Corrects Error running model from local file on Windows and readme update

README.md

@@ -32,11 +32,11 @@ expects an input image with the same features. An example notebook for how the p
 
 **Command line**
 ```bash
-python geo_inference.py -a <args>
+python geo_inference -a <args>
 ```
 - `-a`, `--args`: Path to arguments stored in yaml, consult ./config/sample_config.yaml
 ```bash
-python geo_inference.py -i <image> -m <model> -wd <work_dir> -bs <batch_size> -v <vec> -d <device> -id <gpu_id>
+python geo_inference -i <image> -m <model> -wd <work_dir> -bs <batch_size> -v <vec> -d <device> -id <gpu_id>
 ```
 - `-i`, `--image`: Path to Geotiff
 - `-bb`, `--bbox`: AOI bbox in this format "minx, miny, maxx, maxy" (Optional)
@@ -52,7 +52,7 @@ python geo_inference.py -i <image> -m <model> -wd <work_dir> -bs <batch_size> -v
 You can also use the `-h` option to get a list of supported arguments:
 
 ```bash
-python geo_inference.py -h
+python geo_inference -h
 ```
 
 **Import script**

geo_inference/utils/helpers.py

@@ -197,7 +197,7 @@ def get_model(model_path_or_url: str, work_dir: Path) -> Path:
         Path: Path to the model file.
     """
     parsed_string = urlparse(model_path_or_url)
-    if parsed_string.scheme:
+    if parsed_string.scheme and not os.path.exists(model_path_or_url):
         model_url = model_path_or_url
         model_name = os.path.basename(parsed_string.path)
         cached_file = work_dir.joinpath(model_name)