commit a6fdddce3f94913a0f8fadfcf8c74005e76c192e
parent 7dab7e47ce0e8c5ae996821794450a9ad3186cd3
Author: Étienne Simon <esimon@esimon.eu>
Date: Fri, 24 Jul 2015 16:10:55 -0400
Remove old memory network config files
Diffstat:
3 files changed, 0 insertions(+), 156 deletions(-)
diff --git a/config/memory_network_1.py b/config/memory_network_1.py
@@ -1,44 +0,0 @@
-from blocks.initialization import IsotropicGaussian, Constant
-
-import data
-from model.memory_network import Model, Stream
-
-
-n_begin_end_pts = 5 # 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 = [100, 100, 100]
-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 = [100, 100, 100]
-candidate_encoder.weights_init = IsotropicGaussian(0.01)
-candidate_encoder.biases_init = Constant(0.001)
-
-normalize_representation = True
-
-embed_weights_init = IsotropicGaussian(0.001)
-
-batch_size = 32
-
-max_splits = 1
-num_cuts = 1000
-
-train_candidate_size = 1000
-valid_candidate_size = 10000
diff --git a/config/memory_network_2.py b/config/memory_network_2.py
@@ -1,56 +0,0 @@
-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
-
-max_splits = 1
-num_cuts = 1000
-
-train_candidate_size = 10000
-valid_candidate_size = 20000
-
diff --git a/config/memory_network_3.py b/config/memory_network_3.py
@@ -1,56 +0,0 @@
-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 = [200, 200, 200]
-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 = [200, 200, 200]
-candidate_encoder.weights_init = IsotropicGaussian(0.01)
-candidate_encoder.biases_init = Constant(0.001)
-
-representation_size = 500
-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
-
-max_splits = 1
-num_cuts = 1000
-
-train_candidate_size = 10000
-valid_candidate_size = 20000
-
