def test_fd_srnn_fit(): X = np.random.standard_normal((10, 5, 2)).astype(theano.config.floatX) Z = np.random.standard_normal((10, 5, 3)).astype(theano.config.floatX) rnn = SupervisedFastDropoutRnn(2, [10], 3, hidden_transfer='rectifier', max_iter=10) rnn.fit(X, Z)
def test_fd_srnn_fit(): X = np.random.standard_normal((10, 5, 2)).astype(theano.config.floatX) Z = np.random.standard_normal((10, 5, 3)).astype(theano.config.floatX) X, Z = theano_floatx(X, Z) rnn = SupervisedFastDropoutRnn(2, [10], 3, hidden_transfers=['rectifier'], max_iter=10) rnn.fit(X, Z) rnn = SupervisedFastDropoutRnn( 2, [10, 20], 3, hidden_transfers=['rectifier', 'tanh'], skip_to_out=True, max_iter=10) rnn.fit(X, Z)
def test_fdsrnn_lstm_fit(): X = np.random.standard_normal((13, 5, 4)).astype(theano.config.floatX) Z = np.random.standard_normal((13, 5, 3)).astype(theano.config.floatX) W = np.random.standard_normal((13, 5, 3)).astype(theano.config.floatX) X, Z, W = theano_floatx(X, Z, W) rnn = SupervisedFastDropoutRnn(4, [10], 3, hidden_transfers=['lstm'], max_iter=2) rnn.mode = 'FAST_COMPILE' rnn.fit(X, Z)
def test_fdrnn_pickle(): X = np.random.standard_normal((10, 5, 2)).astype(theano.config.floatX) Z = np.random.standard_normal((10, 5, 3)).astype(theano.config.floatX) W = np.random.standard_normal((10, 5, 3)).astype(theano.config.floatX) X, Z, W = theano_floatx(X, Z, W) rnn = SupervisedFastDropoutRnn(2, [10], 3, hidden_transfers=['rectifier'], max_iter=2) rnn.fit(X, Z) rnn.predict(X) pickle.dumps(rnn)
def test_fd_srnn_fit(): X = np.random.standard_normal((10, 5, 2)).astype(theano.config.floatX) Z = np.random.standard_normal((10, 5, 3)).astype(theano.config.floatX) X, Z = theano_floatx(X, Z) rnn = SupervisedFastDropoutRnn(2, [10], 3, hidden_transfers=['rectifier'], max_iter=10) rnn.fit(X, Z) rnn = SupervisedFastDropoutRnn(2, [10, 20], 3, hidden_transfers=['rectifier', 'tanh'], skip_to_out=True, max_iter=10) rnn.fit(X, Z)
def test_fd_srnn_fit(): raise SkipTest() X = np.random.standard_normal((10, 5, 2)).astype(theano.config.floatX) Z = np.random.standard_normal((10, 5, 3)).astype(theano.config.floatX) W = np.random.standard_normal((10, 5, 3)).astype(theano.config.floatX) X, Z, W = theano_floatx(X, Z, W) rnn = SupervisedFastDropoutRnn(2, [10], 3, hidden_transfers=["rectifier"], max_iter=10) rnn.fit(X, Z) rnn = SupervisedFastDropoutRnn( 2, [10, 20], 3, hidden_transfers=["rectifier", "tanh"], skip_to_out=True, max_iter=10 ) rnn.fit(X, Z) rnn = SupervisedFastDropoutRnn( 2, [10, 20], 3, hidden_transfers=["rectifier", "tanh"], skip_to_out=True, max_iter=10, imp_weight=True ) rnn.fit(X, Z, W)