Hugging Face's logo

agentmorris
/
megadetector

Model card Files
xet
Community
agentmorris commited on
Commit
9fffb01
·
verified ·
1 Parent(s): 379822e

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +7 -1
README.md CHANGED
@@ -16,7 +16,7 @@ If you want to run MegaDetector directly, check out the [MegaDetector User Guide
16
 
17
  # Variations
18
 
19
- Two variations of the model are included: MDv5a and MDv5b.
20
 
21
  MegaDetector v5b was trained only on camera trap images (several million images).
22
 
@@ -28,3 +28,9 @@ Both variations use the same architecture (YOLOv5x6).
28
 
29
  Both variations were trained with a [GPL-licensed version of the YOLOv5 framework](https://github.com/ecologize/yolov5). No restrictions are placed on the use of the model by the MegaDetector developers; the applicable license may be determined by the code you use to run the model.
30
 
 
 
 
 
 
 
 
16
 
17
  # Variations
18
 
19
+ Two variations of the model are included: [MDv5a](https://huggingface.co/agentmorris/megadetector/resolve/main/md_v5a.0.0.pt) and [MDv5b](https://huggingface.co/agentmorris/megadetector/resolve/main/md_v5b.0.0.pt.
20
 
21
  MegaDetector v5b was trained only on camera trap images (several million images).
22
 
 
28
 
29
  Both variations were trained with a [GPL-licensed version of the YOLOv5 framework](https://github.com/ecologize/yolov5). No restrictions are placed on the use of the model by the MegaDetector developers; the applicable license may be determined by the code you use to run the model.
30
 
31
+ # Sample output
32
+
33
+ Here's a “teaser” image of what MegaDetector output looks like:
34
+
35
+ ![](https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F1834656%2Fa0d5a7ab7cf5bb2ff2fe02e4637ade12%2Fdetector_example.jpg?generation=1740326075538537&alt=media)
36
+ Image credit University of Washington.