Hugging Face's logo

HorcruxNo13
/
swin-tiny-patch4-window7-224

Image Classification
Transformers
PyTorch
swin
Generated from Trainer
Eval Results (legacy)
Model card Files
xet
Community
1
HorcruxNo13 commited on
Commit
5215552
·
1 Parent(s): 7b6592f

Model save

Browse files
Files changed (2) hide show
  1. README.md +15 -15
  2. pytorch_model.bin +1 -1
README.md CHANGED
@@ -24,13 +24,13 @@ model-index:
24
  metrics:
25
  - name: Accuracy
26
  type: accuracy
27
- value: 0.7466666666666667
28
  - name: Precision
29
  type: precision
30
- value: 0.7167033192888707
31
  - name: Recall
32
  type: recall
33
- value: 0.7466666666666667
34
  ---
35
 
36
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -40,11 +40,11 @@ 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: 0.6199
44
- - Accuracy: 0.7467
45
- - Precision: 0.7167
46
- - Recall: 0.7467
47
- - F1 Score: 0.7110
48
 
49
  ## Model description
50
 
@@ -78,13 +78,13 @@ The following hyperparameters were used during training:
78
 
79
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 Score |
80
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:--------:|
81
- | No log | 1.0 | 8 | 0.5333 | 0.7583 | 0.7348 | 0.7583 | 0.7122 |
82
- | 0.4735 | 2.0 | 16 | 0.5572 | 0.7708 | 0.7878 | 0.7708 | 0.7094 |
83
- | 0.4492 | 3.0 | 24 | 0.5569 | 0.775 | 0.7830 | 0.775 | 0.7210 |
84
- | 0.3847 | 4.0 | 32 | 0.6170 | 0.7625 | 0.7640 | 0.7625 | 0.6989 |
85
- | 0.337 | 5.0 | 40 | 0.5983 | 0.7625 | 0.7417 | 0.7625 | 0.7189 |
86
- | 0.337 | 6.0 | 48 | 0.5763 | 0.7708 | 0.7507 | 0.7708 | 0.7435 |
87
- | 0.3118 | 7.0 | 56 | 0.6043 | 0.7792 | 0.7661 | 0.7792 | 0.7448 |
88
 
89
 
90
  ### Framework versions
 
24
  metrics:
25
  - name: Accuracy
26
  type: accuracy
27
+ value: 0.7366666666666667
28
  - name: Precision
29
  type: precision
30
+ value: 0.8064765100671142
31
  - name: Recall
32
  type: recall
33
+ value: 0.7366666666666667
34
  ---
35
 
36
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
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: 0.5487
44
+ - Accuracy: 0.7367
45
+ - Precision: 0.8065
46
+ - Recall: 0.7367
47
+ - F1 Score: 0.6315
48
 
49
  ## Model description
50
 
 
78
 
79
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 Score |
80
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:--------:|
81
+ | No log | 1.0 | 8 | 0.5835 | 0.7333 | 0.5378 | 0.7333 | 0.6205 |
82
+ | 0.6395 | 2.0 | 16 | 0.5736 | 0.7333 | 0.5378 | 0.7333 | 0.6205 |
83
+ | 0.5789 | 3.0 | 24 | 0.5943 | 0.7333 | 0.5378 | 0.7333 | 0.6205 |
84
+ | 0.5887 | 4.0 | 32 | 0.5613 | 0.7333 | 0.5378 | 0.7333 | 0.6205 |
85
+ | 0.5791 | 5.0 | 40 | 0.5557 | 0.7333 | 0.5378 | 0.7333 | 0.6205 |
86
+ | 0.5791 | 6.0 | 48 | 0.5535 | 0.7417 | 0.8090 | 0.7417 | 0.6397 |
87
+ | 0.5717 | 7.0 | 56 | 0.5456 | 0.7333 | 0.5378 | 0.7333 | 0.6205 |
88
 
89
 
90
  ### Framework versions
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1abfb089627e250568f523144d54e6f96f58ca4da63793134788a6b3f7abbe78
3
  size 110394865
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3767eccbee6326874ee4ee31faf86b112c49f69226fb388dad681c5c9a0ad176
3
  size 110394865