CharlesGaydon
commited on
Commit
•
cdffdc8
1
Parent(s):
fbfd857
Update README.md
Browse files
README.md
CHANGED
@@ -104,7 +104,7 @@ Therefore, the model is best optimized for aerial lidar point clouds with simila
|
|
104 |
|
105 |
## Bias, Risks, Limitations and Recommendations
|
106 |
|
107 |
-
**_Spatial Generalization_**: The FRACTAL dataset used for training covers 5 spatial domains from 5 southern regions of metropolitan France
|
108 |
While large and diverse, the dataset covers only a fraction of the French territory, and are not representative of its full diversity (landscapes, hardscapes, human-made objects...).
|
109 |
Adequate verifications and evaluations should be done when applied to new spatial domains.
|
110 |
|
|
|
104 |
|
105 |
## Bias, Risks, Limitations and Recommendations
|
106 |
|
107 |
+
**_Spatial Generalization_**: The FRACTAL dataset used for training covers 5 spatial domains from 5 southern regions of metropolitan France.
|
108 |
While large and diverse, the dataset covers only a fraction of the French territory, and are not representative of its full diversity (landscapes, hardscapes, human-made objects...).
|
109 |
Adequate verifications and evaluations should be done when applied to new spatial domains.
|
110 |
|