Hugging Face's logo

karoladelk
/
swin-tiny-patch4-window7-224-classification

Image Classification
Transformers
TensorBoard
Safetensors
swin
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
karoladelk commited on
Commit
5cf2b02
•
1 Parent(s): 47b2fd8

Model save

Browse files
Files changed (2) hide show
  1. README.md +18 -13
  2. model.safetensors +1 -1
README.md CHANGED
@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  This model is a fine-tuned version of [microsoft/swin-tiny-patch4-window7-224](https://huggingface.co/microsoft/swin-tiny-patch4-window7-224) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 0.2736
21
- - Accuracy: 0.9162
22
 
23
  ## Model description
24
 
@@ -46,22 +46,27 @@ The following hyperparameters were used during training:
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
  - lr_scheduler_type: linear
48
  - lr_scheduler_warmup_ratio: 0.1
49
- - num_epochs: 10
50
 
51
  ### Training results
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
54
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
55
- | 0.3193 | 1.0 | 100 | 0.3754 | 0.8717 |
56
- | 0.292 | 2.0 | 200 | 0.4086 | 0.8647 |
57
- | 0.2531 | 2.99 | 300 | 0.3407 | 0.8941 |
58
- | 0.2242 | 4.0 | 401 | 0.3317 | 0.8927 |
59
- | 0.2181 | 5.0 | 501 | 0.3073 | 0.8983 |
60
- | 0.1829 | 6.0 | 601 | 0.3104 | 0.9032 |
61
- | 0.1426 | 6.99 | 701 | 0.2976 | 0.9050 |
62
- | 0.1472 | 8.0 | 802 | 0.2736 | 0.9162 |
63
- | 0.1314 | 9.0 | 902 | 0.2800 | 0.9134 |
64
- | 0.1139 | 9.98 | 1000 | 0.2748 | 0.9148 |
 
 
 
 
 
65
 
66
 
67
  ### Framework versions
 
17
 
18
  This model is a fine-tuned version of [microsoft/swin-tiny-patch4-window7-224](https://huggingface.co/microsoft/swin-tiny-patch4-window7-224) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.2780
21
+ - Accuracy: 0.9264
22
 
23
  ## Model description
24
 
 
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
  - lr_scheduler_type: linear
48
  - lr_scheduler_warmup_ratio: 0.1
49
+ - num_epochs: 15
50
 
51
  ### Training results
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
54
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
55
+ | 0.1469 | 1.0 | 100 | 0.3027 | 0.9127 |
56
+ | 0.1677 | 2.0 | 200 | 0.3351 | 0.9001 |
57
+ | 0.167 | 2.99 | 300 | 0.3875 | 0.8931 |
58
+ | 0.1556 | 4.0 | 401 | 0.3814 | 0.8969 |
59
+ | 0.1328 | 5.0 | 501 | 0.3281 | 0.9046 |
60
+ | 0.1 | 6.0 | 601 | 0.3726 | 0.9004 |
61
+ | 0.1188 | 6.99 | 701 | 0.3736 | 0.9046 |
62
+ | 0.1257 | 8.0 | 802 | 0.3381 | 0.9102 |
63
+ | 0.1017 | 9.0 | 902 | 0.2872 | 0.9215 |
64
+ | 0.0987 | 10.0 | 1002 | 0.3067 | 0.9176 |
65
+ | 0.0874 | 10.99 | 1102 | 0.2919 | 0.9165 |
66
+ | 0.0901 | 12.0 | 1203 | 0.2942 | 0.9229 |
67
+ | 0.0831 | 13.0 | 1303 | 0.2974 | 0.9232 |
68
+ | 0.0838 | 14.0 | 1403 | 0.2787 | 0.9264 |
69
+ | 0.0603 | 14.96 | 1500 | 0.2780 | 0.9264 |
70
 
71
 
72
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:943a38513ac27f396d14b2cb0d423665811539b6c71774bf7642eb0d02f81daa
3
  size 110361288
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f455ad5816dcf601627921a16755a167d7a507c3d39694f988141dd5f9aac6d2
3
  size 110361288