trouble running Geo-SAM Image Encoder!

[MohammadMr]

i'm using .tif file as input and my laptop doesn't have cuda installed on it.
the 'Use GPU if CUDA is available' box is unchecked
I'm getting the fallowing error:

RuntimeError: Attempting to deserialize object on a CUDA device but torch.cuda.is_available() is False. If you are running on a CPU-only machine, please use torch.load with map_location=torch.device('cpu') to map your storages to the CPU.

what can i do? should i install CUDA?

[Fanchengyan]

Hi @MohammadMr ，

Could you please post the original error log? Based on your current information, I am unable to pinpoint the issue.

[MohammadMr]

sure, here it is:

Traceback (most recent call last):
File "C:\Users/MrMe/AppData/Roaming/QGIS/QGIS3\profiles\default/python/plugins\Geo-SAM\tools\sam_processing_algorithm.py", line 491, in processAlgorithm
self.sam_model = self.initialize_sam(
File "C:\Users/MrMe/AppData/Roaming/QGIS/QGIS3\profiles\default/python/plugins\Geo-SAM\tools\sam_processing_algorithm.py", line 627, in initialize_sam
sam_model = sam_model_registry[model_type](
File "C:\Users\MrMe\AppData\Roaming\Python\Python39\site-packages\segment_anything\build_sam.py", line 38, in build_sam_vit_b
return _build_sam(
File "C:\Users\MrMe\AppData\Roaming\Python\Python39\site-packages\segment_anything\build_sam.py", line 105, in _build_sam
state_dict = torch.load(f)
File "C:\Users\MrMe\AppData\Roaming\Python\Python39\site-packages\torch\serialization.py", line 1026, in load
return _load(opened_zipfile,
File "C:\Users\MrMe\AppData\Roaming\Python\Python39\site-packages\torch\serialization.py", line 1438, in _load
result = unpickler.load()
File "C:\Users\MrMe\AppData\Roaming\Python\Python39\site-packages\torch\serialization.py", line 1408, in persistent_load
typed_storage = load_tensor(dtype, nbytes, key, _maybe_decode_ascii(location))
File "C:\Users\MrMe\AppData\Roaming\Python\Python39\site-packages\torch\serialization.py", line 1382, in load_tensor
wrap_storage=restore_location(storage, location),
File "C:\Users\MrMe\AppData\Roaming\Python\Python39\site-packages\torch\serialization.py", line 391, in default_restore_location
result = fn(storage, location)
File "C:\Users\MrMe\AppData\Roaming\Python\Python39\site-packages\torch\serialization.py", line 266, in _cuda_deserialize
device = validate_cuda_device(location)
File "C:\Users\MrMe\AppData\Roaming\Python\Python39\site-packages\torch\serialization.py", line 250, in validate_cuda_device
raise RuntimeError('Attempting to deserialize object on a CUDA '
RuntimeError: Attempting to deserialize object on a CUDA device but torch.cuda.is_available() is False. If you are running on a CPU-only machine, please use torch.load with map_location=torch.device('cpu') to map your storages to the CPU.

Execution failed after 26.18 seconds

[Fanchengyan]

Hi @MohammadMr ,

Please check if you have selected the correct checkpoint : https://geo-sam.readthedocs.io/en/latest/Usage/encoding.html#download-sam-checkpoints

This appears to be a similar issue as problem #21 .