[General boards] [Fall 2018 courses] [Summer 2018 courses] [Winter 2018 courses] [Older or newer terms]

Running A3


#1

When I try to run A3 on the lab machines, the following message is printed and then nothing happens:

b2240-10:~/nlp/assignment3$ python3.6 model.py 
================================================================================
INITIALIZING
================================================================================
Loading word embeddings...there are 4003 word embeddings.
Determining POS tags...there are 17 tags.
Determining deprel labels...there are 39 deprel labels.
Getting training data...there are 1892336 samples.
Getting dev data...there are 1700 samples.
Getting test data...there are 2416 samples.
Word feat size: 18, tag feat size: 18, deprel feat size: 12, classes size: 83
2018-11-29 16:29:43.544734: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE4.1 instructions, but these are available on your machine and could speed up CPU computations.
2018-11-29 16:29:43.544759: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE4.2 instructions, but these are available on your machine and could speed up CPU computations.
2018-11-29 16:29:43.544771: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use AVX instructions, but these are available on your machine and could speed up CPU computations.
2018-11-29 16:29:43.544778: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use AVX2 instructions, but these are available on your machine and could speed up CPU computations.
2018-11-29 16:29:43.544786: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use FMA instructions, but these are available on your machine and could speed up CPU computations.

Anyone knows how to fix this?


#2

For anyone with similar issues, avoid that lab (BA2240). For unknown reasons, it looks like starting a TF GPU session doesn’t work. Try another lab, or ssh into coral01-coral05.


#3

I’m in BA3175 and I’m getting the same message as the one in OP


#4

I’m in 3185 and I get the same message as well. Code works fine on my machine