search

tjiagoM / adni_phenotypes

Identifying healthy individuals with Alzheimer neuroimaging phenotypes in the UK Biobank
Other
4 stars 0 forks source link

FileNotFoundError: [Errno 2] No such file or directory: 'data/adni_train_scaled_corrected.csv' #1

Open 011211 opened 9 months ago

011211 commented 9 months ago

(adni_phenotypes) F:\2023\code\github\adni_phenotypes-main>python inference.py --dataset_location data/adni_test_scaled_corrected.csv --dataset_id adni Namespace(dataset_id='adni', dataset_location='data/adni_test_scaled_corrected.csv', device='cuda:1', do_single_pass=False, wb_model_id='2cxy59fk') wandb: Network error (ProxyError), entering retry loop. Traceback (most recent call last): File "inference.py", line 124, in run_inference(dataset_location=args.dataset_location, dataset_id=args.dataset_id, File "inference.py", line 60, in run_inference model = SimpleMLP(dim_in=155, dropout_rate=best_run.config['dropout']).to(device) File "F:\anaconda3\envs\adni_phenotypes\lib\site-packages\torch\nn\modules\module.py", line 927, in to return self._apply(convert) File "F:\anaconda3\envs\adni_phenotypes\lib\site-packages\torch\nn\modules\module.py", line 579, in _apply module._apply(fn) File "F:\anaconda3\envs\adni_phenotypes\lib\site-packages\torch\nn\modules\module.py", line 602, in _apply param_applied = fn(param) File "F:\anaconda3\envs\adni_phenotypes\lib\site-packages\torch\nn\modules\module.py", line 925, in convert return t.to(device, dtype if t.is_floating_point() or t.is_complex() else None, non_blocking) RuntimeError: CUDA error: invalid device ordinal CUDA kernel errors might be asynchronously reported at some other API call,so the stacktrace below might be incorrect. For debugging consider passing CUDA_LAUNCH_BLOCKING=1.

011211 commented 9 months ago

I followed the instructions in the readme.txt and used the command to download the dataset, but I get the above error, please tell me how I can fix it.

tjiagoM commented 9 months ago

Hi! And thanks for your interest in this work. You seem to be using the command as to use the ADNI dataset; however, I'm very sorry but we are not allowed to share the data directly. As you can see in our data availability statement in the paper, you have to request access yourself to access it: https://adni.loni.usc.edu/data-samples/access-data/

In the file datasets.py you can see which cortical and volume variables we used from processing that data (i.e., variables FEATURES_CORTICAL, FEATURES_VOLUME, and FEATURES_VOLUME_EXTRA).

The way we normalise and scale the data is explained in the paper, with corresponding code in a jupyter notebook here: data/Preprocessing ADNI data.ipynb

I hope this helps.