Francesco Tamborra

The datasets used in the paper are massive and quite complicated to retrieve. Could you push a small sample.csv just to run the code and figure out all the pretreatment...

> The above is similar to what @fratambot writes in #509 Hey @kbakk, in the end I managed to integrate nicely loguru and sentry. You can take a look at...

@jtfidje where the `settings ` are coming from in your example ?

> Shouldn't c = s[i-1] **not** c = s[-i]? -i is the negative of i, not the index you want. He's parsing the string backwards: ``` s = "hey" #...

Actually, reading the paper: https://arxiv.org/pdf/1509.01626.pdf the reason for the backwards mapping is given (page 2): > The character quantization order is backward so that the latest reading on characters is...

Hello Ryan and Sean, The data comes from a public dataset: https://ignf.github.io/FLAIR/#FLAIR1 and they are in `.tif` format; size of every image is ~1 MB. I was seeing the memory...

Hello Ryan, here's the output of `rasterio.show_versions()` : ``` rasterio info: rasterio: 1.3.9 GDAL: 3.7.3 PROJ: 9.3.0 GEOS: 3.12.0 PROJ DATA: /opt/miniconda3/envs/flair-new/share/proj GDAL DATA: /opt/miniconda3/envs/flair-new/share/gdal System: python: 3.11.6 | packaged...

Hello everybody, First of all I realized that `tracemalloc` is not the best tool to measure the overall memory usage of a script so I moved to `memory-profile`. Secondly and...

> @fratambot One thing to note is that the shapes of the arrays returned from gdal and rasterio are different. gdal returns an img array of shape (512, 512, 5),...

> @fratambot I ran your code sample with an environment that tried to match versions as best I could. I could not reproduce your issue on my machine. > >...