andrecastro
/

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

Image Classification

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

andrecastro commited on Dec 7, 2023

Commit

76ad3e6

•

1 Parent(s): 8c86212

Model save

Files changed (2) hide show

README.md +7 -7
model.safetensors +1 -1

README.md CHANGED Viewed

@@ -27,7 +27,7 @@ model-index:
       value: 0.9883021390374331
     - name: Precision
       type: precision
-      value: 0.9883122470936521
     - name: Recall
       type: recall
       value: 0.9883021390374331
@@ -40,11 +40,11 @@ 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: 0.0378
 - Accuracy: 0.9883
-- Precision: 0.9883
 - Recall: 0.9883
-- Confusion Matrix: [[1498, 14], [21, 1459]]
 ## Model description
@@ -78,9 +78,9 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | Confusion Matrix         |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------------------------:|
-| 0.2326        | 1.0   | 374  | 0.0551          | 0.9806   | 0.9807    | 0.9806 | [[1472, 40], [18, 1462]] |
-| 0.072         | 2.0   | 748  | 0.0380          | 0.9876   | 0.9876    | 0.9876 | [[1491, 21], [16, 1464]] |
-| 0.0529        | 3.0   | 1122 | 0.0378          | 0.9883   | 0.9883    | 0.9883 | [[1498, 14], [21, 1459]] |
 ### Framework versions

       value: 0.9883021390374331
     - name: Precision
       type: precision
+      value: 0.9883638028735799
     - name: Recall
       type: recall
       value: 0.9883021390374331
 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: 0.0363
 - Accuracy: 0.9883
+- Precision: 0.9884
 - Recall: 0.9883
+- Confusion Matrix: [[1503, 9], [26, 1454]]
 ## Model description
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | Confusion Matrix         |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------------------------:|
+| 0.1073        | 1.0   | 374  | 0.0387          | 0.9886   | 0.9887    | 0.9886 | [[1502, 10], [24, 1456]] |
+| 0.0892        | 2.0   | 748  | 0.0311          | 0.9896   | 0.9897    | 0.9896 | [[1501, 11], [20, 1460]] |
+| 0.0071        | 3.0   | 1122 | 0.0363          | 0.9883   | 0.9884    | 0.9883 | [[1503, 9], [26, 1454]]  |
 ### Framework versions

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf7c5eddbfab72b115fd0528ae51fc8dd5153020af3a6a5ccf98fced7584051f
 size 110342832

 version https://git-lfs.github.com/spec/v1
+oid sha256:64682c438f4ba11219d4b373cd848f090d0f83ca8cf35acb49ea06190b49cc68
 size 110342832