Hugging Face's logo

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

Image Classification
Transformers
TensorBoard
Safetensors
swin
Generated from Trainer
Eval Results
Model card Files Metrics Community
jjsprockel commited on
Commit
0d68550
·
verified ·
1 Parent(s): 9e0cdb8

Model save

Browse files
Files changed (3) hide show
  1. README.md +12 -7
  2. model.safetensors +1 -1
  3. runs/Feb16_01-15-25_96b03e1b8eae/events.out.tfevents.1739668557.96b03e1b8eae.369.0 +2 -2
README.md CHANGED
@@ -23,7 +23,7 @@ model-index:
23
  metrics:
24
  - name: Accuracy
25
  type: accuracy
26
- value: 0.5964912280701754
27
  ---
28
 
29
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -33,8 +33,8 @@ should probably proofread and complete it, then remove this comment. -->
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: 0.6910
37
- - Accuracy: 0.5965
38
 
39
  ## Model description
40
 
@@ -62,15 +62,20 @@ The following hyperparameters were used during training:
62
  - optimizer: Use OptimizerNames.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: 3
66
 
67
  ### Training results
68
 
69
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
70
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
71
- | No log | 1.0 | 4 | 0.6872 | 0.5614 |
72
- | No log | 2.0 | 8 | 0.7022 | 0.5263 |
73
- | 0.6634 | 3.0 | 12 | 0.6910 | 0.5965 |
 
 
 
 
 
74
 
75
 
76
  ### Framework versions
 
23
  metrics:
24
  - name: Accuracy
25
  type: accuracy
26
+ value: 0.5614035087719298
27
  ---
28
 
29
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
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: 0.6599
37
+ - Accuracy: 0.5614
38
 
39
  ## Model description
40
 
 
62
  - optimizer: Use OptimizerNames.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: 8
66
 
67
  ### Training results
68
 
69
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
70
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
71
+ | No log | 1.0 | 4 | 0.6771 | 0.5789 |
72
+ | No log | 2.0 | 8 | 0.6415 | 0.6140 |
73
+ | 0.6754 | 3.0 | 12 | 0.6351 | 0.6667 |
74
+ | 0.6754 | 4.0 | 16 | 0.6629 | 0.5614 |
75
+ | 0.6122 | 5.0 | 20 | 0.6631 | 0.5789 |
76
+ | 0.6122 | 6.0 | 24 | 0.6529 | 0.5789 |
77
+ | 0.6122 | 7.0 | 28 | 0.6541 | 0.5614 |
78
+ | 0.5894 | 8.0 | 32 | 0.6599 | 0.5614 |
79
 
80
 
81
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1629c9bade3d803440a7399d31508f4704618bf7a83035c7dfa697976fce9c35
3
  size 110342832
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a48645b524dec5d9589099c96f6de92181c6bca15c7cc45dfd3be6c8401f111
3
  size 110342832
runs/Feb16_01-15-25_96b03e1b8eae/events.out.tfevents.1739668557.96b03e1b8eae.369.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0be0538fc0e830655b02e380ca6d6897c5b1d7590cbda19f536af36fdd8095b9
3
- size 8354
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:498e50e5882380738df91031198101fc4d83e5d133c0980cac2f6129555fb633
3
+ size 9019