Clean up bin mlf test

daniel-s-ingram · Nov 12, 2018 · d7101a2 · d7101a2
1 parent 8d87948
commit d7101a2
Show file tree

Hide file tree

Showing 2 changed files with 0 additions and 48 deletions.
diff --git a/Source/SequenceTrainingLib/gammacalculation.h b/Source/SequenceTrainingLib/gammacalculation.h
@@ -208,8 +208,6 @@ class GammaCalculation
                                                                    (const msra::math::ssematrixbase&) predstripe, (const msra::asr::simplesenonehmm&) m_hset,
                                                                    (msra::math::ssematrixbase&) dengammasstripe, (msra::math::ssematrixbase&) gammasbuffer /*empty, not used*/,
                                                                    lmf, wp, amf, boostmmifactor, seqsMBRmode, uidsstripe, boundariesstripe);
-            if (denavlogp < LOGZERO / 2)
-                return;
 
             objectValue += (ElemType)((numavlogp - denavlogp) * numframes);
 

diff --git a/Tests/EndToEndTests/CNTKv2Python/Examples/htk_deserializer_test.py b/Tests/EndToEndTests/CNTKv2Python/Examples/htk_deserializer_test.py
@@ -54,52 +54,6 @@ def test_htk_deserializers():
     assert True
     os.chdir(abs_path)
 
-def test_htk_binary_deserializers():
-    mbsize = 640
-    epoch_size = 1000 * mbsize
-    lr = [0.001]
-
-    feature_dim = 33
-    num_classes = 132
-    context = 2
-
-    os.chdir(data_path)
-
-    features_file = "glob_0000.scp"
-    labels_file = "mlf2.bin"
-
-    fd = HTKFeatureDeserializer(StreamDefs(
-        amazing_features = StreamDef(shape=feature_dim, context=(context,context), scp=features_file)))
-
-    ld = HTKMLFBinaryDeserializer(StreamDefs(awesome_labels = StreamDef(shape=num_classes, mlf=labels_file)))
-
-    reader = MinibatchSource([fd,ld])
-
-    features = C.sequence.input_variable(((2*context+1)*feature_dim))
-    labels = C.sequence.input_variable((num_classes))
-
-    model = Sequential([For(range(3), lambda : Recurrence(LSTM(256))),
-                        Dense(num_classes)])
-    z = model(features)
-    ce = C.cross_entropy_with_softmax(z, labels)
-    errs = C.classification_error    (z, labels)
-
-    learner = C.fsadagrad(z.parameters,
-                          lr=C.learning_parameter_schedule_per_sample(lr, epoch_size=epoch_size),
-                          momentum=C.momentum_schedule_per_sample(0.9990913221888589),
-                          gradient_clipping_threshold_per_sample=15, gradient_clipping_with_truncation=True)
-    progress_printer = C.logging.ProgressPrinter(freq=0)
-    trainer = C.Trainer(z, (ce, errs), learner, progress_printer)
-
-    input_map={ features: reader.streams.amazing_features, labels: reader.streams.awesome_labels }
-
-    # just run and verify it doesn't crash
-    for i in range(3):
-        mb_data = reader.next_minibatch(mbsize, input_map=input_map)
-        trainer.train_minibatch(mb_data)
-    assert True
-    os.chdir(abs_path)
-
 def test_multiple_mlf_files():
     os.chdir(data_path)