Hugging Face's logo

Shk4
/
vit_ana_0.89

Image Classification
Transformers
TensorBoard
Safetensors
swin
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
Shk4 commited on
Commit
3b6f8c2
·
verified ·
1 Parent(s): 9d181b8

Model save

Browse files
Files changed (3) hide show
  1. README.md +36 -13
  2. model.safetensors +1 -1
  3. runs/Dec15_10-24-13_8e47523e7715/events.out.tfevents.1734258255.8e47523e7715.23.0 +2 -2
README.md CHANGED
@@ -1,7 +1,7 @@
1
  ---
2
  library_name: transformers
3
  license: apache-2.0
4
- base_model: Shk4/swin-tiny-patch4-window7-224-finetuned-eurosat
5
  tags:
6
  - generated_from_trainer
7
  datasets:
@@ -23,7 +23,7 @@ model-index:
23
  metrics:
24
  - name: Accuracy
25
  type: accuracy
26
- value: 0.8111111111111111
27
  ---
28
 
29
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -31,10 +31,10 @@ should probably proofread and complete it, then remove this comment. -->
31
 
32
  # swin-tiny-patch4-window7-224-finetuned-eurosat
33
 
34
- This model is a fine-tuned version of [Shk4/swin-tiny-patch4-window7-224-finetuned-eurosat](https://huggingface.co/Shk4/swin-tiny-patch4-window7-224-finetuned-eurosat) on the imagefolder dataset.
35
  It achieves the following results on the evaluation set:
36
- - Loss: 0.4766
37
- - Accuracy: 0.8111
38
 
39
  ## Model description
40
 
@@ -62,17 +62,40 @@ The following hyperparameters were used during training:
62
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
63
  - lr_scheduler_type: linear
64
  - lr_scheduler_warmup_ratio: 0.1
65
- - num_epochs: 5
66
 
67
  ### Training results
68
 
69
- | Training Loss | Epoch | Step | Validation Loss | Accuracy |
70
- |:-------------:|:------:|:----:|:---------------:|:--------:|
71
- | No log | 0.9231 | 3 | 0.6451 | 0.6889 |
72
- | No log | 1.8462 | 6 | 0.5572 | 0.6444 |
73
- | No log | 2.7692 | 9 | 0.4766 | 0.8111 |
74
- | 0.6714 | 4.0 | 13 | 0.4629 | 0.6444 |
75
- | 0.6714 | 4.6154 | 15 | 0.4618 | 0.6444 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
 
77
 
78
  ### Framework versions
 
1
  ---
2
  library_name: transformers
3
  license: apache-2.0
4
+ base_model: microsoft/swin-tiny-patch4-window7-224
5
  tags:
6
  - generated_from_trainer
7
  datasets:
 
23
  metrics:
24
  - name: Accuracy
25
  type: accuracy
26
+ value: 0.8764044943820225
27
  ---
28
 
29
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
31
 
32
  # swin-tiny-patch4-window7-224-finetuned-eurosat
33
 
34
+ 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.
35
  It achieves the following results on the evaluation set:
36
+ - Loss: 0.3101
37
+ - Accuracy: 0.8764
38
 
39
  ## Model description
40
 
 
62
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
63
  - lr_scheduler_type: linear
64
  - lr_scheduler_warmup_ratio: 0.1
65
+ - num_epochs: 30
66
 
67
  ### Training results
68
 
69
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
70
+ |:-------------:|:-------:|:----:|:---------------:|:--------:|
71
+ | No log | 0.9231 | 3 | 1.8889 | 0.2472 |
72
+ | No log | 1.8462 | 6 | 1.7625 | 0.3820 |
73
+ | No log | 2.7692 | 9 | 1.5603 | 0.4494 |
74
+ | 1.7854 | 4.0 | 13 | 1.3005 | 0.5281 |
75
+ | 1.7854 | 4.9231 | 16 | 1.0408 | 0.6292 |
76
+ | 1.7854 | 5.8462 | 19 | 0.8925 | 0.6854 |
77
+ | 1.1431 | 6.7692 | 22 | 0.7614 | 0.7303 |
78
+ | 1.1431 | 8.0 | 26 | 0.6343 | 0.7753 |
79
+ | 1.1431 | 8.9231 | 29 | 0.5810 | 0.7978 |
80
+ | 0.7715 | 9.8462 | 32 | 0.5551 | 0.8427 |
81
+ | 0.7715 | 10.7692 | 35 | 0.5209 | 0.8539 |
82
+ | 0.7715 | 12.0 | 39 | 0.5690 | 0.8202 |
83
+ | 0.5645 | 12.9231 | 42 | 0.4431 | 0.8876 |
84
+ | 0.5645 | 13.8462 | 45 | 0.4922 | 0.8202 |
85
+ | 0.5645 | 14.7692 | 48 | 0.4914 | 0.8315 |
86
+ | 0.4999 | 16.0 | 52 | 0.3768 | 0.8989 |
87
+ | 0.4999 | 16.9231 | 55 | 0.4292 | 0.8539 |
88
+ | 0.4999 | 17.8462 | 58 | 0.3846 | 0.8652 |
89
+ | 0.4555 | 18.7692 | 61 | 0.3498 | 0.8876 |
90
+ | 0.4555 | 20.0 | 65 | 0.3523 | 0.8652 |
91
+ | 0.4555 | 20.9231 | 68 | 0.3541 | 0.8876 |
92
+ | 0.3941 | 21.8462 | 71 | 0.3240 | 0.8989 |
93
+ | 0.3941 | 22.7692 | 74 | 0.3169 | 0.8989 |
94
+ | 0.3941 | 24.0 | 78 | 0.3317 | 0.8764 |
95
+ | 0.361 | 24.9231 | 81 | 0.3251 | 0.8876 |
96
+ | 0.361 | 25.8462 | 84 | 0.3198 | 0.8764 |
97
+ | 0.361 | 26.7692 | 87 | 0.3117 | 0.8764 |
98
+ | 0.3485 | 27.6923 | 90 | 0.3101 | 0.8764 |
99
 
100
 
101
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e0600b1f02eb8688777a6969479bbd6aebd8559f52b5e9c583c40f06426c994a
3
  size 110358212
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52da0dfb81e33f7918223b0e73ad89d4d955d2a528ff86c26bcca36bfc14991f
3
  size 110358212
runs/Dec15_10-24-13_8e47523e7715/events.out.tfevents.1734258255.8e47523e7715.23.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:24ef610554376c76ea9f0193c4fda9954283bc18a37a8e513956c2d8b0213bcc
3
- size 15973
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e81d5d56f98bd9c7d5cc6ffbed3ac040fbc29c9694eb8b98f95af8f557f54b97
3
+ size 16845