96 | 711 | 0.6026 | 0.8533 |
109
- | 0.1271 | 40.0 | 730 | 0.5953 | 0.8533 |
110
- | 0.1053 | 40.99 | 748 | 0.6070 | 0.8533 |
111
- | 0.0846 | 41.97 | 766 | 0.6094 | 0.8610 |
112
- | 0.1206 | 42.96 | 784 | 0.5912 | 0.8494 |
113
- | 0.1225 | 44.0 | 803 | 0.6074 | 0.8494 |
114
- | 0.1184 | 44.99 | 821 | 0.5943 | 0.8494 |
115
- | 0.1027 | 45.97 | 839 | 0.6084 | 0.8494 |
116
- | 0.1113 | 46.96 | 857 | 0.6034 | 0.8533 |
117
- | 0.0945 | 48.0 | 876 | 0.6106 | 0.8494 |
118
- | 0.1159 | 48.99 | 894 | 0.6143 | 0.8533 |
119
- | 0.0963 | 49.32 | 900 | 0.6144 | 0.8533 |
120
 
121
 
122
  ### Framework versions
123
 
124
- - Transformers 4.37.2
125
  - Pytorch 2.1.0+cu121
126
  - Datasets 2.17.1
127
  - Tokenizers 0.15.2
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.8571428571428571
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
32
 
33
  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.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 0.4634
36
+ - Accuracy: 0.8571
37
 
38
  ## Model description
39
 
 
61
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
62
  - lr_scheduler_type: linear
63
  - lr_scheduler_warmup_ratio: 0.1
64
+ - num_epochs: 10
65
 
66
  ### Training results
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
+ | 2.0639 | 0.99 | 18 | 1.1575 | 0.6873 |
71
+ | 1.0962 | 1.97 | 36 | 0.8400 | 0.7336 |
72
+ | 0.8715 | 2.96 | 54 | 0.7163 | 0.7915 |
73
+ | 0.7241 | 4.0 | 73 | 0.6331 | 0.7992 |
74
+ | 0.6171 | 4.99 | 91 | 0.5140 | 0.8340 |
75
+ | 0.5467 | 5.97 | 109 | 0.4848 | 0.8610 |
76
+ | 0.518 | 6.96 | 127 | 0.4585 | 0.8456 |
77
+ | 0.4543 | 8.0 | 146 | 0.4549 | 0.8726 |
78
+ | 0.4378 | 8.99 | 164 | 0.4448 | 0.8571 |
79
+ | 0.431 | 9.86 | 180 | 0.4634 | 0.8571 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
80
 
81
 
82
  ### Framework versions
83
 
84
+ - Transformers 4.38.1
85
  - Pytorch 2.1.0+cu121
86
  - Datasets 2.17.1
87
  - Tokenizers 0.15.2
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a1ec44c4fa7297f17ce55cdd4306f58ed774e4a2bbf9f7221bd7ba3d47fa9f89
3
  size 110367448
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52712d8005b1ec7e23bbe740f3cb25d826aff2e1debf56131c7ce28832e28b9a
3
  size 110367448
runs/Mar01_04-04-16_a2ca3ccf826b/events.out.tfevents.1709266087.a2ca3ccf826b.460.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d613742da901c6b0a0058b4441b73a4d231d712c58a33f168bd21e126383dbd5
3
- size 9395
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7dc98c54360879ce216176228e76e09ce1f8e40862362ad51b9b426358f0c9c4
3
+ size 12715