Skip to content

Commit 44edda1

Browse files
authored
Update README.md
1 parent a3022d9 commit 44edda1

File tree

1 file changed

+12
-1
lines changed

1 file changed

+12
-1
lines changed

README.md

Lines changed: 12 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1,2 +1,13 @@
11
# A-Method-Clustering-and-Classifying-Hand-shapes-from-Auslan
2-
A Method Clustering and Classifying Hand shapes from Auslan
2+
3+
Use the get_signs.py script to create your data set or Auslan signs.
4+
5+
Then use the create_data.py script to run the MediaPipe framework over your collected data to create a dataset for training a fully connected network.
6+
7+
Next, use the make_hand_model.py script to train a full connected network. Be careful to examine the directory references.
8+
9+
Finally, Use posenet_video.py script to classify your handshapes from data has been collected. Make sure this script references your trained hand model
10+
11+
For accuracy and performance metrics, use the classification_report.py script to see your models accuracy
12+
13+
Scripts that end in "clustering.py" and "crop_hand.py" are used for clustering from a video source, where the number of hand shapes are unknown.

0 commit comments

Comments
 (0)