rvorias
commented
3 years ago Hi,
run.py overwrites the old model for each dataset. So to answer your main question: yes, it is possible and in fact it is already implemented.
However, the error code you posted is actually related to a different problem:
The torch.cat operation takes up a large chunk of RAM. Up until now, the capsule dataset has the most training samples (280) and it does not seem to fit in your computer's RAM. Could you tell how much RAM you have installed?
There are a couple of options to go from here:
- create an empty tensor of size [n_train, ...] and fill it with each incoming patch.
- you could place the random dimension selection before the
torch.catoperation. - calculate means and covariances online.
leolin65
(env1) D:\Code\ind_knn_ad-master\indad>python run.py padim DATASETS_PATH in 'D:\dataset\mvtec_anomaly_detection/' Running padim on bottle dataset. Training ... 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 209/209 [00:33<00:00, 6.21it/s] Testing ... 100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 83/83 [00:15<00:00, 5.20it/s] Test results bottle - image_rocauc: 1.00, pixel_rocauc: 0.96 Running padim on cable dataset. Training ... 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 224/224 [00:28<00:00, 7.85it/s] Testing ... 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 150/150 [00:31<00:00, 4.72it/s] Test results cable - image_rocauc: 0.91, pixel_rocauc: 0.96 Running padim on capsule dataset. Training ... 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 219/219 [00:29<00:00, 7.52it/s] Testing ... 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 132/132 [00:26<00:00, 4.91it/s] Test results capsule - image_rocauc: 0.86, pixel_rocauc: 0.98 Running padim on carpet dataset. Training ... 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 280/280 [00:41<00:00, 6.71it/s] Traceback (most recent call last): File "D:\Code\ind_knn_ad-master\indad\run.py", line 82, in
cli_interface()
File "D:\ProgramData\Anaconda3\envs\env1\lib\site-packages\click\core.py", line 1137, in call
return self.main(args, kwargs)
File "D:\ProgramData\Anaconda3\envs\env1\lib\site-packages\click\core.py", line 1062, in main
rv = self.invoke(ctx)
File "D:\ProgramData\Anaconda3\envs\env1\lib\site-packages\click\core.py", line 1404, in invoke
return ctx.invoke(self.callback, ctx.params)
File "D:\ProgramData\Anaconda3\envs\env1\lib\site-packages\click\core.py", line 763, in invoke
return __callback(args, **kwargs)
File "D:\Code\ind_knn_ad-master\indad\run.py", line 77, in cli_interface
total_results = run_model(method, dataset)
File "D:\Code\ind_knn_ad-master\indad\run.py", line 44, in run_model
model.fit(train_ds)
File "D:\Code\ind_knn_ad-master\indad\model.py", line 171, in fit
self.patch_lib = torch.cat(self.patch_lib, 0)
RuntimeError: [enforce fail at ..\c10\core\CPUAllocator.cpp:79] data. DefaultCPUAllocator: not enough memory: you tried to allocate 6294077440 bytes.