jisraeli / deepbind Goto Github PK

Dear Deepbind team,

I'm interested in using the methods discussed in Deepbind to train a new model with a slight twist; I want to slightly edit the model architecture. Can you provide me with the code that you used to train deepbind models?

Thanks!

-Eugene

When I run make on libs/smat/src I get the following error -

./smat_cuda/launch_util.h(67): error: function "atomicAdd(double *, double)" has already been defined

1 error detected in the compilation of "/tmp/tmpxft_00000e6b_00000000-4_reduce.cpp4.ii".
makefile:230: recipe for target '../build/release/obj/SMAT_CUDA/reduce.o' failed
make: *** [../build/release/obj/SMAT_CUDA/reduce.o] Error 2

I think it is happening because I am using CUDA 9.2 and the code doesn't support it. The CUDA samples from NVIDIA were running perfectly. Please look into it.

Thanks

In conda environment, I am trying to install DeepBind, and got the following error message.
Please help me, I need to get something done with DeepBind before Monday.
Thank you!

(base) kong@kong-HP-Laptop-17-ca0xxx:~/Documents/Personal_Add/Apple/Swiss/Hall_Heim/Articles$ kipoi env create DeepBind
INFO [kipoi.cli.env] Writing environment file: /tmp/kipoi/envfiles/5070a3c5
INFO [kipoi.cli.env] Loading model: DeepBind description
INFO [kipoi.sources] Update /home/kong/.kipoi/models/
Already up to date.
INFO [kipoi.cli.env] Found 927 models under the model name: DeepBind. Merging dependencies for all
INFO [kipoi.cli.env] Environment name: kipoi-DeepBind
INFO [kipoi.cli.env] Output env file: /tmp/kipoi/envfiles/5070a3c5/kipoi-DeepBind.yaml
INFO [kipoi.cli.env] Done writing the environment file!
Traceback (most recent call last):
File "/home/kong/Software/anaconda3/bin/kipoi", line 8, in
sys.exit(main())
File "/home/kong/Software/anaconda3/lib/python3.7/site-packages/kipoi/main.py", line 105, in main
command_fn(args.command, sys.argv[2:])
File "/home/kong/Software/anaconda3/lib/python3.7/site-packages/kipoi/cli/env.py", line 696, in cli_main
command_fn(args.command, raw_args[1:])
File "/home/kong/Software/anaconda3/lib/python3.7/site-packages/kipoi/cli/env.py", line 457, in cli_create
envdb.save()
File "/home/kong/Software/anaconda3/lib/python3.7/site-packages/kipoi/env_db.py", line 128, in save
self.db.purge()
File "/home/kong/Software/anaconda3/lib/python3.7/site-packages/tinydb/database.py", line 250, in getattr
return getattr(self.table(self.default_table_name), name)
AttributeError: 'Table' object has no attribute 'purge'

This python fails with the aforementioned CUDA error. The error looks like:

Predicting... ['TF_34']

AssertionError: CUDA error in Memcpy2DAsync: initialization error.
copy_from(...) raised an exception
AssertionError: CUDA error in Memcpy2DAsync: initialization error.
in smat_cuda/copy.cu:190
Traceback (most recent call last):
File "libs/kangaroo/kangaroo/predict.py", line 405, in call
model = load_model(modelinfo)
File "libs/kangaroo/kangaroo/predict.py", line 107, in load_model
model = cp.load(f)
File "libs/smat/py/smat/smat.py", line 230, in setstate
dll.api_copy_from(self._ptr,data.ctypes.data_as(c_void_p),data.strides[0],data.strides[1]) # Copy from data
File "libs/smat/py/smat/smat_dll.py", line 183, in call
raise SmatException(msg)
SmatException: copy_from(...) raised an exception
AssertionError: CUDA error in Memcpy2DAsync: initialization error.
in smat_cuda/copy.cu:190

Error in Worker...
copy_from(...) raised an exception
AssertionError: CUDA error in Memcpy2DAsync: initialization error.
in smat_cuda/copy.cu:190
Traceback (most recent call last):
File "libs/kangaroo/kangaroo/predict.py", line 405, in call
model = load_model(modelinfo)
File "libs/kangaroo/kangaroo/predict.py", line 107, in load_model
model = cp.load(f)
File "libs/smat/py/smat/smat.py", line 230, in setstate
dll.api_copy_from(self._ptr,data.ctypes.data_as(c_void_p),data.strides[0],data.strides[1]) # Copy from data
File "libs/smat/py/smat/smat_dll.py", line 183, in call
raise SmatException(msg)
SmatException: copy_from(...) raised an exception
AssertionError: CUDA error in Memcpy2DAsync: initialization error.
in smat_cuda/copy.cu:190

demo_convnet.py run with error for the reason of libsmat_cudnn.so
code/libs/smat/py/demo_convnet.py
$ demo_convnet.py --device 1
code/libs/smat/build/release/bin/libsmat_cudnn.so: cannot open shared object file: No such file or directory
and then I found that libsmat_cudnn.so is not being compiled in folder code/libs/smat/build/release/bin
check the makefile , found smat_cudnn is not compiled by default.
so I try to re-compile, and failed with

collect2: error: ld returned 1 exit status
make: *** [../build/release/bin/libsmat_cudnn.so] Error 1


sadly failed， please help！

Hello I am new to to deep learning modules and I am using DeepBind for comparison with other tools, I am getting a following error when I run
python deepbind_train_encode.py top calib,train,test,report

-------------- calib: ARID3A_K562_ARID3A_(sc-8821)Stanford --------------
load_traindata: ARID3A_K562_ARID3A(sc-8821)_Stanford
calibrating...
Failed to load extension deepity_smat:
attempt: build/release/bin/
reason: build/release/bin/libdeepity_smat.so: cannot open shared object file: No such file or directory
attempt: ../smat/build/release/bin/
reason: ../smat/build/release/bin/libdeepity_smat.so: cannot open shared object file: No such file or directory
attempt: libs/smat/build/release/bin/
reason: libs/smat/build/release/bin/libdeepity_smat.so: cannot open shared object file: No such file or directory
attempt: libs/deepity/build/release/bin/
reason: libs/deepity/build/release/bin/libdeepity_smat.so: cannot open shared object file: No such file or directory
attempt: libs/kangaroo/build/release/bin/
reason: libs/kangaroo/build/release/bin/libdeepity_smat.so: cannot open shared object file: No such file or directory
attempt: /usr/local/cuda-10.2/bin/
reason: /usr/local/cuda-10.2/bin/libdeepity_smat.so: cannot open shared object file: No such file or directory
attempt: /usr/local/sbin/
reason: /usr/local/sbin/libdeepity_smat.so: cannot open shared object file: No such file or directory
attempt: /usr/local/bin/
reason: /usr/local/bin/libdeepity_smat.so: cannot open shared object file: No such file or directory
attempt: /usr/sbin/
reason: /usr/sbin/libdeepity_smat.so: cannot open shared object file: No such file or directory
attempt: /usr/bin/
reason: /usr/bin/libdeepity_smat.so: cannot open shared object file: No such file or directory
attempt: /sbin/
reason: /sbin/libdeepity_smat.so: cannot open shared object file: No such file or directory
attempt: /bin/
reason: /bin/libdeepity_smat.so: cannot open shared object file: No such file or directory
attempt: /usr/games/
reason: /usr/games/libdeepity_smat.so: cannot open shared object file: No such file or directory
attempt: /usr/local/games/
reason: /usr/local/games/libdeepity_smat.so: cannot open shared object file: No such file or directory
attempt: /snap/bin$/
reason: /snap/bin$/libdeepity_smat.so: cannot open shared object file: No such file or directory
attempt: /home/aishwarya/deepbind/DeepBind/code/libs/smat/build/release/bin/
reason: /home/aishwarya/deepbind/DeepBind/code/libs/smat/build/release/bin/libdeepity_smat.so: cannot open shared object file: No such file or directory
attempt: ../deepity/build/release/bin/
reason: ../deepity/build/release/bin/libdeepity_smat.so: cannot open shared object file: No such file or directory

AssertionError: CUDA error: no kernel image is available for execution on the device.
terminate called after throwing an instance of 'std::runtime_error'
what(): AssertionError: CUDA error: no kernel image is available for execution on the device.
in smat_cuda/cuda_context.cpp:107

When I try to make in kangaroo_smat, the first execution of nvcc raise an error:
nvcc -c -o ../build/release/obj/KANGAROO_SMAT/autotune.o -I. -I/usr/local/cuda/include -I../../smat/src -DKANGAROO_SMAT_EXPORTS -use_fast_math -gencode arch=compute_50,code=sm_50 -include nvcc_preinclude.h -maxrregcount 64 -Xcompiler -m64,-fPIC,-fvisibility=hidden,--param,max-inline-recursive-depth=24,--param,max-inline-recursive-depth-auto=24,-O3, autotune.cu
/usr/local/cuda/include/cuda.h(60): error: "uint64_t" is ambiguous

1 error detected in the compilation of "/tmp/tmpxft_000020b5_00000000-7_autotune.cpp1.ii".
makefile:159: recipe for target '../build/release/obj/KANGAROO_SMAT/autotune.o' failed
make: *** [../build/release/obj/KANGAROO_SMAT/autotune.o] Error 2

What about it? I don't know where is the problem.
Thanks!
Mauro