Closed tashrifbillah closed 2 months ago
Link PR #40
Yes will start digging into this tomorrow. I have a feeling you are correct if it did not run on gpu.
More errors:
Loading sagittal model from disk...
/software/rocky9/miniconda3/envs/dmri_seg/lib/python3.9/site-packages/keras/optimizers/optimizer_v2/adam.py:114: UserWarning: The `lr` argument is deprecated, use `learning_rate` instead.
super().__init__(name, **kwargs)
40/40 [==============================] - 43s 1s/step
Loading coronal model from disk...
40/40 [==============================] - 43s 1s/step
Loading axial model from disk...
40/40 [==============================] - 43s 1s/step
Masking Time Taken : 2.23 min
Splitting files....
Performing Muti View Aggregation...
Converting file format...
Performing ants inverse transform...
Cleaning up /software/rocky9/CNN-Diffusion-MRIBrain-Segmentation/tests/data/Prisma/_ep_b0_bse-multi_originalMask.nii.gz
Traceback (most recent call last):
File "/software/rocky9/CNN-Diffusion-MRIBrain-Segmentation/tests/../pipeline/../src/maskfilter.py", line 3, in <module>
from scipy.ndimage import binary_erosion, binary_dilation, generate_binary_structure
ModuleNotFoundError: No module named 'scipy'
/software/rocky9/CNN-Diffusion-MRIBrain-Segmentation/tests/data/Prisma/_ep_b0_bse-multi_FilteredMask.nii.gz
Traceback (most recent call last):
File "/software/rocky9/miniconda3/envs/dmri_seg/lib/python3.9/site-packages/nibabel/loadsave.py", line 100, in load
stat_result = os.stat(filename)
FileNotFoundError: [Errno 2] No such file or directory: '/software/rocky9/CNN-Diffusion-MRIBrain-Segmentation/tests/data/Prisma/_ep_b0_bse-multi_FilteredMask.nii.gz'
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/software/rocky9/CNN-Diffusion-MRIBrain-Segmentation/tests/../pipeline/dwi_masking.py", line 768, in <module>
brain_mask_multi = npy_to_nifti(list(transformed_cases[i].split()),
File "/software/rocky9/CNN-Diffusion-MRIBrain-Segmentation/tests/../pipeline/dwi_masking.py", line 353, in npy_to_nifti
img = nib.load(output_mask_filtered)
File "/software/rocky9/miniconda3/envs/dmri_seg/lib/python3.9/site-packages/nibabel/loadsave.py", line 102, in load
raise FileNotFoundError(f"No such file or no access: '{filename}'")
FileNotFoundError: No such file or no access: '/software/rocky9/CNN-Diffusion-MRIBrain-Segmentation/tests/data/Prisma/_ep_b0_bse-multi_FilteredMask.nii.gz'
/software/rocky9/CNN-Diffusion-MRIBrain-Segmentation/tests/../pipeline/dwi_masking.py:40: DeprecationWarning: pkg_resources is deprecated as an API. See https://setuptools.pypa.io/en/latest/pkg_resources.html
import pkg_resources
Use GPU device # 0
2024-03-18 17:29:17.953745: E tensorflow/stream_executor/cuda/cuda_blas.cc:2981] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
Ryan, this does not use GPU on pnl-predict either.
However, I missed the scipy error within the traceback I posted yesterday. It is because of the - scikit-image==0.16.2
package you have unknowingly removed. I am going to solve it now:
ModuleNotFoundError: No module named 'scipy'
Let me look into what is going on. I know it did use the gpu there at one point, as I was watching it via nvidia-smi use it. Let me double check versions of code I was using and some other things.
No longer relevant. Thanks to Ryan for providing the correct sequence of package installation.
1.
Can we deal with this warnings?
2. I think these warnings are the reason why it uses only CPU and not GPU. Please test in pnl-axon.