luciagil
/

Human-action-convnext

Image Classification

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

luciagil commited on Apr 6

Commit

13762cf

•

1 Parent(s): 820c13c

Model save

Files changed (1) hide show

README.md +5 -5

README.md CHANGED Viewed

@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
 This model is a fine-tuned version of [facebook/convnext-tiny-224](https://huggingface.co/facebook/convnext-tiny-224) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.9170
-- Accuracy: 0.7575
 ## Model description
@@ -52,9 +52,9 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 1.3216        | 0.99  | 78   | 1.1450          | 0.7143   |
-| 1.1176        | 1.99  | 157  | 0.9661          | 0.7508   |
-| 0.9987        | 2.97  | 234  | 0.9170          | 0.7575   |
 ### Framework versions

 This model is a fine-tuned version of [facebook/convnext-tiny-224](https://huggingface.co/facebook/convnext-tiny-224) on an unknown dataset.
 It achieves the following results on the evaluation set:
+- Loss: 0.7181
+- Accuracy: 0.7917
 ## Model description
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 0.9287        | 0.99  | 78   | 0.8094          | 0.7726   |
+| 0.8263        | 1.99  | 157  | 0.7395          | 0.7877   |
+| 0.7472        | 2.97  | 234  | 0.7181          | 0.7917   |
 ### Framework versions