[BUG] BBOX parameter not working properly.

[mpelchat04]

2 things limit the use of the bbox argument for inference.

1: Data type error converting the bbox to col/row index.

Traceback (most recent call last):
  File "d:\Travail\AIAAS\geo_inf_ella.py", line 22, in <module>
    geo_inference(inference_input=r"D:\Travail\AIAAS\0.tif",
  File "D:\conda_envs\geo_inference300\Lib\site-packages\torch\utils\_contextlib.py", line 116, in decorate_context
    return func(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^
  File "D:\conda_envs\geo_inference300\Lib\site-packages\geo_inference\geo_inference.py", line 158, in __call__
    asyncio.run(run_async())
  File "D:\conda_envs\geo_inference300\Lib\asyncio\runners.py", line 194, in run
    return runner.run(main)
           ^^^^^^^^^^^^^^^^
  File "D:\conda_envs\geo_inference300\Lib\asyncio\runners.py", line 118, in run
    return self._loop.run_until_complete(task)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "D:\conda_envs\geo_inference300\Lib\asyncio\base_events.py", line 664, in run_until_complete
    return future.result()
           ^^^^^^^^^^^^^^^
  File "D:\conda_envs\geo_inference300\Lib\site-packages\geo_inference\geo_inference.py", line 144, in run_async
    self.mask_layer_name = await self.async_run_inference(
                           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "D:\conda_envs\geo_inference300\Lib\site-packages\geo_inference\geo_inference.py", line 371, in async_run_inference
    raise e
  File "D:\conda_envs\geo_inference300\Lib\site-packages\geo_inference\geo_inference.py", line 298, in async_run_inference
    aoi_dask_array = aoi_dask_array[
                     ^^^^^^^^^^^^^^^
  File "D:\conda_envs\geo_inference300\Lib\site-packages\xarray\core\dataarray.py", line 899, in __getitem__
    return self.isel(indexers=self._item_key_to_dict(key))
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "D:\conda_envs\geo_inference300\Lib\site-packages\xarray\core\dataarray.py", line 1535, in isel
    variable = self._variable.isel(indexers, missing_dims=missing_dims)
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "D:\conda_envs\geo_inference300\Lib\site-packages\xarray\core\variable.py", line 1038, in isel
    return self[key]
           ~~~~^^^^^
  File "D:\conda_envs\geo_inference300\Lib\site-packages\xarray\core\variable.py", line 802, in __getitem__
    dims, indexer, new_order = self._broadcast_indexes(key)
                               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "D:\conda_envs\geo_inference300\Lib\site-packages\xarray\core\variable.py", line 638, in _broadcast_indexes
    return self._broadcast_indexes_basic(key)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "D:\conda_envs\geo_inference300\Lib\site-packages\xarray\core\variable.py", line 668, in _broadcast_indexes_basic
    return dims, BasicIndexer(key), None
                 ^^^^^^^^^^^^^^^^^
  File "D:\conda_envs\geo_inference300\Lib\site-packages\xarray\core\indexing.py", line 397, in __init__
    k = as_integer_slice(k)
        ^^^^^^^^^^^^^^^^^^^
  File "D:\conda_envs\geo_inference300\Lib\site-packages\xarray\core\indexing.py", line 351, in as_integer_slice
    stop = as_integer_or_none(value.stop)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "D:\conda_envs\geo_inference300\Lib\site-packages\xarray\core\indexing.py", line 346, in as_integer_or_none
    return None if value is None else operator.index(value)
                                      ^^^^^^^^^^^^^^^^^^^^^
TypeError: 'float' object cannot be interpreted as an integer

In geo_inference.py, converting the col/row offsets to int fixes this issue.

2 : The writen array is not properly placed.

The xy offset is not used to write the mask, when using the bbox parameter. The mask is systematically located in the upper-left corner of the original image.

[mpelchat04]

Closed by #28