def test_fprop_faster(self):
seed = 1234
repeat = 100
lstm = LSTM(input_size=DATA['features_size'],
hidden_sizes=[DATA['hidden_size']],
)
lstm.initialize(initer.UniformInitializer(seed))
lstm2 = LSTMFaster(input_size=DATA['features_size'],
hidden_sizes=[DATA['hidden_size']],
)
# Wi, Wo, Wf, Wm
# Make sure the weights are the same.
lstm2.layers_lstm[0].W.set_value(np.concatenate([lstm.layers_lstm[0].Wi.get_value(), lstm.layers_lstm[0].Wo.get_value(), lstm.layers_lstm[0].Wf.get_value(), lstm.layers_lstm[0].Wm.get_value()], axis=1))
lstm2.layers_lstm[0].U.set_value(np.concatenate([lstm.layers_lstm[0].Ui.get_value(), lstm.layers_lstm[0].Uo.get_value(), lstm.layers_lstm[0].Uf.get_value(), lstm.layers_lstm[0].Um.get_value()], axis=1))
input = T.tensor3('input')
input.tag.test_value = DATA['batch']
fprop = theano.function([input], lstm.get_output(input))
fprop2 = theano.function([input], lstm2.get_output(input))
fprop_time = measure("out = fprop(DATA['batch'])", repeat)
print("fprop time: {:.2f} sec.", fprop_time)
fprop2_time = measure("out = fprop2(DATA['batch'])", repeat)
print("fprop faster time: {:.2f} sec.", fprop2_time)
print("Speedup: {:.2f}x".format(fprop_time/fprop2_time))
out = fprop(DATA['batch'])
out2 = fprop2(DATA['batch'])
assert_array_equal(out, out2)
def test_fprop_mask_vs_not_mask(self):
activation = "tanh"
seed = 1234
repeat = 100
lstm = LSTM(input_size=DATA['features_size'],
hidden_sizes=[DATA['hidden_size']],
)
lstm.initialize(initer.UniformInitializer(seed))
lstm2 = LSTMFast(input_size=DATA['features_size'],
hidden_sizes=[DATA['hidden_size']],
)
lstm2.mask = sharedX(DATA['mask'])
# Wi, Wo, Wf, Wm
# Make sure the weights are the same.
lstm2.layers_lstm[0].W.set_value(np.concatenate([lstm.layers_lstm[0].Wi.get_value(), lstm.layers_lstm[0].Wo.get_value(), lstm.layers_lstm[0].Wf.get_value(), lstm.layers_lstm[0].Wm.get_value()], axis=1))
lstm2.layers_lstm[0].U.set_value(np.concatenate([lstm.layers_lstm[0].Ui.get_value(), lstm.layers_lstm[0].Uo.get_value(), lstm.layers_lstm[0].Uf.get_value(), lstm.layers_lstm[0].Um.get_value()], axis=1))
input = T.tensor3('input')
input.tag.test_value = DATA['batch']
fprop = theano.function([input], lstm.get_output(input))
fprop2 = theano.function([input], lstm2.get_output(input))
# fprop_time = measure("out = fprop(DATA['batch'])", repeat)
# print("fprop time: {:.2f} sec.", fprop_time)
out = fprop(DATA['batch'])
out2 = fprop2(DATA['batch'])
assert_true(out.sum != out2.sum())
assert_array_equal((out * DATA['mask'][:, :, None]),
(out2 * DATA['mask'][:, :, None]))
def test_fprop_mask_vs_not_mask(self):
activation = "tanh"
seed = 1234
repeat = 100
lstm = LSTM(
input_size=DATA['features_size'],
hidden_sizes=[DATA['hidden_size']],
)
lstm.initialize(initer.UniformInitializer(seed))
lstm2 = LSTMFast(
input_size=DATA['features_size'],
hidden_sizes=[DATA['hidden_size']],
)
lstm2.mask = sharedX(DATA['mask'])
# Wi, Wo, Wf, Wm
# Make sure the weights are the same.
lstm2.layers_lstm[0].W.set_value(
np.concatenate([
lstm.layers_lstm[0].Wi.get_value(),
lstm.layers_lstm[0].Wo.get_value(),
lstm.layers_lstm[0].Wf.get_value(),
lstm.layers_lstm[0].Wm.get_value()
],
axis=1))
lstm2.layers_lstm[0].U.set_value(
np.concatenate([
lstm.layers_lstm[0].Ui.get_value(),
lstm.layers_lstm[0].Uo.get_value(),
lstm.layers_lstm[0].Uf.get_value(),
lstm.layers_lstm[0].Um.get_value()
],
axis=1))
input = T.tensor3('input')
input.tag.test_value = DATA['batch']
fprop = theano.function([input], lstm.get_output(input))
fprop2 = theano.function([input], lstm2.get_output(input))
# fprop_time = measure("out = fprop(DATA['batch'])", repeat)
# print("fprop time: {:.2f} sec.", fprop_time)
out = fprop(DATA['batch'])
out2 = fprop2(DATA['batch'])
assert_true(out.sum != out2.sum())
assert_array_equal((out * DATA['mask'][:, :, None]),
(out2 * DATA['mask'][:, :, None]))
def test_fprop_faster(self):
seed = 1234
repeat = 100
lstm = LSTM(
input_size=DATA['features_size'],
hidden_sizes=[DATA['hidden_size']],
)
lstm.initialize(initer.UniformInitializer(seed))
lstm2 = LSTMFaster(
input_size=DATA['features_size'],
hidden_sizes=[DATA['hidden_size']],
)
# Wi, Wo, Wf, Wm
# Make sure the weights are the same.
lstm2.layers_lstm[0].W.set_value(
np.concatenate([
lstm.layers_lstm[0].Wi.get_value(),
lstm.layers_lstm[0].Wo.get_value(),
lstm.layers_lstm[0].Wf.get_value(),
lstm.layers_lstm[0].Wm.get_value()
],
axis=1))
lstm2.layers_lstm[0].U.set_value(
np.concatenate([
lstm.layers_lstm[0].Ui.get_value(),
lstm.layers_lstm[0].Uo.get_value(),
lstm.layers_lstm[0].Uf.get_value(),
lstm.layers_lstm[0].Um.get_value()
],
axis=1))
input = T.tensor3('input')
input.tag.test_value = DATA['batch']
fprop = theano.function([input], lstm.get_output(input))
fprop2 = theano.function([input], lstm2.get_output(input))
fprop_time = measure("out = fprop(DATA['batch'])", repeat)
print("fprop time: {:.2f} sec.", fprop_time)
fprop2_time = measure("out = fprop2(DATA['batch'])", repeat)
print("fprop faster time: {:.2f} sec.", fprop2_time)
print("Speedup: {:.2f}x".format(fprop_time / fprop2_time))
out = fprop(DATA['batch'])
out2 = fprop2(DATA['batch'])
assert_array_equal(out, out2)
