Errors with Installation

[Energyquantum]

Hi,

I have successfully installed the following: virtualenv e2e_awni source e2e_awni/bin/activate cd speech pip install -r requirements.txt

As the next step, should I install pytorch while virtualenv is activated or not?

The following errors occur If I install pytorch when virtualenv is activated:

(e2e_awni)kevin@DEVBOX2:~$ pip install http://download.pytorch.org/whl/cu80/torch-0.4.1-cp27-cp27mu-linux_x86_64.whl torch-0.4.1-cp27-cp27mu-linux_x86_64.whl is not a supported wheel on this platform. Storing debug log for failure in /home/zhme/.pip/pip.log

(e2e_awni)kevin@DEVBOX2:~$ pip install http://download.pytorch.org/whl/cu80/torch-0.4.1-cp27-cp27m-linux_x86_64.whl torch-0.4.1-cp27-cp27m-linux_x86_64.whl is not a supported wheel on this platform. Storing debug log for failure in /home/zhme/.pip/pip.log

I can successfully install pytorch when virtualenv is deactivated. But the following errors occur when I run pytest under speech/tests after "make".

(e2e_awni)kevin@DEVBOX2:~/speech/tests$ pytest

================================================================================== ERRORS =================================================================================== _ ERROR collecting ctc_test.py __ ImportError while importing test module '/home/kevin/speech/tests/ctc_test.py'. Hint: make sure your test modules/packages have valid Python names. Traceback: ctc_test.py:2: in import torch E ImportError: No module named torch ____ ERROR collecting io_test.py ____ ImportError while importing test module '/home/kevin/speech/tests/io_test.py'. Hint: make sure your test modules/packages have valid Python names. Traceback: io_test.py:3: in import speech.models E ImportError: No module named speech.models __ ERROR collecting loader_test.py __ ImportError while importing test module '/home/kevin/speech/tests/loader_test.py'. Hint: make sure your test modules/packages have valid Python names. Traceback: loader_test.py:3: in from speech import loader E ImportError: No module named speech __ ERROR collecting model_test.py ___ ImportError while importing test module '/home/kevin/speech/tests/model_test.py'. Hint: make sure your test modules/packages have valid Python names. Traceback: modeltest.py:3: in import torch E ImportError: No module named torch ERROR collecting seq2seq_test.py __ ImportError while importing test module '/home/kevin/speech/tests/seq2seq_test.py'. Hint: make sure your test modules/packages have valid Python names. Traceback: seq2seq_test.py:3: in import torch E ImportError: No module named torch ___ ERROR collecting wave_test.py ___ ImportError while importing test module '/home/kevin/speech/tests/wave_test.py'. Hint: make sure your test modules/packages have valid Python names. Traceback: wave_test.py:4: in import speech.utils.wave as wave E ImportError: No module named speech.utils.wave !!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!! Interrupted: 6 errors during collection !!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!! ========================================================================== 6 error in 0.23 seconds ==========================================================================

Could you help me out?

Thank you.

[awni]

Does python -c 'import torch' work? If not looks like you have a problem with your torch installation which is the first thing you should fix.

[ghost]

I too had this problem, and with python -c 'import torch' working. What worked for me was to manually run each command for the targets in the Makefile, and then no errors arose from import torch. Because I normally reserve the command python for working with 2.7 and command python3 for my current 3.x version (for which PyTorch is installed), interestingly doing an alias python=python3 also ended up in still having errors when running the Makefile. But changing the Makefile to use python3 wherever it stated python, actually DID end up in being built successfully.