Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,22 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: mit
|
| 3 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
---
|
| 4 |
+
|
| 5 |
+
Original repo: https://github.com/gifu-wildlife/MDetToolsForJCameraTraps
|
| 6 |
+
|
| 7 |
+
The model weights have been soptred here for easy integration with AddaxAI: https://addaxdatascience.com/addaxai/
|
| 8 |
+
|
| 9 |
+
Gifu-wildlife cls model v0.2 (resnet50) for AddaxAI v6.14
|
| 10 |
+
|
| 11 |
+
Filename (weight): gifu-wildlife_cls_resnet50_v0.2.1.pth
|
| 12 |
+
|
| 13 |
+
Changes from v0.1:
|
| 14 |
+
* Trained using data excluding “human” and “dog” due to insufficient data. As a result, the number of categories decreased from 15 to 13.
|
| 15 |
+
* Modified classify_datections.py to match changes in AddaxAI v6.14.
|
| 16 |
+
* Changed “rabbit” to “hare.”
|
| 17 |
+
* Carefully rewrote classes.csv.
|
| 18 |
+
|
| 19 |
+
Test results[2025-05-20]:
|
| 20 |
+
* Top1 Accuracy : 0.926069438457489
|
| 21 |
+
* Top3 Accuracy : 0.9869807958602905
|
| 22 |
+
* class wise acc | bear:0.816 | bird:0.571 | boar:0.941 | cat:0.200 | deer:0.971 | fox:0.607 | masked:0.519 | monkey:0.000 | mustelidae:0.600 | rabbit:0.235 | raccoondog:0.871 | serow:0.884 | squirrel:0.649
|