usamaaleem99tech
/

segformer-class-classWeights-augmentation

Image Classification

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

usamaaleem99tech commited on Jul 7, 2023

Commit

2505f6a

•

1 Parent(s): c8d3f18

update model card README.md

Files changed (1) hide show

README.md +13 -13

README.md CHANGED Viewed

@@ -21,7 +21,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.9545454545454546
 ---
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -31,8 +31,8 @@ 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: 0.0927
-- Accuracy: 0.9545
 ## Model description
@@ -66,16 +66,16 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 0.96  | 6    | 0.9944          | 0.4773   |
-| 1.0159        | 1.92  | 12   | 0.6948          | 0.75     |
-| 1.0159        | 2.88  | 18   | 0.3417          | 0.9318   |
-| 0.5444        | 4.0   | 25   | 0.2642          | 0.9091   |
-| 0.2331        | 4.96  | 31   | 0.0986          | 0.9545   |
-| 0.2331        | 5.92  | 37   | 0.1735          | 0.9545   |
-| 0.2596        | 6.88  | 43   | 0.1091          | 0.9545   |
-| 0.1737        | 8.0   | 50   | 0.0685          | 0.9545   |
-| 0.1737        | 8.96  | 56   | 0.0995          | 0.9545   |
-| 0.1716        | 9.6   | 60   | 0.0927          | 0.9545   |
 ### Framework versions

     metrics:
     - name: Accuracy
       type: accuracy
+      value: 0.9772727272727273
 ---
 <!-- 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: 0.0991
+- Accuracy: 0.9773
 ## Model description
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
+| No log        | 0.96  | 6    | 1.0191          | 0.6364   |
+| 1.0551        | 1.92  | 12   | 0.8644          | 0.7273   |
+| 1.0551        | 2.88  | 18   | 0.5563          | 0.8636   |
+| 0.7192        | 4.0   | 25   | 0.2687          | 0.9545   |
+| 0.4056        | 4.96  | 31   | 0.1921          | 0.9545   |
+| 0.4056        | 5.92  | 37   | 0.1246          | 0.9545   |
+| 0.267         | 6.88  | 43   | 0.1010          | 0.9773   |
+| 0.2547        | 8.0   | 50   | 0.1442          | 0.9773   |
+| 0.2547        | 8.96  | 56   | 0.1188          | 0.9773   |
+| 0.189         | 9.6   | 60   | 0.0991          | 0.9773   |
 ### Framework versions