Models after fixing the issues with CG index, slope, and substrate

README.md

@@ -31,7 +31,7 @@ SKeMa is a Python-based tool for semantic segmentation of kelp in Sentinel-2 sat
 - **Framework**: PyTorch, Segmentation Models PyTorch (SMP) library.
 - **Encoder**: MaxViT-Tiny-512.
 - **Decoder**: UNet.
-- **Input Channels**: 12 (Sentinel-2 bands B2, B3, B4, B8, B5; substrate; bathymetry; slope; spectral indices with the order NDVI; NDWI; GNDVI; ClI; NDVIRE).
+- **Input Channels**: 13 (Sentinel-2 bands B2, B3, B4, B8, B5; substrate; bathymetry; slope; spectral indices with the order NDVI; NDWI; GNDVI; ClI; NDVIRE).
 - **Model Types**:
   - `model_full`: Uses all 13 channels, including substrate, bathymetry, and slope (optimized for BC coast).
   - `model_s2bandsandindices_only`: Uses Sentinel-2 bands and indices only (no bathymetry/substrate/slope).

model.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ed0a8558e9158102dbf9468318f0d057681594fa4ad2f86b2ebe8ec19719ca5
-size 134215307
+oid sha256:42e6665257f0ed6d9367494ee140b13d95f3fb818d8b24712d3384931a5666b6
+size 134207976

modelS2Only.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3dbad0256f909750fafc9dc9ef12dbb5700f253bc56c0ff4d23115f82793e746
-size 134221531
+oid sha256:0757dd2be663a579e8e46efdaed0377ae383e7311d11925541c6dbc4094c1933
+size 134201064