Update README.md
Browse files
README.md
CHANGED
|
@@ -13,7 +13,7 @@ probably proofread and complete it, then remove this comment. -->
|
|
| 13 |
|
| 14 |
# volvoDon/petro-daemon
|
| 15 |
|
| 16 |
-
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on
|
| 17 |
It achieves the following results on the evaluation set:
|
| 18 |
- Train Loss: 0.8890
|
| 19 |
- Validation Loss: 1.1803
|
|
@@ -26,13 +26,8 @@ More information needed
|
|
| 26 |
|
| 27 |
## Intended uses & limitations
|
| 28 |
|
| 29 |
-
|
| 30 |
-
|
| 31 |
-
## Training and evaluation data
|
| 32 |
-
|
| 33 |
-
More information needed
|
| 34 |
-
|
| 35 |
-
## Training procedure
|
| 36 |
|
| 37 |
### Training hyperparameters
|
| 38 |
|
|
|
|
| 13 |
|
| 14 |
# volvoDon/petro-daemon
|
| 15 |
|
| 16 |
+
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on a [DataSet of petrologic cross sections](https://huggingface.co/datasets/volvoDon/petrology-sections).
|
| 17 |
It achieves the following results on the evaluation set:
|
| 18 |
- Train Loss: 0.8890
|
| 19 |
- Validation Loss: 1.1803
|
|
|
|
| 26 |
|
| 27 |
## Intended uses & limitations
|
| 28 |
|
| 29 |
+
Currently it is just a proof of concept and does a great job identifiying Olivine
|
| 30 |
+
It currently is not ready for a production enviroment but the results are promising, with an improved dataset I'm confident better results could be acheived.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 31 |
|
| 32 |
### Training hyperparameters
|
| 33 |
|