geo-deep-learning
geo-deep-learning copied to clipboard
NRCan
Deep learning applied to georeferenced datasets
**Description** An import error arises when attempting to run the code. "ImportError: /lib/x86_64-linux-gnu/libstdc++.so.6: version `GLIBCXX_3.4.29' not found (required by /opt/anaconda3/envs/geo_deep_env/lib/python3.10/site-packages/pandas/_libs/window/aggregations.cpython-310-x86_64-linux-gnu.so)" **Steps To Reproduce** 1. Clone the repository 2. cd geo-deep-learning...
The following documentation should include the "verify" mode: https://geo-deep-learning.readthedocs.io/en/latest/mode.html
**Is your feature request related to a problem? Please describe.** Problem: some mosaics we use consists mostly of nodata regions. For example, NB_Edmunstron_2016-B:  This 15 cm image covers approx....
**Describe the bug** A missing binary library causes docker image creation to fail **To Reproduce** `docker build . --file Dockerfile` **Expected behavior** Succesful build. **Screenshots** 
**Describe the bug** During inference, certain image raise a ValueError: "can't extend empty axis 0 using modes other than 'constant' or 'empty'" This seems to be related to the image,...
I notice percent in the split dataset do not match the expected proportions. It seems split is made before filtering patches by min_annot_perc.
After tiling, the destination folder contains all possible patches from the raster image, event when there is not ground truth (GT) labels matching (< min_annot_perc). Flood happens close to water...
https://github.com/NRCan/geo-deep-learning/blob/develop/utils/utils.py#L169 ``` if not val: # Skips below if statements if val is None logging.error(f"The key {key} as a None value.") ``` The "val" variable may be None without it...
Add the option to read a multilayers GPKG when is read by the AOI function. Plus tests for the entire `check_gdf_load` function.
At the moment the AOI function dont manage a given annoation with multiple layer. It need to be add by looking to the layer list if only one find continue...