def test_model_not_criterion_subset():
input_dim = 2
proj_dim = 11
model1_dim = 3
model2_dim = 4
x = input_variable((input_dim,))
core = Embedding(proj_dim)
model1 = Dense(model1_dim)(sequence.last(core(x)))
model1_label = input_variable((model1_dim,), dynamic_axes=[Axis.default_batch_axis()])
ce_model1 = cross_entropy_with_softmax(model1, model1_label)
pe_model1 = classification_error(model1, model1_label)
model2 = Dense(model2_dim)(core(x))
model2_label = input_variable((model2_dim,))
ce_model2 = cross_entropy_with_softmax(model2, model2_label)
pe_model2 = classification_error(model2, model2_label)
ce = 0.5 * sequence.reduce_sum(ce_model2) + 0.5 * ce_model1
lr_schedule = learning_rate_schedule(0.003, UnitType.sample)
trainer_multitask = Trainer(model1, (ce, pe_model1), sgd(ce.parameters, lr=lr_schedule))
x_data = np.asarray([[2., 1.], [1., 2.]], np.float32)
model1_label_data = np.asarray([1., 0., 0.], np.float32)
model2_label_data = np.asarray([[0., 1., 0., 0.], [0., 0., 0., 1.]], np.float32)
trainer_multitask.train_minibatch({x : [x_data], model1_label : [model1_label_data], model2_label : [model2_label_data]})
def test_model_not_criterion_subset():
input_dim = 2
proj_dim = 11
model1_dim = 3
model2_dim = 4
x = sequence.input((input_dim, ))
core = Embedding(proj_dim)
model1 = Dense(model1_dim)(sequence.last(core(x)))
model1_label = input((model1_dim, ))
ce_model1 = cross_entropy_with_softmax(model1, model1_label)
pe_model1 = classification_error(model1, model1_label)
model2 = Dense(model2_dim)(core(x))
model2_label = sequence.input((model2_dim, ))
ce_model2 = cross_entropy_with_softmax(model2, model2_label)
pe_model2 = classification_error(model2, model2_label)
ce = 0.5 * sequence.reduce_sum(ce_model2) + 0.5 * ce_model1
lr_schedule = learning_rate_schedule(0.003, UnitType.sample)
trainer_multitask = Trainer(model1, (ce, pe_model1),
sgd(ce.parameters, lr=lr_schedule))
x_data = np.asarray([[2., 1.], [1., 2.]], np.float32)
model1_label_data = np.asarray([1., 0., 0.], np.float32)
model2_label_data = np.asarray([[0., 1., 0., 0.], [0., 0., 0., 1.]],
np.float32)
trainer_multitask.train_minibatch({
x: [x_data],
model1_label: [model1_label_data],
model2_label: [model2_label_data]
})
def LSTM_sequence_classifer_net(input, num_output_classes, embedding_dim,
LSTM_dim, cell_dim):
embedded_inputs = embedding(input, embedding_dim)
lstm_outputs = simple_lstm(embedded_inputs, LSTM_dim, cell_dim)[0]
thought_vector = sequence.last(lstm_outputs)
return linear_layer(thought_vector, num_output_classes)
def BiRecurrence(fwd, bwd):
F = C.layers.Recurrence(fwd)
G = C.layers.Recurrence(bwd, go_backwards=True)
x = C.placeholder()
apply_x = C.splice(sequence.last(F(x)), sequence.first(G(x)),name='h2')
return apply_x