Hugging Face's logo

marthakk
/
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
marthakk commited on
Commit
086dad7
•
1 Parent(s): 60c86f6

Model save

Browse files
Files changed (2) hide show
  1. README.md +19 -19
  2. model.safetensors +1 -1
README.md CHANGED
@@ -26,16 +26,16 @@ model-index:
26
  metrics:
27
  - name: Accuracy
28
  type: accuracy
29
- value: 0.8842443729903537
30
  - name: Precision
31
  type: precision
32
- value: 0.8965561746996403
33
  - name: Recall
34
  type: recall
35
- value: 0.8842443729903537
36
  - name: F1
37
  type: f1
38
- value: 0.8866264991906878
39
  ---
40
 
41
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -45,11 +45,11 @@ should probably proofread and complete it, then remove this comment. -->
45
 
46
  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.
47
  It achieves the following results on the evaluation set:
48
- - Loss: 0.2001
49
- - Accuracy: 0.8842
50
- - Precision: 0.8966
51
- - Recall: 0.8842
52
- - F1: 0.8866
53
 
54
  ## Model description
55
 
@@ -83,16 +83,16 @@ The following hyperparameters were used during training:
83
 
84
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
85
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
86
- | 0.2604 | 1.0 | 22 | 0.2334 | 0.8392 | 0.8375 | 0.8392 | 0.8333 |
87
- | 0.2492 | 2.0 | 44 | 0.2621 | 0.8264 | 0.8229 | 0.8264 | 0.8232 |
88
- | 0.2373 | 3.0 | 66 | 0.2334 | 0.8617 | 0.8639 | 0.8617 | 0.8626 |
89
- | 0.2623 | 4.0 | 88 | 0.2036 | 0.8810 | 0.8908 | 0.8810 | 0.8832 |
90
- | 0.2378 | 5.0 | 110 | 0.2944 | 0.8199 | 0.8165 | 0.8199 | 0.8173 |
91
- | 0.221 | 6.0 | 132 | 0.2027 | 0.8682 | 0.8752 | 0.8682 | 0.8701 |
92
- | 0.2339 | 7.0 | 154 | 0.2291 | 0.8585 | 0.8573 | 0.8585 | 0.8577 |
93
- | 0.2215 | 8.0 | 176 | 0.2732 | 0.8682 | 0.8685 | 0.8682 | 0.8683 |
94
- | 0.2162 | 9.0 | 198 | 0.2260 | 0.8682 | 0.8713 | 0.8682 | 0.8693 |
95
- | 0.2226 | 10.0 | 220 | 0.2001 | 0.8842 | 0.8966 | 0.8842 | 0.8866 |
96
 
97
 
98
  ### Framework versions
 
26
  metrics:
27
  - name: Accuracy
28
  type: accuracy
29
+ value: 0.842443729903537
30
  - name: Precision
31
  type: precision
32
+ value: 0.8395802314162165
33
  - name: Recall
34
  type: recall
35
+ value: 0.842443729903537
36
  - name: F1
37
  type: f1
38
+ value: 0.8393214641540072
39
  ---
40
 
41
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
45
 
46
  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.
47
  It achieves the following results on the evaluation set:
48
+ - Loss: 0.2213
49
+ - Accuracy: 0.8424
50
+ - Precision: 0.8396
51
+ - Recall: 0.8424
52
+ - F1: 0.8393
53
 
54
  ## Model description
55
 
 
83
 
84
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
85
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
86
+ | 0.5793 | 1.0 | 22 | 0.5874 | 0.6785 | 0.4603 | 0.6785 | 0.5485 |
87
+ | 0.3711 | 2.0 | 44 | 0.4135 | 0.7781 | 0.8169 | 0.7781 | 0.7395 |
88
+ | 0.2961 | 3.0 | 66 | 0.2816 | 0.8553 | 0.8676 | 0.8553 | 0.8582 |
89
+ | 0.2576 | 4.0 | 88 | 0.2899 | 0.7942 | 0.7884 | 0.7942 | 0.7857 |
90
+ | 0.261 | 5.0 | 110 | 0.2469 | 0.8103 | 0.8057 | 0.8103 | 0.8037 |
91
+ | 0.2559 | 6.0 | 132 | 0.2548 | 0.8360 | 0.8632 | 0.8360 | 0.8179 |
92
+ | 0.2249 | 7.0 | 154 | 0.2835 | 0.8135 | 0.8479 | 0.8135 | 0.7882 |
93
+ | 0.2242 | 8.0 | 176 | 0.2335 | 0.8296 | 0.8261 | 0.8296 | 0.8262 |
94
+ | 0.2215 | 9.0 | 198 | 0.2293 | 0.8521 | 0.8549 | 0.8521 | 0.8532 |
95
+ | 0.2269 | 10.0 | 220 | 0.2213 | 0.8424 | 0.8396 | 0.8424 | 0.8393 |
96
 
97
 
98
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b65fb0d0cdba542f99225fc328048e90f53e195487d02c4224f4b613d9eedbee
3
  size 110342832
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77587557ee68e3cd14e83b3fa6463430d8a00b2e501c44984caa077f6d42cab7
3
  size 110342832