diff --git a/scripts/testword2vec.ssc b/scripts/testword2vec.ssc new file mode 100755 index 00000000..f8d9d533 --- /dev/null +++ b/scripts/testword2vec.ssc @@ -0,0 +1,27 @@ +import BIDMach.networks.Word2Vec + +val mdir = "/code/word2vec/data/"; + +val (nn, opts) = Word2Vec.learner(mdir+"data%03d.imat.lz4"); + +opts.nstart = 0; +opts.nend = 7; +opts.npasses = 1; +opts.batchSize = 100000; +opts.lrate = 1e-3f; +opts.vexp = 0.5f +opts.nreuse = 5 +opts.dim = 300 +opts.vocabSize = 800000 + +//opts.useGPU = false; +//opts.autoReset = false; +//Mat.useMKL = false; + +nn.train + +val mod = nn.model.asInstanceOf[Word2Vec] + +//saveFMat(mdir+"model0.fmat.lz4", FMat(mod.modelmats(0))) + +//saveFMat(mdir+"model1.fmat.lz4", FMat(mod.modelmats(1)))