Update README.md
Browse files
README.md
CHANGED
|
@@ -53,14 +53,16 @@ I also utilized Ultralytics’ heatmap code to display a heatmap on the input vi
|
|
| 53 |
## Confusion Matrix
|
| 54 |
The final confusion matrix shows that my model was very successful at identifying sea otters across the dataset. There are a portion of mislabels where the model mistook a sea otter for background, but this can be expected with the quality of training images and smaller dataset.
|
| 55 |
https://huggingface.co/OceanCV/Southern_Sea_Otter_Tracking/blob/main/confusion_matrix_final.png
|
|
|
|
| 56 |
|
| 57 |
## F1 Score
|
| 58 |
The final F1 curve shows my model’s high precision and recall across the various confidence levels. The curve had a high peak, signifying a harmonic balance between precision and recall.
|
| 59 |
https://huggingface.co/OceanCV/Southern_Sea_Otter_Tracking/blob/main/F1_curve.png
|
| 60 |
-
|
| 61 |
|
| 62 |
## Object Detection Model Output
|
| 63 |
My final object detection output video was a key metric in assessing the performance of my model. I bounced between looking at the output video, assessing how accurate the bounding boxes and identifications were, and rerunning the model with modified parameters. My final model output was successful at identifying sea otters in both land and water, with minimal misclassifications or missed detections.
|
|
|
|
| 64 |
|
| 65 |
---
|
| 66 |
# Model Use-case
|
|
|
|
| 53 |
## Confusion Matrix
|
| 54 |
The final confusion matrix shows that my model was very successful at identifying sea otters across the dataset. There are a portion of mislabels where the model mistook a sea otter for background, but this can be expected with the quality of training images and smaller dataset.
|
| 55 |
https://huggingface.co/OceanCV/Southern_Sea_Otter_Tracking/blob/main/confusion_matrix_final.png
|
| 56 |
+
|
| 57 |
|
| 58 |
## F1 Score
|
| 59 |
The final F1 curve shows my model’s high precision and recall across the various confidence levels. The curve had a high peak, signifying a harmonic balance between precision and recall.
|
| 60 |
https://huggingface.co/OceanCV/Southern_Sea_Otter_Tracking/blob/main/F1_curve.png
|
| 61 |
+
|
| 62 |
|
| 63 |
## Object Detection Model Output
|
| 64 |
My final object detection output video was a key metric in assessing the performance of my model. I bounced between looking at the output video, assessing how accurate the bounding boxes and identifications were, and rerunning the model with modified parameters. My final model output was successful at identifying sea otters in both land and water, with minimal misclassifications or missed detections.
|
| 65 |
+
|
| 66 |
|
| 67 |
---
|
| 68 |
# Model Use-case
|