Closed avitalsteiman closed 4 years ago
Hi @avitalsteiman ,
What is the version of your GPU and CUDA? Maybe you can add "CUDA_VISIABLE_DEVICES=0" in front of the command like:
CUDA_VISIABLE_DEVICES=0 deepsignal call_mods --input_path deepSignal_NPmeT1_fast5_CpG_signalFeature.tsv --model_path deepSignalModel/model.CpG.R9.4_1D.human_hx1.bn17.sn360.v0.1.7+/bn_17.sn_360.epoch_9.ckpt --result_file deepSignal_NPmeT1_fast5.CpG.call_mods.tsv --nproc 10 --is_gpu yes
and see what happens.
Best, Peng
Hi, Thanks for the reply. I am using NVIDIA-SMI 440.33.01 Driver Version: 440.33.01 CUDA Version: 10.2 I installed tensorflow 1.8 (after trying with the most updated version of tensorflow, and older versions and not getting deepsignal to run at all). I tried your suggestion, it did not seem to work.
I'm getting this message:
write_process started.. 2020-04-05 11:54:31.412546: I tensorflow/core/platform/cpu_feature_guard.cc:140] Your CPU supports instructions that this TensorFlow binary was not compiled to use: SSE4.1 SSE4.2 AVX AVX2 AVX512F FMA 2020-04-05 11:54:31.413228: I tensorflow/core/common_runtime/process_util.cc:63] Creating new thread pool with default inter op setting: 2. Tune using inter_op_parallelism_threads for best performance.
Could it have something to do with it?
Thank you again, Avital
On Fri, Apr 3, 2020 at 4:06 AM Peng Ni notifications@github.com wrote:
Hi @avitalsteiman https://github.com/avitalsteiman ,
What is the version of your GPU and CUDA? Maybe you can add "CUDA_VISIABLE_DEVICES=0" in front of the command like: CUDA_VISIABLE_DEVICES=0 deepsignal call_mods --input_path deepSignal_NPmeT1_fast5_CpG_signalFeature.tsv --model_path deepSignalModel/model.CpG.R9.4_1D.human_hx1.bn17.sn360.v0.1.7+/bn_17.sn_360.epoch_9.ckpt --result_file deepSignal_NPmeT1_fast5.CpG.call_mods.tsv --nproc 10 --is_gpu yes
and see what happens.
Best, Peng
— You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub https://github.com/bioinfomaticsCSU/deepsignal/issues/40#issuecomment-608173459, or unsubscribe https://github.com/notifications/unsubscribe-auth/ALD3LR5G7H6HLYSYBIZ4IHLRKUZCHANCNFSM4L267U3A .
--
@avitalsteiman , I suggest that you install tensorflow-gpu 1.13.1 for your cuda version:
# install using conda
conda install -c anaconda tensorflow-gpu==1.13.1
# or install using pip
pip install 'tensorflow-gpu==1.13.1'
It should work.
Best, Peng
Thank you. That seems to have done the trick. Just adding that to get it to work, I had to uninstall tensorflow-gpu 1.8 and then re-install tensorflow 1.13.1 (as per your instructions).
Regards, Avital
On Sun, Apr 5, 2020 at 2:30 PM Peng Ni notifications@github.com wrote:
@avitalsteiman https://github.com/avitalsteiman , I suggest that you install tensorflow-gpu 1.13.1 for your cuda version:
install using conda
conda install -c anaconda tensorflow-gpu==1.13.1
or install using pip
pip install 'tensorflow-gpu==1.13.1'
It should work.
Best, Peng
— You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub https://github.com/bioinfomaticsCSU/deepsignal/issues/40#issuecomment-609401719, or unsubscribe https://github.com/notifications/unsubscribe-auth/ALD3LRZP2YEJEPYTXO37SRTRLBTV7ANCNFSM4L267U3A .
--
Hi, I'm running deepsignal with the following command:
deepsignal call_mods --input_path deepSignal_NPmeT1_fast5_CpG_signalFeature.tsv --model_path deepSignalModel/model.CpG.R9.4_1D.human_hx1.bn17.sn360.v0.1.7+/bn_17.sn_360.epoch_9.ckpt --result_file deepSignal_NPmeT1_fast5.CpG.call_mods.tsv --nproc 10 --is_gpu yes
It is running (with many warnings) but for some reason rather than running on the gpu it is running on the cpu(s) and taking a very long time. I though this may be similar to issue #38 however, I checked and I am using the model for deepsignal v0.1.7 (which is what I seem to be running).
I'm pasting the warnings, below. Thank you for your help, Avital