Keras
mikejrodd commited on
Commit
775750a
1 Parent(s): 8f1fe15

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +28 -3
README.md CHANGED
@@ -1,3 +1,28 @@
1
- ---
2
- license: mit
3
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ ---
4
+
5
+ # Grape Leaf Disease Detection with KANConv2D
6
+
7
+ ## Description
8
+ This project used a custom convolutional layer, KANConv2D, to build a convolutional neural network (CNN) for detecting Esca disease in grape leaves. The KANConv2D layer incorporates kernel adaptive networks to enhance the performance of traditional Conv2D layers.
9
+
10
+ For more on KAN see: https://arxiv.org/pdf/2406.13155
11
+
12
+ Final accuracy was 84.17%
13
+
14
+ ## Features
15
+ - Custom KANConv2D layer with kernel adaptive networks
16
+ - Data augmentation for robust training
17
+ - Early stopping to prevent overfitting
18
+ - Class weighting to handle imbalanced datasets
19
+
20
+ ## Model Architecture
21
+ The CNN model consists of:
22
+ - Multiple KANConv2D layers
23
+ - Max pooling layers
24
+ - Dense and dropout layers
25
+ - Binary output with sigmoid activation
26
+
27
+ ## Training
28
+ The model is compiled with the Adam optimizer, binary cross-entropy loss, and accuracy as the metric. Class weights are adjusted to reduce false negatives for Esca detection. The model is trained with early stopping to restore the best weights based on validation loss.