vlevi
/

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

Image Classification

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

vlevi commited on Apr 6

Commit

b451aa0

•

1 Parent(s): 31dc926

Model save

Files changed (1) hide show

README.md +16 -7

README.md CHANGED Viewed

@@ -22,7 +22,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.5359712230215827
 ---
 <!-- 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. -->
 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.
 It achieves the following results on the evaluation set:
-- Loss: 0.9638
-- Accuracy: 0.5360
 ## Model description
@@ -61,15 +61,24 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1
-- num_epochs: 3
 ### Training results
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 1.0905        | 0.96  | 19   | 1.0363          | 0.4388   |
-| 0.9897        | 1.97  | 39   | 0.9945          | 0.5072   |
-| 0.9218        | 2.89  | 57   | 0.9638          | 0.5360   |
 ### Framework versions

     metrics:
     - name: Accuracy
       type: accuracy
+      value: 0.9100719424460432
 ---
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 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.
 It achieves the following results on the evaluation set:
+- Loss: 0.2633
+- Accuracy: 0.9101
 ## Model description
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 12
 ### Training results
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 0.8026        | 0.96  | 19   | 0.9313          | 0.5612   |
+| 0.7571        | 1.97  | 39   | 0.8835          | 0.5755   |
+| 0.7061        | 2.99  | 59   | 0.7589          | 0.6871   |
+| 0.5911        | 4.0   | 79   | 0.6329          | 0.7482   |
+| 0.5194        | 4.96  | 98   | 0.5634          | 0.7698   |
+| 0.4471        | 5.97  | 118  | 0.4552          | 0.8165   |
+| 0.3743        | 6.99  | 138  | 0.3760          | 0.8525   |
+| 0.3686        | 8.0   | 158  | 0.3233          | 0.8705   |
+| 0.318         | 8.96  | 177  | 0.3141          | 0.8777   |
+| 0.3163        | 9.97  | 197  | 0.2772          | 0.8993   |
+| 0.2871        | 10.99 | 217  | 0.2707          | 0.9029   |
+| 0.2909        | 11.54 | 228  | 0.2633          | 0.9101   |
 ### Framework versions