External Email - Use Caution
Hi FreeSurfer Developers,
I'm attempting to register two T2 images using mri_easyreg (FreeSurfer 7.4.1). This is what my bash code looks like:
#!/bin/bash
for subject in ./sub-?????.nii.gz do mri_easyreg --ref ./mni152_t2_strip.nii.gz --flo $subject \ --ref_seg ./mni152_t2_strip_parc.nii.gz \ --flo_seg "${subject/.nii.gz/_parc.nii.gz}" \ --flo_reg "${subject/.nii.gz/_moved.nii.gz}" \ --fwd_field "${subject/.nii.gz/_fwd_fld.nii.gz}" \ --thread 24 subject+=" Done!" echo $subject done
This is what the output looks like when I execute the bash script:
2023-10-02 11:15:58.965124: I tensorflow/core/util/port.cc:110] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`. 2023-10-02 11:15:58.988396: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations. To enable the following instructions: AVX2 AVX_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags. 2023-10-02 11:15:59.313149: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT using 24 threads Segmentation of reference image already exists; reading from disk Segmentation of floating image already exists; reading from disk Linear registration Computing centroids and estimating affine transform Reading reference image Deforming reference image to reference space Deforming reference segmentation to reference space Normalizing intensities of reference image Reading floating image Deforming floating image to reference space Deforming floating segmentation to reference space Normalizing intensities of floating image 2023-10-02 11:16:08.118592: E tensorflow/compiler/xla/stream_executor/cuda/cuda_driver.cc:266] failed call to cuInit: CUDA_ERROR_NO_DEVICE: no CUDA-capable device is detected 2023-10-02 11:16:08.118640: I tensorflow/compiler/xla/stream_executor/cuda/cuda_diagnostics.cc:168] retrieving CUDA diagnostic information for host: kaibo-Alienware-Aurora-R13 2023-10-02 11:16:08.118647: I tensorflow/compiler/xla/stream_executor/cuda/cuda_diagnostics.cc:175] hostname: kaibo-Alienware-Aurora-R13 2023-10-02 11:16:08.118766: I tensorflow/compiler/xla/stream_executor/cuda/cuda_diagnostics.cc:199] libcuda reported version is: 510.108.3 2023-10-02 11:16:08.118794: I tensorflow/compiler/xla/stream_executor/cuda/cuda_diagnostics.cc:203] kernel reported version is: 510.108.3 2023-10-02 11:16:08.118801: I tensorflow/compiler/xla/stream_executor/cuda/cuda_diagnostics.cc:309] kernel version seems to match DSO: 510.108.3 UserWarning: int_downsize is deprecated, use the int_resolution parameter. UserWarning: unet_half_res is deprecated, use the svf_resolution parameter. ./easyreg.sh: line 3: 1588985 Killed mri_easyreg --ref ./mni152_t2_strip.nii.gz --flo $subject --ref_seg ./mni152_t2_strip_parc.nii.gz --flo_seg "${subject/.nii.gz/_parc.nii.gz}" --flo_reg "${subject/.nii.gz/_moved.nii.gz}" --fwd_field "${subject/.nii.gz/_fwd_fld.nii.gz}" --thread 24 ./sub-00001.nii.gz Done!
When I checked the folder, I saw only the parcellation results. Neither the moved floating image nor the forward field were generated.
I initially thought this might be a memory problem and I set --thread 1 but I ended up getting the same result (Killed).
I've searched the list and there was another error (https://secure-web.cisco.com/1oerdskR7ZTpxdkdU8iIXVp5sQdJ_BWDnyMHH3nMMFRZxQm...) similar to mine. But I don't think mine was related. Can anyone provide any insight into this?
FreeSurfer version: freesurfer-linux-ubuntu22_x86_64-7.4.1-20230614-7eb8460 Platform: Ubuntu 22.04.2 LTS I am running the script on 12th Gen Intel® Core™ i9-12900KF × 24 with a 64.0 GiB memory and NVIDIA Corporation GA102 [GeForce RTX 3090].
Thanks, Kaibo
External Email - Use Caution
Dear Kaibo, How much RAM does your machine have? Cheers, /Eugenio
-- Juan Eugenio Iglesias http://secure-web.cisco.com/1f4DYOHf8Rr4YRZ9OT7geQMSYd2V5bpiQti0xpXTDLLzxMI7...
From: freesurfer-bounces@nmr.mgh.harvard.edu freesurfer-bounces@nmr.mgh.harvard.edu on behalf of Tang, Kaibo ktang@unc.edu Date: Monday, October 2, 2023 at 8:43 AM To: freesurfer@nmr.mgh.harvard.edu freesurfer@nmr.mgh.harvard.edu Subject: [Freesurfer] mri_easyreg error: Killed
External Email - Use Caution Hi FreeSurfer Developers,
I'm attempting to register two T2 images using mri_easyreg (FreeSurfer 7.4.1). This is what my bash code looks like:
#!/bin/bash
for subject in ./sub-?????.nii.gz do mri_easyreg --ref ./mni152_t2_strip.nii.gz --flo $subject \ --ref_seg ./mni152_t2_strip_parc.nii.gz \ --flo_seg "${subject/.nii.gz/_parc.nii.gz}" \ --flo_reg "${subject/.nii.gz/_moved.nii.gz}" \ --fwd_field "${subject/.nii.gz/_fwd_fld.nii.gz}" \ --thread 24 subject+=" Done!" echo $subject done
This is what the output looks like when I execute the bash script:
2023-10-02 11:15:58.965124: I tensorflow/core/util/port.cc:110] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`. 2023-10-02 11:15:58.988396: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations. To enable the following instructions: AVX2 AVX_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags. 2023-10-02 11:15:59.313149: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT using 24 threads Segmentation of reference image already exists; reading from disk Segmentation of floating image already exists; reading from disk Linear registration Computing centroids and estimating affine transform Reading reference image Deforming reference image to reference space Deforming reference segmentation to reference space Normalizing intensities of reference image Reading floating image Deforming floating image to reference space Deforming floating segmentation to reference space Normalizing intensities of floating image 2023-10-02 11:16:08.118592: E tensorflow/compiler/xla/stream_executor/cuda/cuda_driver.cc:266] failed call to cuInit: CUDA_ERROR_NO_DEVICE: no CUDA-capable device is detected 2023-10-02 11:16:08.118640: I tensorflow/compiler/xla/stream_executor/cuda/cuda_diagnostics.cc:168] retrieving CUDA diagnostic information for host: kaibo-Alienware-Aurora-R13 2023-10-02 11:16:08.118647: I tensorflow/compiler/xla/stream_executor/cuda/cuda_diagnostics.cc:175] hostname: kaibo-Alienware-Aurora-R13 2023-10-02 11:16:08.118766: I tensorflow/compiler/xla/stream_executor/cuda/cuda_diagnostics.cc:199] libcuda reported version is: 510.108.3 2023-10-02 11:16:08.118794: I tensorflow/compiler/xla/stream_executor/cuda/cuda_diagnostics.cc:203] kernel reported version is: 510.108.3 2023-10-02 11:16:08.118801: I tensorflow/compiler/xla/stream_executor/cuda/cuda_diagnostics.cc:309] kernel version seems to match DSO: 510.108.3 UserWarning: int_downsize is deprecated, use the int_resolution parameter. UserWarning: unet_half_res is deprecated, use the svf_resolution parameter. ./easyreg.sh: line 3: 1588985 Killed mri_easyreg --ref ./mni152_t2_strip.nii.gz --flo $subject --ref_seg ./mni152_t2_strip_parc.nii.gz --flo_seg "${subject/.nii.gz/_parc.nii.gz}" --flo_reg "${subject/.nii.gz/_moved.nii.gz}" --fwd_field "${subject/.nii.gz/_fwd_fld.nii.gz}" --thread 24 ./sub-00001.nii.gz Done!
When I checked the folder, I saw only the parcellation results. Neither the moved floating image nor the forward field were generated.
I initially thought this might be a memory problem and I set --thread 1 but I ended up getting the same result (Killed).
I've searched the list and there was another error (MailScanner has detected a possible fraud attempt from "secure-web.cisco.com" claiming to be https://secure-web.cisco.com/1n2McJOwf1rxdgOs_zFgdELDnZoaGDEve7PAdSHf2tX-Vpe...https://secure-web.cisco.com/1oerdskR7ZTpxdkdU8iIXVp5sQdJ_BWDnyMHH3nMMFRZxQmw09udoBAQU3797SK7CqMgUzI2gQjf_BWb-NQyloanH4pjWR9TRjhtWcNq-p7mqnOEoyepCh4LTb98wYr-JoNaSVPY0fJEzkZQ2s6hg7OgZd-OgDH_pzZvgxj7pEyKf7-AS4RRrzFjuQPVpAyBK5HcAf7tsCGEdO90xpQg9YVMXxlt7Oaok7p5ojtiawjtpLaTqDRyY8Dn34pA1ULAoD18zr2LboaYdjC4hU0edeFOss2Ijsna8mF4G03aa1tRzLNFV4tMznQDO-0-94ZhJTf1FeYXes_TvCWMWMndT5g/https%3A%2F%2Fwww.mail-archive.com%2Ffreesurfer%40nmr.mgh.harvard.edu%2Fmsg75001.html) similar to mine. But I don't think mine was related. Can anyone provide any insight into this?
FreeSurfer version: freesurfer-linux-ubuntu22_x86_64-7.4.1-20230614-7eb8460 Platform: Ubuntu 22.04.2 LTS I am running the script on 12th Gen Intel® Core™ i9-12900KF × 24 with a 64.0 GiB memory and NVIDIA Corporation GA102 [GeForce RTX 3090].
Thanks, Kaibo
External Email - Use Caution
Hi,
I have 64 GB RAM.
Best, Kaibo ________________________________ From: freesurfer-bounces@nmr.mgh.harvard.edu freesurfer-bounces@nmr.mgh.harvard.edu on behalf of Iglesias Gonzalez, Juan E. JIGLESIASGONZALEZ@mgh.harvard.edu Sent: Monday, October 2, 2023 6:40:19 PM To: Freesurfer support list freesurfer@nmr.mgh.harvard.edu Subject: Re: [Freesurfer] mri_easyreg error: Killed
You don't often get email from jiglesiasgonzalez@mgh.harvard.edu. Learn why this is importanthttps://secure-web.cisco.com/17Hhs58uou4wOlI8yITeSP2vCVCaYISuevgqmF-YP1aabO0yJLZEY01E_Yx8Bn2sZySZ_RSFunJWlWCzM5Hz32SENnhx-Gd5au7LA4zbdbYiFIrUjy-o1x2wi0Ad1b-TyaBnVl8tKJLnKJD_rWzV0YcYawdMrpVYW2lvjLzOhdZ0d1vP1Wa6pOt0r17IDubjn3G9qZcfwhPpUtnrFbNP7e7iSzKd45MJ08qeAr4zZhfc1KhhV-LRIGybBEDceqj3QKZ3r4e2oESXKl6_BZXbjfaqRiC14Zchq2v7mh0wxMgmIPz2INPKQ_7LVF0zn8bFQ/https%3A%2F%2Faka.ms%2FLearnAboutSenderIdentification
External Email - Use Caution
Dear Kaibo,
How much RAM does your machine have?
Cheers,
/Eugenio
--
Juan Eugenio Iglesias
http://secure-web.cisco.com/1FppblFrwV_QhjdZlJJ-sabIQxbb2FzUuN1O5WbYp6pW30cb...
From: freesurfer-bounces@nmr.mgh.harvard.edu freesurfer-bounces@nmr.mgh.harvard.edu on behalf of Tang, Kaibo ktang@unc.edu Date: Monday, October 2, 2023 at 8:43 AM To: freesurfer@nmr.mgh.harvard.edu freesurfer@nmr.mgh.harvard.edu Subject: [Freesurfer] mri_easyreg error: Killed
External Email - Use Caution
Hi FreeSurfer Developers,
I'm attempting to register two T2 images using mri_easyreg (FreeSurfer 7.4.1). This is what my bash code looks like:
#!/bin/bash
for subject in ./sub-?????.nii.gz
do
mri_easyreg --ref ./mni152_t2_strip.nii.gz --flo $subject \
--ref_seg ./mni152_t2_strip_parc.nii.gz \
--flo_seg "${subject/.nii.gz/_parc.nii.gz}" \
--flo_reg "${subject/.nii.gz/_moved.nii.gz}" \
--fwd_field "${subject/.nii.gz/_fwd_fld.nii.gz}" \
--thread 24
subject+=" Done!"
echo $subject
done
This is what the output looks like when I execute the bash script:
2023-10-02 11:15:58.965124: I tensorflow/core/util/port.cc:110] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.
2023-10-02 11:15:58.988396: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.
To enable the following instructions: AVX2 AVX_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.
2023-10-02 11:15:59.313149: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT
using 24 threads
Segmentation of reference image already exists; reading from disk
Segmentation of floating image already exists; reading from disk
Linear registration
Computing centroids and estimating affine transform
Reading reference image
Deforming reference image to reference space
Deforming reference segmentation to reference space
Normalizing intensities of reference image
Reading floating image
Deforming floating image to reference space
Deforming floating segmentation to reference space
Normalizing intensities of floating image
2023-10-02 11:16:08.118592: E tensorflow/compiler/xla/stream_executor/cuda/cuda_driver.cc:266] failed call to cuInit: CUDA_ERROR_NO_DEVICE: no CUDA-capable device is detected
2023-10-02 11:16:08.118640: I tensorflow/compiler/xla/stream_executor/cuda/cuda_diagnostics.cc:168] retrieving CUDA diagnostic information for host: kaibo-Alienware-Aurora-R13
2023-10-02 11:16:08.118647: I tensorflow/compiler/xla/stream_executor/cuda/cuda_diagnostics.cc:175] hostname: kaibo-Alienware-Aurora-R13
2023-10-02 11:16:08.118766: I tensorflow/compiler/xla/stream_executor/cuda/cuda_diagnostics.cc:199] libcuda reported version is: 510.108.3
2023-10-02 11:16:08.118794: I tensorflow/compiler/xla/stream_executor/cuda/cuda_diagnostics.cc:203] kernel reported version is: 510.108.3
2023-10-02 11:16:08.118801: I tensorflow/compiler/xla/stream_executor/cuda/cuda_diagnostics.cc:309] kernel version seems to match DSO: 510.108.3
UserWarning: int_downsize is deprecated, use the int_resolution parameter.
UserWarning: unet_half_res is deprecated, use the svf_resolution parameter.
./easyreg.sh: line 3: 1588985 Killed mri_easyreg --ref ./mni152_t2_strip.nii.gz --flo $subject --ref_seg ./mni152_t2_strip_parc.nii.gz --flo_seg "${subject/.nii.gz/_parc.nii.gz}" --flo_reg "${subject/.nii.gz/_moved.nii.gz}" --fwd_field "${subject/.nii.gz/_fwd_fld.nii.gz}" --thread 24
./sub-00001.nii.gz Done!
When I checked the folder, I saw only the parcellation results. Neither the moved floating image nor the forward field were generated.
I initially thought this might be a memory problem and I set --thread 1 but I ended up getting the same result (Killed).
I've searched the list and there was another error (MailScanner has detected a possible fraud attempt from "secure-web.cisco.com" claiming to be https://secure-web.cisco.com/1Isa_VC0nqDChVRzBk_FN9quL_94Cvp41-ZZvNimRwjniG6...https://secure-web.cisco.com/1oerdskR7ZTpxdkdU8iIXVp5sQdJ_BWDnyMHH3nMMFRZxQmw09udoBAQU3797SK7CqMgUzI2gQjf_BWb-NQyloanH4pjWR9TRjhtWcNq-p7mqnOEoyepCh4LTb98wYr-JoNaSVPY0fJEzkZQ2s6hg7OgZd-OgDH_pzZvgxj7pEyKf7-AS4RRrzFjuQPVpAyBK5HcAf7tsCGEdO90xpQg9YVMXxlt7Oaok7p5ojtiawjtpLaTqDRyY8Dn34pA1ULAoD18zr2LboaYdjC4hU0edeFOss2Ijsna8mF4G03aa1tRzLNFV4tMznQDO-0-94ZhJTf1FeYXes_TvCWMWMndT5g/https%3A%2F%2Fwww.mail-archive.com%2Ffreesurfer%40nmr.mgh.harvard.edu%2Fmsg75001.html) similar to mine. But I don't think mine was related. Can anyone provide any insight into this?
FreeSurfer version: freesurfer-linux-ubuntu22_x86_64-7.4.1-20230614-7eb8460
Platform: Ubuntu 22.04.2 LTS
I am running the script on 12th Gen Intel® Core™ i9-12900KF × 24 with a 64.0 GiB memory and NVIDIA Corporation GA102 [GeForce RTX 3090].
Thanks,
Kaibo
freesurfer@nmr.mgh.harvard.edu
-
Iglesias Gonzalez, Juan E. -
Tang, Kaibo