diff options
| -rw-r--r-- | config/memory_network_mlp_2.py | 10 | ||||
| -rw-r--r-- | config/memory_network_mlp_2_momentum.py | 10 | ||||
| -rw-r--r-- | config/memory_network_mlp_3_momentum.py | 55 |
3 files changed, 65 insertions, 10 deletions
diff --git a/config/memory_network_mlp_2.py b/config/memory_network_mlp_2.py index a64a4fc..33b4867 100644 --- a/config/memory_network_mlp_2.py +++ b/config/memory_network_mlp_2.py @@ -43,11 +43,11 @@ representation_activation = Tanh normalize_representation = True -batch_size = 100 -batch_sort_size = 20 +batch_size = 1000 +# batch_sort_size = 20 max_splits = 100 -train_candidate_size = 1000 -valid_candidate_size = 1000 -test_candidate_size = 1000 +train_candidate_size = 5000 +valid_candidate_size = 5000 +test_candidate_size = 5000 diff --git a/config/memory_network_mlp_2_momentum.py b/config/memory_network_mlp_2_momentum.py index 8a0ac81..483dfe8 100644 --- a/config/memory_network_mlp_2_momentum.py +++ b/config/memory_network_mlp_2_momentum.py @@ -45,11 +45,11 @@ normalize_representation = True step_rule = Momentum(learning_rate=0.01, momentum=0.9) -batch_size = 100 -batch_sort_size = 20 +batch_size = 1000 +# batch_sort_size = 20 max_splits = 100 -train_candidate_size = 1000 -valid_candidate_size = 1000 -test_candidate_size = 1000 +train_candidate_size = 5000 +valid_candidate_size = 5000 +test_candidate_size = 5000 diff --git a/config/memory_network_mlp_3_momentum.py b/config/memory_network_mlp_3_momentum.py new file mode 100644 index 0000000..5e1e4b2 --- /dev/null +++ b/config/memory_network_mlp_3_momentum.py @@ -0,0 +1,55 @@ +from blocks.initialization import IsotropicGaussian, Constant +from blocks.algorithms import Momentum + +from blocks.bricks import Tanh + +import data +from model.memory_network_mlp import Model, Stream + +n_begin_end_pts = 5 + +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), +] + +embed_weights_init = IsotropicGaussian(0.001) + +class MLPConfig(object): + __slots__ = ('dim_input', 'dim_hidden', 'dim_output', 'weights_init', 'biases_init', 'embed_weights_init', 'dim_embeddings') + +prefix_encoder = MLPConfig() +prefix_encoder.dim_input = n_begin_end_pts * 2 * 2 + sum(x for (_, _, x) in dim_embeddings) +prefix_encoder.dim_hidden = [500] +prefix_encoder.weights_init = IsotropicGaussian(0.01) +prefix_encoder.biases_init = Constant(0.001) +prefix_encoder.embed_weights_init = embed_weights_init +prefix_encoder.dim_embeddings = dim_embeddings + +candidate_encoder = MLPConfig() +candidate_encoder.dim_input = n_begin_end_pts * 2 * 2 + sum(x for (_, _, x) in dim_embeddings) +candidate_encoder.dim_hidden = [500] +candidate_encoder.weights_init = IsotropicGaussian(0.01) +candidate_encoder.biases_init = Constant(0.001) +candidate_encoder.embed_weights_init = embed_weights_init +candidate_encoder.dim_embeddings = dim_embeddings + +representation_size = 500 +representation_activation = Tanh + +normalize_representation = True + +step_rule = Momentum(learning_rate=0.01, momentum=0.9) + +batch_size = 500 +# batch_sort_size = 20 + +max_splits = 100 + +train_candidate_size = 2000 +valid_candidate_size = 2000 +test_candidate_size = 2000 |