Hugging Face's logo

mountaincreek12
/
swin-tiny-patch4-window7-224-finetuned-sealv1

Image Classification
Transformers
TensorBoard
Safetensors
swin
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
mountaincreek12 commited on
Commit
3879522
•
1 Parent(s): 2ae7651

Model save

Browse files
Files changed (2) hide show
  1. README.md +33 -14
  2. model.safetensors +1 -1
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.9119804400977995
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: 0.2553
36
- - Accuracy: 0.9120
37
 
38
  ## Model description
39
 
@@ -61,22 +61,41 @@ 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: 10
65
 
66
  ### Training results
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
- | 1.1068 | 0.95 | 14 | 0.6518 | 0.7066 |
71
- | 0.4912 | 1.97 | 29 | 0.4668 | 0.8435 |
72
- | 0.2749 | 2.98 | 44 | 0.4127 | 0.8704 |
73
- | 0.3189 | 4.0 | 59 | 0.3626 | 0.8875 |
74
- | 0.2226 | 4.95 | 73 | 0.2638 | 0.9046 |
75
- | 0.2394 | 5.97 | 88 | 0.3584 | 0.8802 |
76
- | 0.2241 | 6.98 | 103 | 0.2821 | 0.9046 |
77
- | 0.1815 | 8.0 | 118 | 0.2138 | 0.9218 |
78
- | 0.1862 | 8.95 | 132 | 0.2738 | 0.9046 |
79
- | 0.1942 | 9.49 | 140 | 0.2553 | 0.9120 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
80
 
81
 
82
  ### Framework versions
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.9793103448275862
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: 0.0650
36
+ - Accuracy: 0.9793
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
+ | No log | 0.95 | 5 | 1.2920 | 0.4966 |
71
+ | 1.1379 | 1.9 | 10 | 1.0177 | 0.4966 |
72
+ | 1.1379 | 2.86 | 15 | 0.7626 | 0.8759 |
73
+ | 0.6784 | 4.0 | 21 | 0.5388 | 0.9310 |
74
+ | 0.6784 | 4.95 | 26 | 0.4191 | 0.9103 |
75
+ | 0.3269 | 5.9 | 31 | 0.3990 | 0.8897 |
76
+ | 0.3269 | 6.86 | 36 | 0.2090 | 0.9517 |
77
+ | 0.2068 | 8.0 | 42 | 0.1819 | 0.9586 |
78
+ | 0.2068 | 8.95 | 47 | 0.1192 | 0.9655 |
79
+ | 0.1104 | 9.9 | 52 | 0.0682 | 0.9724 |
80
+ | 0.1104 | 10.86 | 57 | 0.0854 | 0.9724 |
81
+ | 0.0571 | 12.0 | 63 | 0.0816 | 0.9655 |
82
+ | 0.0571 | 12.95 | 68 | 0.0535 | 0.9793 |
83
+ | 0.0382 | 13.9 | 73 | 0.0491 | 0.9793 |
84
+ | 0.0382 | 14.86 | 78 | 0.0534 | 0.9793 |
85
+ | 0.0158 | 16.0 | 84 | 0.0369 | 0.9793 |
86
+ | 0.0158 | 16.95 | 89 | 0.1111 | 0.9724 |
87
+ | 0.0082 | 17.9 | 94 | 0.0515 | 0.9862 |
88
+ | 0.0082 | 18.86 | 99 | 0.0713 | 0.9793 |
89
+ | 0.0105 | 20.0 | 105 | 0.0598 | 0.9793 |
90
+ | 0.009 | 20.95 | 110 | 0.0759 | 0.9724 |
91
+ | 0.009 | 21.9 | 115 | 0.0769 | 0.9793 |
92
+ | 0.0134 | 22.86 | 120 | 0.0702 | 0.9793 |
93
+ | 0.0134 | 24.0 | 126 | 0.0605 | 0.9793 |
94
+ | 0.0042 | 24.95 | 131 | 0.0621 | 0.9793 |
95
+ | 0.0042 | 25.9 | 136 | 0.0654 | 0.9793 |
96
+ | 0.0027 | 26.86 | 141 | 0.0666 | 0.9724 |
97
+ | 0.0027 | 28.0 | 147 | 0.0665 | 0.9793 |
98
+ | 0.0065 | 28.57 | 150 | 0.0650 | 0.9793 |
99
 
100
 
101
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1b9684265d95fbfacd7ba04c5e1796ede05e2841cc2f411b7fb35257b57564b8
3
  size 110348984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:906024750d8d4fc61fb267c5ef650bafa6d3a7f15b568fc2f56be4112895decc
3
  size 110348984