Hugging Face's logo

0xhzx
/
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
0xhzx commited on
Commit
14a9747
•
1 Parent(s): 6238084

Model save

Browse files
Files changed (3) hide show
  1. README.md +34 -7
  2. model.safetensors +1 -1
  3. runs/Feb12_00-29-37_3621747748f3/events.out.tfevents.1707697784.3621747748f3.6471.2 +2 -2
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.8295454545454546
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: 0.4648
36
- - Accuracy: 0.8295
37
 
38
  ## Model description
39
 
@@ -61,15 +61,42 @@ 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: 3
65
 
66
  ### Training results
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
- | 0.6107 | 0.99 | 43 | 0.5792 | 0.7808 |
71
- | 0.4367 | 2.0 | 87 | 0.4921 | 0.8247 |
72
- | 0.4166 | 2.97 | 129 | 0.4648 | 0.8295 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
73
 
74
 
75
  ### Framework versions
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.9366883116883117
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: 0.2525
36
+ - Accuracy: 0.9367
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: 30
65
 
66
  ### Training results
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
+ | 0.9843 | 0.99 | 43 | 0.8500 | 0.6948 |
71
+ | 0.5335 | 2.0 | 87 | 0.5584 | 0.7825 |
72
+ | 0.4263 | 2.99 | 130 | 0.4791 | 0.8117 |
73
+ | 0.3308 | 4.0 | 174 | 0.4269 | 0.8344 |
74
+ | 0.2882 | 4.99 | 217 | 0.3567 | 0.8636 |
75
+ | 0.2517 | 6.0 | 261 | 0.3317 | 0.8701 |
76
+ | 0.1908 | 6.99 | 304 | 0.3082 | 0.8815 |
77
+ | 0.187 | 8.0 | 348 | 0.3230 | 0.8799 |
78
+ | 0.1434 | 8.99 | 391 | 0.3323 | 0.9010 |
79
+ | 0.1277 | 10.0 | 435 | 0.2489 | 0.9075 |
80
+ | 0.156 | 10.99 | 478 | 0.3246 | 0.8880 |
81
+ | 0.0781 | 12.0 | 522 | 0.3121 | 0.9010 |
82
+ | 0.1001 | 12.99 | 565 | 0.2708 | 0.9058 |
83
+ | 0.0892 | 14.0 | 609 | 0.2582 | 0.9140 |
84
+ | 0.0644 | 14.99 | 652 | 0.2486 | 0.9221 |
85
+ | 0.0689 | 16.0 | 696 | 0.2465 | 0.9237 |
86
+ | 0.0547 | 16.99 | 739 | 0.2402 | 0.9334 |
87
+ | 0.0597 | 18.0 | 783 | 0.2534 | 0.9237 |
88
+ | 0.0512 | 18.99 | 826 | 0.2400 | 0.9318 |
89
+ | 0.041 | 20.0 | 870 | 0.2397 | 0.9286 |
90
+ | 0.0376 | 20.99 | 913 | 0.2663 | 0.9269 |
91
+ | 0.0412 | 22.0 | 957 | 0.3026 | 0.9221 |
92
+ | 0.0423 | 22.99 | 1000 | 0.2678 | 0.9302 |
93
+ | 0.0266 | 24.0 | 1044 | 0.2510 | 0.9318 |
94
+ | 0.0313 | 24.99 | 1087 | 0.2542 | 0.9334 |
95
+ | 0.0207 | 26.0 | 1131 | 0.2743 | 0.9334 |
96
+ | 0.0292 | 26.99 | 1174 | 0.2614 | 0.9318 |
97
+ | 0.0242 | 28.0 | 1218 | 0.2469 | 0.9383 |
98
+ | 0.0201 | 28.99 | 1261 | 0.2534 | 0.9367 |
99
+ | 0.0354 | 29.66 | 1290 | 0.2525 | 0.9367 |
100
 
101
 
102
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3c7eaf932ee9f52ce970b3d26b126c5145e2fdf558a207429b5bc1639fae925d
3
  size 110358212
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3272f0dd25f922f0c779093579f998bfac8c81e07b2f133abeeb8e99e093a96
3
  size 110358212
runs/Feb12_00-29-37_3621747748f3/events.out.tfevents.1707697784.3621747748f3.6471.2 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f9528f6abf80367ffab70ccd15e8fd81f247c498734489dd2d85189f7ca1dabb
3
- size 34823
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:613d5030d2cdf6b4b48e5a87ee64192ffeeb47e38b859538b9ce8487697b4f65
3
+ size 35177