Hugging Face's logo

andrecastro
/
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
andrecastro commited on
Commit
bfa38c1
•
1 Parent(s): 15da652

Model save

Browse files
Files changed (2) hide show
  1. README.md +21 -18
  2. model.safetensors +1 -1
README.md CHANGED
@@ -7,8 +7,6 @@ datasets:
7
  - imagefolder
8
  metrics:
9
  - accuracy
10
- - precision
11
- - recall
12
  model-index:
13
  - name: swin-tiny-patch4-window7-224-finetuned-eurosat
14
  results:
@@ -24,13 +22,7 @@ model-index:
24
  metrics:
25
  - name: Accuracy
26
  type: accuracy
27
- value: 0.9872952189903043
28
- - name: Precision
29
- type: precision
30
- value: 0.9873025359218194
31
- - name: Recall
32
- type: recall
33
- value: 0.9872952189903043
34
  ---
35
 
36
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -40,11 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
40
 
41
  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.
42
  It achieves the following results on the evaluation set:
43
- - Loss: 0.0325
44
- - Accuracy: 0.9873
45
- - Precision: 0.9873
46
- - Recall: 0.9873
47
- - Confusion Matrix: [[1495, 16], [22, 1458]]
48
 
49
  ## Model description
50
 
@@ -72,13 +61,27 @@ The following hyperparameters were used during training:
72
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
73
  - lr_scheduler_type: linear
74
  - lr_scheduler_warmup_ratio: 0.1
75
- - num_epochs: 1
76
 
77
  ### Training results
78
 
79
- | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | Confusion Matrix |
80
- |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------------------------:|
81
- | 0.0786 | 1.0 | 374 | 0.0325 | 0.9873 | 0.9873 | 0.9873 | [[1495, 16], [22, 1458]] |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
82
 
83
 
84
  ### Framework versions
 
7
  - imagefolder
8
  metrics:
9
  - accuracy
 
 
10
  model-index:
11
  - name: swin-tiny-patch4-window7-224-finetuned-eurosat
12
  results:
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.9913101604278075
 
 
 
 
 
 
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: 0.0352
36
+ - Accuracy: 0.9913
 
 
 
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: 15
65
 
66
  ### Training results
67
 
68
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
+ | 0.2379 | 1.0 | 327 | 0.1448 | 0.9436 |
71
+ | 0.1352 | 2.0 | 654 | 0.0955 | 0.9643 |
72
+ | 0.1388 | 3.0 | 981 | 0.1047 | 0.9648 |
73
+ | 0.1045 | 4.0 | 1309 | 0.0740 | 0.9762 |
74
+ | 0.144 | 5.0 | 1636 | 0.0479 | 0.9835 |
75
+ | 0.0888 | 6.0 | 1963 | 0.0358 | 0.9871 |
76
+ | 0.0893 | 7.0 | 2290 | 0.0542 | 0.9820 |
77
+ | 0.0743 | 8.0 | 2618 | 0.0536 | 0.9846 |
78
+ | 0.0532 | 9.0 | 2945 | 0.0654 | 0.9813 |
79
+ | 0.0358 | 10.0 | 3272 | 0.0507 | 0.9882 |
80
+ | 0.0257 | 11.0 | 3599 | 0.0287 | 0.9906 |
81
+ | 0.0118 | 12.0 | 3927 | 0.0355 | 0.9904 |
82
+ | 0.0274 | 13.0 | 4254 | 0.0275 | 0.9918 |
83
+ | 0.0442 | 14.0 | 4581 | 0.0321 | 0.9915 |
84
+ | 0.019 | 14.99 | 4905 | 0.0352 | 0.9913 |
85
 
86
 
87
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5a0bf9b28b4fe7b495349f3f36a3f91c65f4d6de08d0959fcb0fa5de8c266f3b
3
  size 110342832
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5c2ab51a6d7888add1662daf12bc845418fa69d8fa7fd1849e81b5a85fbcf49
3
  size 110342832