Hugging Face's logo

onizukal
/
Boya2_SGD_1e3_20Epoch_Swin-large-224_fold1

PyTorch
swin
Generated from Trainer
Eval Results
Model card Files Community
onizukal commited on
Commit
aa5261d
•
1 Parent(s): 2898ff6

End of training

Browse files
Files changed (2) hide show
  1. README.md +25 -25
  2. pytorch_model.bin +1 -1
README.md CHANGED
@@ -1,6 +1,6 @@
1
  ---
2
  license: apache-2.0
3
- base_model: microsoft/swin-large-patch4-window7-224-in22k
4
  tags:
5
  - generated_from_trainer
6
  datasets:
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.43978052126200273
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -30,10 +30,10 @@ should probably proofread and complete it, then remove this comment. -->
30
 
31
  # Boya2_SGD_1e3_20Epoch_Swin-large-224_fold1
32
 
33
- This model is a fine-tuned version of [microsoft/swin-large-patch4-window7-224-in22k](https://huggingface.co/microsoft/swin-large-patch4-window7-224-in22k) on the imagefolder dataset.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 1.7177
36
- - Accuracy: 0.4398
37
 
38
  ## Model description
39
 
@@ -65,26 +65,26 @@ The following hyperparameters were used during training:
65
 
66
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
67
  |:-------------:|:-----:|:-----:|:---------------:|:--------:|
68
- | 2.5254 | 1.0 | 914 | 2.5193 | 0.2337 |
69
- | 2.2335 | 2.0 | 1828 | 2.2973 | 0.2768 |
70
- | 2.1501 | 3.0 | 2742 | 2.1851 | 0.2985 |
71
- | 2.0837 | 4.0 | 3656 | 2.0892 | 0.3210 |
72
- | 2.023 | 5.0 | 4570 | 2.0285 | 0.3427 |
73
- | 2.1197 | 6.0 | 5484 | 1.9778 | 0.3567 |
74
- | 1.8735 | 7.0 | 6398 | 1.9315 | 0.3712 |
75
- | 1.9425 | 8.0 | 7312 | 1.8942 | 0.3855 |
76
- | 1.7959 | 9.0 | 8226 | 1.8616 | 0.3975 |
77
- | 1.8811 | 10.0 | 9140 | 1.8352 | 0.4102 |
78
- | 1.7687 | 11.0 | 10054 | 1.8101 | 0.4129 |
79
- | 1.745 | 12.0 | 10968 | 1.7884 | 0.4184 |
80
- | 1.6926 | 13.0 | 11882 | 1.7712 | 0.4241 |
81
- | 1.8703 | 14.0 | 12796 | 1.7556 | 0.4285 |
82
- | 1.799 | 15.0 | 13710 | 1.7425 | 0.4321 |
83
- | 1.7167 | 16.0 | 14624 | 1.7343 | 0.4337 |
84
- | 1.8017 | 17.0 | 15538 | 1.7266 | 0.4362 |
85
- | 1.7314 | 18.0 | 16452 | 1.7220 | 0.4387 |
86
- | 1.8866 | 19.0 | 17366 | 1.7190 | 0.4398 |
87
- | 1.8724 | 20.0 | 18280 | 1.7177 | 0.4398 |
88
 
89
 
90
  ### Framework versions
 
1
  ---
2
  license: apache-2.0
3
+ base_model: microsoft/swin-large-patch4-window12-384
4
  tags:
5
  - generated_from_trainer
6
  datasets:
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.47160493827160493
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
30
 
31
  # Boya2_SGD_1e3_20Epoch_Swin-large-224_fold1
32
 
33
+ This model is a fine-tuned version of [microsoft/swin-large-patch4-window12-384](https://huggingface.co/microsoft/swin-large-patch4-window12-384) on the imagefolder dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 1.6332
36
+ - Accuracy: 0.4716
37
 
38
  ## Model description
39
 
 
65
 
66
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
67
  |:-------------:|:-----:|:-----:|:---------------:|:--------:|
68
+ | 2.4897 | 1.0 | 914 | 2.4409 | 0.2804 |
69
+ | 2.1506 | 2.0 | 1828 | 2.2233 | 0.2968 |
70
+ | 2.0176 | 3.0 | 2742 | 2.1001 | 0.3311 |
71
+ | 1.9799 | 4.0 | 3656 | 2.0112 | 0.3564 |
72
+ | 1.9403 | 5.0 | 4570 | 1.9459 | 0.3786 |
73
+ | 1.9907 | 6.0 | 5484 | 1.8909 | 0.4003 |
74
+ | 1.7985 | 7.0 | 6398 | 1.8449 | 0.4159 |
75
+ | 1.8712 | 8.0 | 7312 | 1.8057 | 0.4239 |
76
+ | 1.7195 | 9.0 | 8226 | 1.7733 | 0.4348 |
77
+ | 1.8526 | 10.0 | 9140 | 1.7458 | 0.4436 |
78
+ | 1.67 | 11.0 | 10054 | 1.7203 | 0.4488 |
79
+ | 1.6061 | 12.0 | 10968 | 1.7023 | 0.4549 |
80
+ | 1.6256 | 13.0 | 11882 | 1.6832 | 0.4582 |
81
+ | 1.8212 | 14.0 | 12796 | 1.6685 | 0.4634 |
82
+ | 1.7157 | 15.0 | 13710 | 1.6584 | 0.4639 |
83
+ | 1.6148 | 16.0 | 14624 | 1.6491 | 0.4661 |
84
+ | 1.7158 | 17.0 | 15538 | 1.6424 | 0.4675 |
85
+ | 1.7391 | 18.0 | 16452 | 1.6370 | 0.4689 |
86
+ | 1.8077 | 19.0 | 17366 | 1.6337 | 0.4716 |
87
+ | 1.7769 | 20.0 | 18280 | 1.6332 | 0.4716 |
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:cab11382f74df548a2013fa3f0f0f68374fbba70d161dc6c974c72df92ce551f
3
  size 785043790
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c2d3b899769fc778de6931cb95852c1abcb8121cbfba95ff41fdb72c661209d
3
  size 785043790