Week Seven: 10/16-10/20

After training the dataset last week, for this week, I was finally able to move on to testing.

I ran the command below to accomplish testing:

Boost_DIR=/opt/boost-1.63.0-gcc4.9/ OpenCV_DIR=/opt/opencv2.4-gcc4.9/ PKG_CONFIG_PATH=/opt/libzip-1.2.0-gcc4.9/lib/pkgconfig PATH=/opt/openexr-2.2.0-bin/bin:/opt/protobuf-3.2.0-gcc4.9/bin/:/opt/python2.7-gcc4.9/bin:$PATH PYTHONPATH=/opt/dlib-19.3-gcc4.9/:/opt/opencv2.4-gcc4.9/lib:/opt/opencv2.4-gcc4.9/lib/python2.7/site-packages/ LD_LIBRARY_PATH=/opt/openexr-2.2.0-bin/lib:/opt/python2.7-gcc4.9/lib/:/opt/boost-1.63.0-gcc4.9/lib/:/opt/opencv2.4-gcc4.9/lib/:/opt/protobuf-3.2.0-gcc4.9/lib:/opt/glog-gcc4.9-bin/lib:/opt/gflags-gcc4.9-bin/lib:/opt/snappy-gcc4.9-bin/lib/:/opt/cuda/lib64/:/opt/libzip-1.2.0-gcc4.9/lib/ python BiMPM/src/SentenceMatchDecoder.py --in_path Quora_question_pair_partition/test.tsv --word_vec_path Quora_question_pair_partition/wordvec.txt --mode prediction --model_prefix models/SentenceMatch.sample --out_path test.prediction 

 

It first loaded the configurations, then the vocabs.

word_vocab: (106686, 300)                                           label_vocab: (3, 2)                                                 char_vocab: (1199, 20)      

 

Next, it built the SentenceMatchDataStream.

Build SentenceMatchDataStream ...                                   Number of instances in testDataStream: 10000                        Number of batches in testDataStream: 167     

 

When it finished running, I got similar results from when I trained the data.

Accuracy for test set is 87.26