Update README.md
Browse files
README.md
CHANGED
@@ -127,11 +127,13 @@ No data augmentation method concerning scale change was used during training. Th
|
|
127 |
The input images are distributed in 8-bit encoding format per channel. For traning the model, input normalization was performed so as the input dataset has a mean of 0 and a standart deviation of 1.
|
128 |
For this model here are the statistics of the TRAIN+VALIDATION partition. It is recommended that the user apply the same type of input normalization.
|
129 |
|
130 |
-
|
|
131 |
-
|
|
132 |
-
|
|
133 |
-
|
|
134 |
-
|
|
|
|
|
135 |
|
136 |
|
137 |
|
|
|
127 |
The input images are distributed in 8-bit encoding format per channel. For traning the model, input normalization was performed so as the input dataset has a mean of 0 and a standart deviation of 1.
|
128 |
For this model here are the statistics of the TRAIN+VALIDATION partition. It is recommended that the user apply the same type of input normalization.
|
129 |
|
130 |
+
| Modalities | Mean |Std |
|
131 |
+
| ----------------------- | ----------- |----------- |
|
132 |
+
| Red Channel (R) | 105.08 |52.17 |
|
133 |
+
| Green Channel (V) | 110.87 |45.38 |
|
134 |
+
| Blue Channel (B) | 101.82 |44.00 |
|
135 |
+
| Infrared Channel (I) | 106.38 |39.69 |
|
136 |
+
| Elevation Channel (E) | 53.26 |79.30 |
|
137 |
|
138 |
|
139 |
|