Trying to replicate a paper with code

[FelixPQ]

The paper is here:
The code and data link are here

I've created a directory structure locally as per the recommendations on Github, with images, weights and all (at least I think)

I transferred all of these files and directories to my Google Drive account, then in Colab,

cd /content/drive/MyDrive/BAID/

and then
!python test.py

100% 3200/3200 [00:00<00:00, 915474.58it/s] Traceback (most recent call last): File "/content/drive/MyDrive/BAID/test.py", line 75, in <module> test(args) File "/content/drive/MyDrive/BAID/test.py", line 37, in test model = SAAN(num_classes=1) File "/content/drive/MyDrive/BAID/models/model.py", line 101, in __init__ self.GenAes = GAB() File "/content/drive/MyDrive/BAID/models/model.py", line 79, in __init__ self._init_weights() File "/content/drive/MyDrive/BAID/models/model.py", line 94, in _init_weights self.model.load_state_dict(torch.load('checkpoint/ResNet_Pretrain/epoch_99.pth'), File "/usr/local/lib/python3.10/dist-packages/torch/serialization.py", line 1014, in load return _load(opened_zipfile, File "/usr/local/lib/python3.10/dist-packages/torch/serialization.py", line 1422, in _load result = unpickler.load() File "/usr/local/lib/python3.10/dist-packages/torch/serialization.py", line 1392, in persistent_load typed_storage = load_tensor(dtype, nbytes, key, _maybe_decode_ascii(location)) File "/usr/local/lib/python3.10/dist-packages/torch/serialization.py", line 1366, in load_tensor wrap_storage=restore_location(storage, location), File "/usr/local/lib/python3.10/dist-packages/torch/serialization.py", line 381, in default_restore_location result = fn(storage, location) File "/usr/local/lib/python3.10/dist-packages/torch/serialization.py", line 274, in _cuda_deserialize device = validate_cuda_device(location) File "/usr/local/lib/python3.10/dist-packages/torch/serialization.py", line 258, 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.

and I also tried with a GPU (By the way I'm on the free version of Colab at the moment.

I change the workspace to gpu and ran this.
100% 3200/3200 [00:00<00:00, 686957.35it/s] Traceback (most recent call last): File "/content/drive/MyDrive/BAID/test.py", line 75, in <module> test(args) File "/content/drive/MyDrive/BAID/test.py", line 37, in test model = SAAN(num_classes=1) File "/content/drive/MyDrive/BAID/models/model.py", line 101, in __init__ self.GenAes = GAB() File "/content/drive/MyDrive/BAID/models/model.py", line 79, in __init__ self._init_weights() File "/content/drive/MyDrive/BAID/models/model.py", line 94, in _init_weights self.model.load_state_dict(torch.load('checkpoint/ResNet_Pretrain/epoch_99.pth'), File "/usr/local/lib/python3.10/dist-packages/torch/serialization.py", line 1014, in load return _load(opened_zipfile, File "/usr/local/lib/python3.10/dist-packages/torch/serialization.py", line 1422, in _load result = unpickler.load() File "/usr/local/lib/python3.10/dist-packages/torch/serialization.py", line 1392, in persistent_load typed_storage = load_tensor(dtype, nbytes, key, _maybe_decode_ascii(location)) File "/usr/local/lib/python3.10/dist-packages/torch/serialization.py", line 1366, in load_tensor wrap_storage=restore_location(storage, location), File "/usr/local/lib/python3.10/dist-packages/torch/serialization.py", line 381, in default_restore_location result = fn(storage, location) File "/usr/local/lib/python3.10/dist-packages/torch/serialization.py", line 274, in _cuda_deserialize device = validate_cuda_device(location) File "/usr/local/lib/python3.10/dist-packages/torch/serialization.py", line 265, in validate_cuda_device raise RuntimeError('Attempting to deserialize object on CUDA device ' RuntimeError: Attempting to deserialize object on CUDA device 1 but torch.cuda.device_count() is 1. Please use torch.load with map_location to map your storages to an existing device.

I'm a complete newbie with all this and I have no clue. Maybe someone came across a similar problem and would have some suggestions.

Regards,
Yves

[FelixPQ]

I forgot to mention I use this for the second call.

!python test.py --device="gpu"

[shisirkha]

use default torch cuda type not the python