Error

[phenometry]

Dear all,

I am new to python and I was interested to try AutoNEB.
I installed the prerequisites successfully as mentioned.
(python 3.8.3 and numpy 1.20.3)
I tried python main.py project_directory config_file
and I get thee below;

File "main.py", line 131, in
main()
File "main.py", line 68, in main
graph_path, project_config_path = setup_project(config_file, project_directory)
File "main.py", line 105, in setup_project
raise ValueError(f"Config file {config_file} not found.")
ValueError: Config file config_file not found.

How can I fix this ?
Thank you

[fdraxler]

Hi, thank you for your question. You will need to call the script like this:
python <PROJECT_DIRECTORY> <CONFIG_FILE>

Here, PROJECT_DIRECTORY is the path to a folder where results should be stored, and CONFIG_FILE is the path to an existing configuration file which you can find in the configs folder.

[fdraxler]

Beware that this library has not been updated for three years now, so I cannot guarantee that the code is compatible to the newer versions of libraries like PyTorch.

[phenometry]

thank you for your response.

[phenometry]

Thanks to your response, I paid more attention to the instructions,
I chose one of the .yaml(s) in the config directory.
So I did:
python main.py .. C:\Users\conta\PyTorch-AutoNEB\configs\cifar10-cnn12.yaml

and I got the below:

Downloading https://www.cs.toronto.edu/~kriz/cifar-10-python.tar.gz to C:\Users\conta\PyTorch-AutoNEB\tmp\cifar10\cifar-10-python.tar.gz
100%|█████████████████████████████████████████████████████████████▉| 170229760/170498071 [00:24<00:00, 16478417.28it/s]Extracting C:\Users\conta\PyTorch-AutoNEB\tmp\cifar10\cifar-10-python.tar.gz to C:\Users\conta\PyTorch-AutoNEB\tmp\cifar10
Files already downloaded and verified
Traceback (most recent call last):
File "main.py", line 131, in
main()
File "main.py", line 70, in main
model, minima_count, min_config, lex_config = read_config_file(project_config_path)
File "main.py", line 32, in read_config_file
model = architecture(**arguments)
File "C:\Users\conta\PyTorch-AutoNEB\torch_autoneb\models\cnn.py", line 40, in init
dims /= Tensor(pool_size).to(int64)
RuntimeError: result type Float can't be cast to the desired output type Long
170500096it [00:28, 5918821.23it/s]

There is a torch runtimeerror which I have to resolve.