1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
|
from blocks import roles
from blocks.bricks import Rectifier, Tanh, Logistic
from blocks.filter import VariableFilter
from blocks.initialization import IsotropicGaussian, Constant
import data
from model.memory_network import Model, Stream
n_begin_end_pts = 10 # how many points we consider at the beginning and end of the known trajectory
dim_embeddings = [
('origin_call', data.origin_call_train_size, 10),
('origin_stand', data.stands_size, 10),
('week_of_year', 52, 10),
('day_of_week', 7, 10),
('qhour_of_day', 24 * 4, 10),
('day_type', 3, 10),
]
class MLPConfig(object):
__slots__ = ('dim_input', 'dim_hidden', 'dim_output', 'weights_init', 'biases_init')
prefix_encoder = MLPConfig()
prefix_encoder.dim_input = n_begin_end_pts * 2 * 2 + sum(x for (_, _, x) in dim_embeddings)
prefix_encoder.dim_hidden = [1000, 1000]
prefix_encoder.weights_init = IsotropicGaussian(0.01)
prefix_encoder.biases_init = Constant(0.001)
candidate_encoder = MLPConfig()
candidate_encoder.dim_input = n_begin_end_pts * 2 * 2 + sum(x for (_, _, x) in dim_embeddings)
candidate_encoder.dim_hidden = [1000, 1000]
candidate_encoder.weights_init = IsotropicGaussian(0.01)
candidate_encoder.biases_init = Constant(0.001)
representation_size = 1000
representation_activation = Tanh
normalize_representation = True
embed_weights_init = IsotropicGaussian(0.001)
dropout = 0.5
dropout_inputs = VariableFilter(bricks=[Rectifier], name='output')
noise = 0.01
noise_inputs = VariableFilter(roles=[roles.PARAMETER])
batch_size = 512
valid_set = 'cuts/test_times_0'
max_splits = 1
num_cuts = 1000
train_candidate_size = 10000
valid_candidate_size = 20000
|
