Output with Errors

[bijendrabio]

Hello, After running a DeepTE.py, I was able to get the output but with following error. So curious if the run/output is incomplete or should I ignore this error.

I thought the error was due to tensorflow-gpu incompatibility, so I tried setting up the tensorflow-cpu but that didn't work. Kindly suggest!

ERROR: Using TensorFlow backend. WARNING:tensorflow:From /home/miniconda3/envs/DeepTEpy36/lib/python3.6/site-packages/keras/backend/tensorflow_backend.py:4070: The name tf.nn.max_pool is deprecated. Please use tf.nn.max_pool2d instead.

2022-08-08 23:24:48.689611: I tensorflow/core/platform/cpu_feature_guard.cc:142] Your CPU supports instructions that this TensorFlow binary was not compiled to use: SSE4.1 SSE4.2 AVX AVX2 FMA 2022-08-08 23:24:48.711068: I tensorflow/core/platform/profile_utils/cpu_utils.cc:94] CPU Frequency: 2095000000 Hz 2022-08-08 23:24:48.719119: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x55bbcb0b9810 executing computations on platform Host. Devices: 2022-08-08 23:24:48.719162: I tensorflow/compiler/xla/service/service.cc:175] StreamExecutor device (0): , 2022-08-08 23:24:48.724248: I tensorflow/stream_executor/platform/default/dso_loader.cc:53] Could not dlopen library 'libcuda.so.1'; dlerror: libcuda.so.1: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /opt/gridengine/lib/lx-amd64:/opt/openmpi/lib:/opt/python/lib:/opt/perl/lib 2022-08-08 23:24:48.724280: E tensorflow/stream_executor/cuda/cuda_driver.cc:318] failed call to cuInit: UNKNOWN ERROR (303) 2022-08-08 23:24:48.724316: I tensorflow/stream_executor/cuda/cuda_diagnostics.cc:156] kernel driver does not appear to be running on this host (biocomp-2-4.local): /proc/driver/nvidia/version does not exist 2022-08-08 23:24:48.757916: W tensorflow/compiler/jit/mark_for_compilation_pass.cc:1412] (One-time warning): Not using XLA:CPU for cluster because envvar TF_XLA_FLAGS=--tf_xla_cpu_global_jit was not set. If you want XLA:CPU, either set that envvar, or use experimental_jit_scope to enable XLA:CPU. To confirm that XLA is active, pass --vmodule=xla_compilation_cache=1 (as a proper command-line flag, not via TF_XLA_FLAGS) or set the envvar XLA_FLAGS=--xla_hlo_profile. WARNING:tensorflow:From /home/miniconda3/envs/DeepTEpy36/lib/python3.6/site-packages/keras/backend/tensorflow_backend.py:422: The name tf.global_variables is deprecated. Please use tf.compat.v1.global_variables instead.

Regards,

[songliVT]

This looks like a tensorflow version issue. Which tensorflow version did you use?

Song

On Tue, Aug 9, 2022 at 8:15 AM bijendrabio @.***> wrote:

Hello, After running a DeepTE.py, I was able to get the output but with following error. So curious if the run/output is incomplete or should I ignore this error.

I thought the error was due to tensorflow-gpu incompatibility, so I tried setting up the tensorflow-cpu but that didn't work. Kindly suggest!

ERROR: Using TensorFlow backend. WARNING:tensorflow:From /home/miniconda3/envs/DeepTEpy36/lib/python3.6/site-packages/keras/backend/tensorflow_backend.py:4070: The name tf.nn.max_pool is deprecated. Please use tf.nn.max_pool2d instead.

2022-08-08 23:24:48.689611: I tensorflow/core/platform/cpu_feature_guard.cc:142] Your CPU supports instructions that this TensorFlow binary was not compiled to use: SSE4.1 SSE4.2 AVX AVX2 FMA 2022-08-08 23:24:48.711068: I tensorflow/core/platform/profile_utils/cpu_utils.cc:94] CPU Frequency: 2095000000 Hz 2022-08-08 23:24:48.719119: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x55bbcb0b9810 executing computations on platform Host. Devices: 2022-08-08 23:24:48.719162: I tensorflow/compiler/xla/service/service.cc:175] StreamExecutor device (0): , 2022-08-08 23:24:48.724248: I tensorflow/stream_executor/platform/default/dso_loader.cc:53] Could not dlopen library 'libcuda.so.1'; dlerror: libcuda.so.1: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /opt/gridengine/lib/lx-amd64:/opt/openmpi/lib:/opt/python/lib:/opt/perl/lib 2022-08-08 23:24:48.724280: E tensorflow/stream_executor/cuda/cuda_driver.cc:318] failed call to cuInit: UNKNOWN ERROR (303) 2022-08-08 23:24:48.724316: I tensorflow/stream_executor/cuda/cuda_diagnostics.cc:156] kernel driver does not appear to be running on this host (biocomp-2-4.local): /proc/driver/nvidia/version does not exist 2022-08-08 23:24:48.757916: W tensorflow/compiler/jit/mark_for_compilation_pass.cc:1412] (One-time warning): Not using XLA:CPU for cluster because envvar TF_XLA_FLAGS=--tf_xla_cpu_global_jit was not set. If you want XLA:CPU, either set that envvar, or use experimental_jit_scope to enable XLA:CPU. To confirm that XLA is active, pass --vmodule=xla_compilation_cache=1 (as a proper command-line flag, not via TF_XLA_FLAGS) or set the envvar XLA_FLAGS=--xla_hlo_profile. WARNING:tensorflow:From /home/miniconda3/envs/DeepTEpy36/lib/python3.6/site-packages/keras/backend/tensorflow_backend.py:422: The name tf.global_variables is deprecated. Please use tf.compat.v1.global_variables instead.

Regards,

— Reply to this email directly, view it on GitHub https://github.com/LiLabAtVT/DeepTE/issues/19, or unsubscribe https://github.com/notifications/unsubscribe-auth/ACEEENQQN5CYCQ3FDGUATCDVYJDX7ANCNFSM56ASEZMA . You are receiving this because you are subscribed to this thread.Message ID: @.***>

-- Associate Professor in Plant Genomics and Bioinformatics School of Plant and Environmental Sciences Virginia Polytechnic Institute and State University

zoom https://virginiatech.zoom.us/j/8790572835

[yanhaidong1]

Hey,

I guess these warnings were generated probably because DeepTEs were developed using old package loadings. I do not think the results would have problems once you got the results. Also, if there are something wrong with gpu settings, the system probably uses cpu instead to run the process. Here is one link that may help you to figure it out towards 'Could not dlopen library 'libcuda.so.1'; dlerror: libcuda.so.1: cannot open shared object file: No such file or directory'. (https://stackoverflow.com/questions/54249577/importerror-libcuda-so-1-cannot-open-shared-object-file)

Best, Haidong

[bijendrabio]

@songliVT @yanhaidong1 Thank you for your response.

I am using tensorflow version 1.14 as recommended in the .

In the output, I noted that few TEs do not show complete labelling(shown example below). So curious if this may be due to result of the aforementioned error?

TE_00005418_LTR#LTR/unknown ClassI_LTR_Gypsy TE_00005419_LTR#LTR/unknown ClassI_LTR TE_00005423_LTR#LTR/unknown ClassI_LTR_Gypsy TE_00005427_LTR#LTR/unknown ClassI_LTR_Copia

Also, I got following ERROR while using DeepTE_domain.py; note: hmmer version 3.1b2;

cp: cannot stat ‘/users/tools/DeepTE/example_data/supplement//minifam*’: No such file or directory

Error: File existence/permissions problem in trying to open HMM file working//minifam. HMM file working//minifam not found (nor an .h3m binary of it); also looked in PFAMDB

Kindly Suggest!

[yanhaidong1]

Hi bijendrabio,

For the first question, would you please send me this input file that I can test it. For the second question, would you please tell me the command line you run for the DeepTE_domain.py. It looks like we need to provide a right path such as /users/tools/DeepTE/example_data/supfile_dir/ other than '/supplement'.

Best, Haidong