Update README.md
Browse files
README.md
CHANGED
|
@@ -54,6 +54,9 @@ This model had high metrics across each of the classes, meeting the success thre
|
|
| 54 |
***
|
| 55 |
# Limitations and Biases
|
| 56 |
### *Known failure cases*
|
|
|
|
|
|
|
|
|
|
| 57 |
|
| 58 |
### *Poor performing classes*
|
| 59 |
### *Data biases*
|
|
|
|
| 54 |
***
|
| 55 |
# Limitations and Biases
|
| 56 |
### *Known failure cases*
|
| 57 |
+
<img alt="Failure Cases" src="https://huggingface.co/cvtechniques/DogTypeDetection/resolve/main/Screenshot%202026-03-15%20160209.png" height="500"></img>
|
| 58 |
+
|
| 59 |
+
After testing with images outside of the training set, a pattern imerged where the model would perform well but consistently made mistakes on the same breeds(seen in the image above). This is because these breeds were not in the orginal training data.
|
| 60 |
|
| 61 |
### *Poor performing classes*
|
| 62 |
### *Data biases*
|