def test_fast__SerializePatternNet(): def method(model): # enough for test purposes, only pattern application is tested here # pattern computation is tested separately. # assume that one dim weights are biases, drop them. patterns = [x for x in model.get_weights() if len(x.shape) > 1] return PatternNet(model, patterns=patterns) dryrun.test_serialize_analyzer(method, "mnist.log_reg")
def test_fast_serialize(method, kwargs): def analyzer(model): return method(model, **kwargs) dryrun.test_serialize_analyzer(analyzer, "trivia.*:mnist.log_reg")
def test_fast__SerializeReverseAnalyzerkBase(): def method(model): return Gradient(model) dryrun.test_serialize_analyzer(method, "trivia.*:mnist.log_reg")
def test_fast__SerializeRandom(): def method(model): return Random(model) dryrun.test_serialize_analyzer(method, "trivia.*:mnist.log_reg")
def test_fast__SerializeLRPAlpha2Beta1(): def method(model): return LRPAlpha2Beta1(model) dryrun.test_serialize_analyzer(method, "trivia.*:mnist.log_reg")
def test_fast__SerializeGaussianSmoother(): def method(model): return GaussianSmoother(Gradient(model)) dryrun.test_serialize_analyzer(method, "trivia.*:mnist.log_reg")
def test_fast__SerializeAugmentReduceBase(): def method(model): return AugmentReduceBase(Gradient(model)) dryrun.test_serialize_analyzer(method, "trivia.*:mnist.log_reg")
def test_fast__SerializePathIntegrator(): def method(model): return PathIntegrator(Gradient(model)) dryrun.test_serialize_analyzer(method, "trivia.*:mnist.log_reg")