Hugging Face's logo

impcabbie
/
swin-tiny-patch4-window7-224-finetuned-eurosat

Image Classification
Transformers
PyTorch
TensorBoard
Safetensors
swin
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
impcabbie commited on
Commit
eef7315
•
1 Parent(s): 35bb8fe

Model save

Browse files
Files changed (2) hide show
  1. README.md +12 -7
  2. pytorch_model.bin +1 -1
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.35294117647058826
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: 1.0718
36
- - Accuracy: 0.3529
37
 
38
  ## Model description
39
 
@@ -61,15 +61,20 @@ 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: 3
65
 
66
  ### Training results
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
- | No log | 0.8 | 3 | 1.0966 | 0.2941 |
71
- | No log | 1.87 | 7 | 1.0756 | 0.3529 |
72
- | No log | 2.4 | 9 | 1.0718 | 0.3529 |
 
 
 
 
 
73
 
74
 
75
  ### Framework versions
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.6274509803921569
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: 0.8015
36
+ - Accuracy: 0.6275
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: 10
65
 
66
  ### Training results
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
+ | No log | 0.8 | 3 | 1.0688 | 0.5490 |
71
+ | No log | 1.87 | 7 | 0.9906 | 0.5882 |
72
+ | 1.0511 | 2.93 | 11 | 0.9322 | 0.6275 |
73
+ | 1.0511 | 4.0 | 15 | 0.8665 | 0.6667 |
74
+ | 1.0511 | 4.8 | 18 | 0.8342 | 0.6275 |
75
+ | 0.8781 | 5.87 | 22 | 0.8201 | 0.6471 |
76
+ | 0.8781 | 6.93 | 26 | 0.8070 | 0.6471 |
77
+ | 0.7623 | 8.0 | 30 | 0.8015 | 0.6275 |
78
 
79
 
80
  ### Framework versions
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f2f87424a8f0508ae67adbcd9cdb502e5b263f60f44187d1990d84c9d9134b01
3
  size 110397937
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:551d1bdb0e9ea1e87e437ec74e9b435f70538f93be8bb4ca1e628486fe3d85a1
3
  size 110397937