def test_usrnn_iter_fit(): raise SkipTest() X = np.random.standard_normal((10, 5, 2)).astype(theano.config.floatX) X, = theano_floatx(X) rnn = UnsupervisedRnn(2, [10], 3, hidden_transfers=['tanh'], loss=lambda x: T.log(x), max_iter=10) for i, info in enumerate(rnn.iter_fit(X)): if i >= 10: break
def test_usrnn_transform(): raise SkipTest() X = np.random.standard_normal((10, 5, 2)).astype(theano.config.floatX) X, = theano_floatx(X) rnn = UnsupervisedRnn(2, [10], 3, hidden_transfers=['tanh'], loss=lambda x: T.log(x), max_iter=10) rnn.transform(X)
def test_usrnn_transform(): X = np.random.standard_normal((10, 5, 2)).astype(theano.config.floatX) rnn = UnsupervisedRnn(2, 10, 3, loss=lambda x: T.log(x), max_iter=10) rnn.transform(X)
def test_usrnn_iter_fit(): X = np.random.standard_normal((10, 5, 2)).astype(theano.config.floatX) rnn = UnsupervisedRnn(2, 10, 3, loss=lambda x: T.log(x), max_iter=10) for i, info in enumerate(rnn.iter_fit(X)): if i >= 10: break
def test_usrnn_transform(): X = np.random.standard_normal((10, 5, 2)) rnn = UnsupervisedRnn(2, 10, 3, loss=lambda x: T.log(x), max_iter=10) rnn.transform(X)
def test_usrnn_iter_fit(): X = np.random.standard_normal((10, 5, 2)) rnn = UnsupervisedRnn(2, 10, 3, loss=lambda x: T.log(x), max_iter=10) for i, info in enumerate(rnn.iter_fit(X)): if i >= 10: break